BEGIN:VCALENDAR
VERSION:2.0
X-WR-CALNAME:agntconmcpconeu26
X-WR-CALDESC:Event Calendar
METHOD:PUBLISH
CALSCALE:GREGORIAN
PRODID:-//Sched.com AGNTCon + MCPCon Europe 2026//EN
X-WR-TIMEZONE:UTC
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T053000Z
DTEND:20260917T170000Z
SUMMARY:Registration & Badge Pick-Up
DESCRIPTION:\n
CATEGORIES:SPECIAL EVENTS / EXHIBITS / BREAKS
LOCATION:Onyx Lounge (Ground Level)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:9439645c550fcff40e77c59449459f7c
URL:http://agntconmcpconeu26.sched.com/event/9439645c550fcff40e77c59449459f7c
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T070000Z
DTEND:20260917T070500Z
SUMMARY:Keynote: Welcome - Angie Jones\, Vice President of Developer Experience\, The Agentic AI Foundation
DESCRIPTION:\n
CATEGORIES:KEYNOTE SESSIONS
LOCATION:Auditorium (Ground Level)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:a33aec1a98c9e77ac1b2d5556804a715
URL:http://agntconmcpconeu26.sched.com/event/a33aec1a98c9e77ac1b2d5556804a715
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T070500Z
DTEND:20260917T071500Z
SUMMARY:Keynote: Mazin Gilbert\, Executive Director\, The Agentic AI Foundation
DESCRIPTION:\n
CATEGORIES:KEYNOTE SESSIONS
LOCATION:Auditorium (Ground Level)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:a96f94632eec478290d3c91a583611b2
URL:http://agntconmcpconeu26.sched.com/event/a96f94632eec478290d3c91a583611b2
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T072000Z
DTEND:20260917T073000Z
SUMMARY:Keynote: Clare Liguori\, Senior Principal Engineer\, AWS Agentic AI
DESCRIPTION:\n
CATEGORIES:KEYNOTE SESSIONS
LOCATION:Auditorium (Ground Level)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:6e6f2a0798fa2937b99241a3a1e22960
URL:http://agntconmcpconeu26.sched.com/event/6e6f2a0798fa2937b99241a3a1e22960
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T073000Z
DTEND:20260917T074000Z
SUMMARY:Keynote: Getting to Stateless MCP: In Production - Shaun Smith\, Open Source Agents / MCP\, Hugging Face
DESCRIPTION:The latest MCP Specification introduces one of the largest changes to the protocol since launch: a stateless transport.At Hugging Face we use MCP as infrastructure for Agents\, Interactive and Inference workloads.&nbsp\;In this session we will:- Summarize the MCP Transport story to date&nbsp\;- Use production analytics from Hugging Face's MCP infrastructure to track migration metrics and success- Explore new opportunities for Client\, Server and Gateway implementations offered by the new transport features.- Share lessons learned from implementing the stateless transport for Clients and Servers
CATEGORIES:KEYNOTE SESSIONS
LOCATION:Auditorium (Ground Level)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:c1f445360eeb9275ef5515e19fc8f313
URL:http://agntconmcpconeu26.sched.com/event/c1f445360eeb9275ef5515e19fc8f313
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T074500Z
DTEND:20260917T080500Z
SUMMARY:Coffee Break
DESCRIPTION:\n
CATEGORIES:SPECIAL EVENTS / EXHIBITS / BREAKS
LOCATION:Solutions Showcse - Diamond Lounge\, Amsterdam\, Netherlands
SEQUENCE:0
UID:cb8ed3047f6fe6b3c91443e752f3266d
URL:http://agntconmcpconeu26.sched.com/event/cb8ed3047f6fe6b3c91443e752f3266d
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T074500Z
DTEND:20260917T173000Z
SUMMARY:Solutions Showcase
DESCRIPTION:\n
CATEGORIES:SPECIAL EVENTS / EXHIBITS / BREAKS
LOCATION:Diamond Lounge (Ground Level)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:cb20d84264544d57f2326bd9a95b1460
URL:http://agntconmcpconeu26.sched.com/event/cb20d84264544d57f2326bd9a95b1460
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T081000Z
DTEND:20260917T083500Z
SUMMARY:The Modern AI Stack: Agents\, MCP and Skills - Adewale Abati\, Block
DESCRIPTION:Agent harnesses. MCP. Skills. MCP Apps. If you've been watching the AI space and feeling like everyone else already understands something you don't\, this talk is for you.\n \n I've spent the last several months building with each layer of the modern AI stack\, and what I kept finding was that the concepts aren't as hard as the terminology makes them sound. Nobody had just sat down and explained what each piece actually is\, what problem it solves\, and how they fit together. So that's this talk. Technical enough to be useful\, grounded in real workflow experience\, and paced so that by the end you have a clear mental model of where AI tooling actually stands today and where you fit in it.
CATEGORIES:AGENTIC ENGINEERING
LOCATION:G102 + G103 (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:ac8657991703b1b888e03ed5f2014d2f
URL:http://agntconmcpconeu26.sched.com/event/ac8657991703b1b888e03ed5f2014d2f
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T081000Z
DTEND:20260917T083500Z
SUMMARY:From Personal Agent To Org Catalog: 13 Specialists\, One Orchestrator - Nick Veenhof\, GitLab
DESCRIPTION:Every team at our company was building agents from scratch. Duplicated prompts. Duplicated tool configs. No shared memory. I watched five teams present their setups at a meetup in Ghent. Same patterns\, reinvented five times. So I built Paul\, an AI chief of staff with 13 specialist agents: analyst\, writer\, broadcaster\, operator\, architect\, reviewer\, and more. Each agent has a defined job family\, a cultural perspective\, and a skill library. One orchestrator delegates. A reviewer gates quality. The whole system runs on open source tooling with MCP servers for memory\, calendar\, email\, GitLab\, and smart home. The sharing layer is a platform AI catalog. Agent definitions\, flows\, and MCP server configs become organizational assets. A team publishes an agent. Another team reuses it. Skills are composable. Memory is scoped: user\, project\, or org. This talk covers the architecture\, the real failures\, and the pattern for moving from a personal experiment to an organizational capability. You leave with concrete agent definitions\, delegation patterns\, and a mental model for building a catalog your whole organization can use.
CATEGORIES:ENTERPRISE ADOPTION IN PRACTICE
LOCATION:Auditorium (Ground Level)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:cbf2b2063ed4a305936e7d6672e7e7eb
URL:http://agntconmcpconeu26.sched.com/event/cbf2b2063ed4a305936e7d6672e7e7eb
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T081000Z
DTEND:20260917T083500Z
SUMMARY:What Does It Take To Ship a New MCP Spec - Den Delimarsky\, Anthropic
DESCRIPTION:An end-to-end deep dive into how a new spec goes from idea to a production\, stable release. In this session\, you will learn more about the MCP governance process\, Spec Enhancement Proposals (SEPs) and how all of this work translates into a brand-new MCP spec that then is adopted by the agentic space at large!
CATEGORIES:MCPCON
LOCATION:Emerald Room (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:3d842d83855592f0f93f749abc5a09e8
URL:http://agntconmcpconeu26.sched.com/event/3d842d83855592f0f93f749abc5a09e8
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T081000Z
DTEND:20260917T084500Z
SUMMARY:Workshop to be Announced
DESCRIPTION:\n
CATEGORIES:WORKSHOP
LOCATION:G106 + G107 (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:e190753c9a27025eebdb6e7e15e006f9
URL:http://agntconmcpconeu26.sched.com/event/e190753c9a27025eebdb6e7e15e006f9
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T084500Z
DTEND:20260917T091000Z
SUMMARY:Legal Implications Under EU Law When Deploying AI Agents - Mirela Takacs\, Law Office Takacs Mirela
DESCRIPTION:This presentation highlights general rules that any engineer should keep in mind before implementing an AI agent\, around one core idea: legislation should be treated as part of the system architecture. At EU level\, the AI Act is the central regulation\, but adjacent European legislation may also be activated based on the AI agent’s actions.\n Translating legal obligations into technical requirements from the design stage makes deployment safer and more compliant. Five practical takeaways help in doing that:\n 1. compliance should not be seen as a one-time check\, but as a continuous monitoring and evaluation process\n 2. it demands interdisciplinary work from the design phase\, not a back-and-forth decision chain\n 3. the agent is a system\, not a legal person\, so the ones held accountable are the humans behind it\n 4. a clear map of what the agent does\, accesses\, and produces is what lets you navigate the law \n 5. there is no universal rule applicable: start with the AI Act\, then identify the adjacent legislation activated by the agent’s specific functions\n The goal is to design agents that are safe\, compliant and genuinely useful\, by treating law as an architectural concern\, not bureaucracy.
CATEGORIES:AGENTIC ENGINEERING
LOCATION:G102 + G103 (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:42c9a055275fc191f23220c546c8a8ad
URL:http://agntconmcpconeu26.sched.com/event/42c9a055275fc191f23220c546c8a8ad
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T084500Z
DTEND:20260917T091000Z
SUMMARY:Sponsored Session: Beyond the Easy 80%: Bringing Legacy\, Spatial\, and Locked-Down Data to MCP - Don Murray\, Safe Software
DESCRIPTION:AI models are becoming a commodity. GPT-4\, Claude\, Gemini. &nbsp\;Pick one\, swap it next quarter\, and the differentiation has already moved on. What hasn't moved is context: the data an agent can actually reach. Most of today's MCP ecosystem wraps the easy 80 percent. &nbsp\;SaaS APIs\, ticketing systems\, chat platforms\, anything that already had a REST endpoint. The other 20 percent: legacy databases running since the 1980s\, CAD/BIM/GIS formats\, real-time sensor and SCADA feeds\, regulated records that legally can't leave the building\, and hybrid environments split across cloud and on-prem by design\, &nbsp\;still have no real path to an agent. In most enterprises\, that's exactly where the decision-relevant data lives.&nbsp\;\nDrawing on 32 years building spatial and enterprise data integration\, this talk looks at what it actually takes to expose hard\, hybrid\, and on-prem data as MCP tools: treating data workflows as callable tools instead of one-off scripts\, separating the control plane (what an agent is allowed to call) from execution (where the data actually lives and stays)\, and building both directions\, consuming MCP tools and exposing your own\, without hardwiring to one model or vendor.&nbsp\;
CATEGORIES:INTEROPERABILITY & STANDARDS
LOCATION:G104 + G105 (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:b64de80d15aa7d2c3aa1d7a3b7bec8d5
URL:http://agntconmcpconeu26.sched.com/event/b64de80d15aa7d2c3aa1d7a3b7bec8d5
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T084500Z
DTEND:20260917T091000Z
SUMMARY:Stateless: The Future of MCP Transports - Kurtis Van Gent\, Google
DESCRIPTION:MCP is becoming stateless in one of the largest changes to the protocol since its launch. \n \n This change simplifies the deployment of robust servers\, making MCP ready for the next wave of scaled usage driven by agents and use cases like MCP Apps. \n \n This session led by members of the Transports Working Group:\n - Explores the upcoming changes - and sharing real data from Google and Hugging Face on the motivation behind them.\n - Details the latest approaches on handling serverless Elicitation\, Sampling and Sessions.\n - Introduces the application and infrastructure patterns that can take advantage of the stateless protocol.\n \n We'll also update on the latest roadmap status and expected migration timelines and approach
CATEGORIES:MCPCON
LOCATION:Emerald Room (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:b49c7410bc17e60971fd9f784a4c358b
URL:http://agntconmcpconeu26.sched.com/event/b49c7410bc17e60971fd9f784a4c358b
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T084500Z
DTEND:20260917T091000Z
SUMMARY:An Orchestra of Agents: What I Learned Running a Multi-Agent System for 5\,000+ Developers - Muhammad Ahsan Ayaz\, Scania
DESCRIPTION:Most "AI agents" are a single LLM wrapped in a system prompt. They look great in demos and collapse the moment real users show up. I know because I built one for my 5\,000+ member developer community\, and the first version broke in ways I didn't see coming.\n In this talk\, I'll walk through the multi-agent system I run in production: a tree of 12 specialist agents built on Google's ADK\, coordinating through sequential pipelines\, parallel fan-out\, and LLM-driven dynamic routing\, each armed with MCP tools to act on the real world. We'll cover the orchestration primitives\, then climb into the real architecture: how onboarding chains three agents in sequence\, how external knowledge fans out across GitHub\, Dev.to\, and StackOverflow in parallel\, and how the root agent delegates per message.\n Then the fun part: the bugs. The drain-loop that cancelled a ParallelAgent mid-flight. The recency drift that surfaced 2020 articles in 2026. The callback layer I had to build for PII sanitization\, caching\, and observability \; none of which made it into the tutorial.\n You'll leave with a mental model for each pattern\, production patterns that kept it running\, and war stories that'll save you a week.
CATEGORIES:MULTI-AGENT & DISTRIBUTED SYSTEMS
LOCATION:Auditorium (Ground Level)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:80826fbc5cc99019699571a6395ab758
URL:http://agntconmcpconeu26.sched.com/event/80826fbc5cc99019699571a6395ab758
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T092000Z
DTEND:20260917T094500Z
SUMMARY:When NOT To Use an Agent: Choosing Between Workflows\, Services\, and Agent Systems - Jigyasa Grover\, Uber & Rishabh Misra\, Atlassian
DESCRIPTION:LLM-powered “agents” are quickly becoming the default architectural pattern for AI-enabled systems. Need automation? Agent. Need integration? Agent. Need reasoning? Agent. But agents are not an upgrade\; they are a trade-off. They introduce non-determinism\, larger attack surfaces\, evaluation complexity\, and operational unpredictability. In this session\, we’ll examine three common architectural patterns for LLM-enabled systems: - Deterministic workflows (state machines\, orchestrated pipelines) - Service-oriented architectures with LLM augmentation - Fully agentic orchestration with dynamic tool use Rather than comparing features\, we’ll analyze these patterns across real engineering constraints: - Failure isolation and blast radius - Latency and cost predictability - Observability and debugging complexity - Security boundaries and permission scoping - Evaluation and regression testing strategy - Operational burden over time This talk offers a practical decision framework grounded in system design principles. You’ll leave with a mental model and checklist to evaluate whether an agent is justified\, or whether a simpler architecture will deliver more predictable\, resilient outcomes.
CATEGORIES:AGENTIC ENGINEERING
LOCATION:Auditorium (Ground Level)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:59ef4419bf81f6a3064248ecb37c5f5f
URL:http://agntconmcpconeu26.sched.com/event/59ef4419bf81f6a3064248ecb37c5f5f
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T092000Z
DTEND:20260917T094500Z
SUMMARY:CHAP\, an Open Protocol for Auditable Human-Agent Collaboration - Dr Arsalan Shahid\, Brightbeam AI
DESCRIPTION:\n \n The next phase of agents is not one human supervising one model. It is multi-human\, multi-agent work across teams\, tools\, and trust boundaries. The decisive moments are not model outputs\; they are human approvals\, edits\, overrides\, escalations\, and handoffs\, and the rationale behind them. Today those moments leak into chat logs\, tickets\, and application code\, where they cannot be replayed or audited.\n \n CHAP\, the Collaborative Human-Agent Protocol\, gives this shared workspace a protocol layer. A small Core (workspaces\, participants\, tasks\, artefacts\, and an append-only evidence log) carries composable profiles for review\, structured override\, operating modes\, handoff\, deliberation\, identity\, and signed audit. It composes with MCP and A2A rather than replacing them: MCP connects agents to tools\, A2A connects agents to agents\, CHAP lets humans and agents do accountable work together.\n \n The talk covers the protocol gap\, the Core primitives\, a worked 'override as evidence' flow\, and lessons from building the open reference implementations and conformance harness. Spec\, code\, and examples are public.\n \n Paper: https://arxiv.org/abs/2606.09751\n Repo: https://github.com/BrightbeamAI/chap
CATEGORIES:HUMAN-AGENT COLLABORATION
LOCATION:G102 + G103 (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:2d29d0fef15d58a45879b1b1323352fb
URL:http://agntconmcpconeu26.sched.com/event/2d29d0fef15d58a45879b1b1323352fb
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T092000Z
DTEND:20260917T094500Z
SUMMARY:Call Now\, Fetch Later: Durable MCP Tasks on an Event Log - Jeremy Frenay\, Lenses
DESCRIPTION:MCP's new Tasks primitive makes tool calls asynchronous: a request returns a durable handle now\, and the result arrives later. That's the right model for work that runs for minutes or hours\, like ETL jobs\, deep research\, or batch reasoning\, but the spec leaves the hard parts to implementers. \n Where does in-flight work live? How does a task survive a restart? How do you deliver a result exactly once and let multiple clients subscribe to it?\n \n This talk argues that an append-only event log is a natural backend\, because a Task is a state machine and a state machine's history is just an ordered log of its transitions. We walk a concrete\, vendor-neutral implementation: creation\, status\, and completion become events\, recovery becomes replay\, and the server can go stateless\, lining up with MCP's roadmap. We dig into the failure modes that bite in production: orphaned tasks\, duplicate side effects\, and at-least-once versus exactly-once delivery\, plus the gaps the 2026 roadmap is still closing around retry and expiry.\n \n You'll leave with a reference architecture you can build on any log or queue\, and an honest view of what Tasks gives you today and what it doesn't yet.
CATEGORIES:MCPCON
LOCATION:Emerald Room (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:7e47fcddb7c291d6319a253a780dd577
URL:http://agntconmcpconeu26.sched.com/event/7e47fcddb7c291d6319a253a780dd577
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T095500Z
DTEND:20260917T102000Z
SUMMARY:The Other 90%: Agentic AI for the Legacy Codebases Nobody Wants To Touch - Ayush Bhardwaj\, Siemens
DESCRIPTION:The AI coding conversation has been almost entirely about greenfield: new features\, fresh repos\, throwaway scripts. Meanwhile the codebases that quietly run hospitals\, factories\, and banks are maintained by skeleton crews drowning in tribal knowledge\, dead build systems\, and 20-year-old decisions. Single-LLM code assistants do not survive contact with them.\n Agentic systems can\, but only with very different workflow patterns than the ones usually demoed. This session is a field report from modernizing a long-lived industrial codebase: what worked\, what catastrophically did not\, and the patterns that emerged.\n We cover the shift from "LLM completes my code" to "agents reason about my codebase": the two-loop research and execute split\, vertical slicing\, measurement-first execution\, structured unknowns\, and rollback discipline. We name the failure modes that wreck naive setups on legacy code\, including context overflow\, hallucinated APIs\, false-positive fixes\, and agentic drift\, and the practices that prevent them.\n It closes with where agents still lose\, what OSS tooling is missing\, and how the community can treat legacy maintenance as a first-class agentic AI problem.
CATEGORIES:AGENTIC ENGINEERING
LOCATION:Auditorium (Ground Level)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:fe8db7db56aaa3bdca5cb4614adf330c
URL:http://agntconmcpconeu26.sched.com/event/fe8db7db56aaa3bdca5cb4614adf330c
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T095500Z
DTEND:20260917T102000Z
SUMMARY:MCP Conformance Testing V1.0\, Testing the 2026-07-28 Spec in SDK's and Online - Paul Carleton\, Anthropic
DESCRIPTION:MCP Conformance testing is a set of tools for ensuring SDK's implement the spec in a way that's compatible with each other.\n \n The most recent spec revision 2026-07-28 is the first release that requires conformance testing as a part of the Specification Enhancement Proposal (SEP) process. This talk will go over lessons learned from the rollout of that specification\, and also introduce hosted conformance testing that clients and servers can use to test their deployed implementations.
CATEGORIES:MCPCON
LOCATION:Emerald Room (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:8648b45cda74cfa4f5d95ef0db40ab7d
URL:http://agntconmcpconeu26.sched.com/event/8648b45cda74cfa4f5d95ef0db40ab7d
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T095500Z
DTEND:20260917T102000Z
SUMMARY:From Opaque To Observable: Tracing Multi-Agent OpenClaw Workflows With OpenTelemetry - Pavan Sudheendra\, Cisco Systems
DESCRIPTION:Agent systems are getting more capable\, but they are still hard to operate when a single user request fans out across multiple agents\, tools\, model calls\, queues\, and outbound messages. In this session\, we will walk through how we built an open observability plugin for OpenClaw (InsightClaw) that turns that opaque execution path into a connected telemetry story using OpenTelemetry.\n \n The talk covers a practical design that combines three signal paths: typed lifecycle hooks for request\, agent\, tool\, and response flow\; diagnostics events for model usage\, cost\, queue\, webhook\, and stuck-session signals\; and optional provider SDK auto-instrumentation for GenAI calls. Together\, these produce connected traces\, useful operational metrics\, and cross-session lineage for handoffs\, spawned subagents\, and parallel branches.\n \n We will show the trace model we used\, the session semantics we had to define for real workflows\, and the engineering tradeoffs around payload capture\, runtime patching\, and correlating control-plane events with agent execution.
CATEGORIES:OPEN TOOLING
LOCATION:G102 + G103 (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:83f37169e46203cae13266651a163234
URL:http://agntconmcpconeu26.sched.com/event/83f37169e46203cae13266651a163234
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T095500Z
DTEND:20260917T113000Z
SUMMARY:Workshop to be Announced
DESCRIPTION:\n
CATEGORIES:WORKSHOP
LOCATION:G106 + G107 (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:00f406e2e624124e75ebda56dce6b639
URL:http://agntconmcpconeu26.sched.com/event/00f406e2e624124e75ebda56dce6b639
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T103000Z
DTEND:20260917T105500Z
SUMMARY:We Built AI Agents To Fix Security Findings in Production — Here's What Developers Actually Merged - Amine Boudraa\, Ruchita Kshirsagar\, Nihit Gupta & Gianfranco Romani\, Thomson Reuters
DESCRIPTION:AI is accelerating vulnerability discovery\, finding more security issues than any team can fix by hand. The obvious next step is letting AI fix them too\, but pushing automated changes into production is difficult\, and the trust bar is super high.\n \n Over the past year\, we built and shipped two autonomous remediation agents raising PRs against hundreds of production repositories: one for SAST findings in first-party code\, and one for SCA findings in third-party libraries. While developers can already fix vulnerabilities by going back and forth with a general-purpose AI assistant\, our goal is to make that loop faster and more trustworthy.\n \n That trust came from unglamorous engineering: teaching our agents how to build and test an application\, trace data flows to reject risky fixes\, and resolve breaking changes when modernizing legacy code. Along the way\, we’ll share common patterns we’ve seen across rejected PRs\, and what we had to iterate on to get hundreds of them merged.\n \n We are open sourcing both agents for the community. The volume of CVEs keeps growing\, automated remediation will become a must\, and existing solutions don't yet solve this problem at the level we need.
CATEGORIES:ENTERPRISE ADOPTION IN PRACTICE
LOCATION:Auditorium (Ground Level)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:2747326638cb2d4adbf1773fffdfbfe1
URL:http://agntconmcpconeu26.sched.com/event/2747326638cb2d4adbf1773fffdfbfe1
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T103000Z
DTEND:20260917T105500Z
SUMMARY:A2A Goes Stable: What Changed\, Why\, and What's Next - Sam Betts\, Cisco Systems & Kuba Herczyński\, Google
DESCRIPTION:A2A Protocol v1.0 is the first stable\, production-ready release of the open standard for agent-to-agent communication — marking the transition from a protocol you could experiment with to a foundation organisations can commit to with confidence.\n \n This talk is delivered by two maintainers who helped shape the release. We cover what changed from v0.3 and why: the deliberate choice to prioritise maturity over reinvention\, new enterprise capabilities — signed Agent Cards\, multi-tenancy\, modern OAuth flows\, and a web-aligned architecture — and the breaking changes that were unavoidable on the path to a durable standard.\n \n We also cover the SDK story: how official SDKs support v1.0 while maintaining backward compatibility with v0.3\, and a per-interface versioning strategy that makes progressive migration practical rather than a forced cutover.\n \n Finally\, we look at extensibility: how extensions add capabilities while keeping a stable core\, and how custom protocol bindings let implementations replace the default transport while preserving A2A semantics.\n \n If you are building on A2A today or evaluating it\, this talk gives you a clear picture of what changed\, why\, and how to migrate.
CATEGORIES:INTEROPERABILITY & STANDARDS
LOCATION:G102 + G103 (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:c705cc6b88f10076b19b6b29c22b4471
URL:http://agntconmcpconeu26.sched.com/event/c705cc6b88f10076b19b6b29c22b4471
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T103000Z
DTEND:20260917T105500Z
SUMMARY:MCP Doesn't Have a Context Problem - Sam Morrow\, GitHub
DESCRIPTION:People frequently assume MCP requires tools to be dumped straight into the system prompt\, and responses to be returned straight to the model. Critics say the protocol has a context problem\, that CLIs and agent skills are more efficient and composable. They're right about the symptoms\, but wrong about the diagnosis. The problem isn't MCP - it's for a long time few had applied serious context engineering to it.\n \n Through a self-built agent harness (mcpi)\, I will demonstrate three complementary strategies for progressive tool discovery over MCP - each paying only the context tokens it needs.\n \n This talk focuses on the most transformative of the three: skills over MCP that describe the tool surface\, and progressively enable tools upon skill invocation. I will also look at MCP CLIs and Code Mode approaches\, and show how they can complement each other with their different strengths.\n \n Attendees will leave with practical patterns they can implement in their own MCP servers and agent harnesses today.
CATEGORIES:MCPCON
LOCATION:Emerald Room (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:8f016a545ccf11a82b80612d0b35cd2d
URL:http://agntconmcpconeu26.sched.com/event/8f016a545ccf11a82b80612d0b35cd2d
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T110500Z
DTEND:20260917T113000Z
SUMMARY:What *IS* an Agent's Identity? - Christian Posta\, Solo.io
DESCRIPTION:Enterprises understand human identity fairly well. You could argue they are decent at service accounts. But what about an AI agent? Is it either of these? Agents are driven by intent\, discover/invoke tools\, make decisions\, and interact with other resources (APIs\, databases\, other agents\, etc). Enterprises will care about "Who is this agent?"\, "What is it allowed to do?"\, "What has it done?" and of course "Can we revoke its authority?" In this talk we'll break down what actually makes up an agent's identity. We'll look at authentication\, delegated authority\, provenance\, trust establishment\, and accountability. We'll also examine where technologies like OAuth\, OpenID Connect\, SPIFFE\, and emerging efforts such as AAuth fit into the picture. You'll leave with a practical framework for thinking about agent identity\, which problems have already been solved\, and which ones we're still figuring out.
CATEGORIES:ENTERPRISE ADOPTION IN PRACTICE
LOCATION:Auditorium (Ground Level)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:c1be08166f7bd5326366168c39e58fe7
URL:http://agntconmcpconeu26.sched.com/event/c1be08166f7bd5326366168c39e58fe7
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T110500Z
DTEND:20260917T113000Z
SUMMARY:Cleared for Landing: Designing MCP Servers for Long-Horizon Agents - Casey Chow\, OpenAI
DESCRIPTION:As agents evolve from quick tool calls to work that unfolds over hours or even days\, MCP servers need to do more than expose tools. They need to teach agents what work they are suited for\, how to sequence it\, how to monitor progress\, when to involve a human\, and recognize when results have actually landed.\n \n This talk presents a practical quality bar for MCP servers that support long-horizon agentic work. We'll discuss patterns for describing capabilities\, guiding workflows\, coordinating changes across services and validating outcomes\, drawing on lessons from building effective MCP apps and plugins inside of ChatGPT and Codex. These patterns let us separate enduring design principles from changing protocol details\, and discuss how today’s servers can adapt as tasks\, triggers\, resources\, skills\, and related MCP capabilities evolve.
CATEGORIES:MCPCON
LOCATION:Emerald Room (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:b7271a5f69a1eb58a9f232320c9e5cbb
URL:http://agntconmcpconeu26.sched.com/event/b7271a5f69a1eb58a9f232320c9e5cbb
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T110500Z
DTEND:20260917T113000Z
SUMMARY:Composable\, Low-code Agent Systems With the Tools You Already Have - Adam Jones\, Anthropic
DESCRIPTION:You don't write a pile of glue code to onboard a new hire — you give them an account and point them at a few channels. So why do we hardcode workflows and wire up orchestration SDKs to put AI agents to work? There's a lighter path: let agents coordinate the way people already do — by tagging each other and posting into channels — so the system is something you own and shape rather than something you engineer. This talk makes the case for that low-code\, team-owned approach\, the patterns that make it work\, and the surprising amount of custom infrastructure it lets you delete.
CATEGORIES:MULTI-AGENT & DISTRIBUTED SYSTEMS
LOCATION:G102 + G103 (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:cfb19734e38ec49eddee30cd8ae00cb8
URL:http://agntconmcpconeu26.sched.com/event/cfb19734e38ec49eddee30cd8ae00cb8
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T113000Z
DTEND:20260917T124500Z
SUMMARY:Lunch (Provided Onsite for Attendees)
DESCRIPTION:\n
CATEGORIES:SPECIAL EVENTS / EXHIBITS / BREAKS
LOCATION:Solutions Showcse - Diamond Lounge\, Amsterdam\, Netherlands
SEQUENCE:0
UID:ca6b256b7b8f71b363b78548b6db236a
URL:http://agntconmcpconeu26.sched.com/event/ca6b256b7b8f71b363b78548b6db236a
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T124500Z
DTEND:20260917T125000Z
SUMMARY:Welcome Back - Angie Jones\, Vice President of Developer Experience\, The Agentic AI Foundation
DESCRIPTION:\n
CATEGORIES:KEYNOTE SESSIONS
LOCATION:Auditorium (Ground Level)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:4352718f5d0edbfb486946752b594e77
URL:http://agntconmcpconeu26.sched.com/event/4352718f5d0edbfb486946752b594e77
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T125200Z
DTEND:20260917T130200Z
SUMMARY:Keynote: David Soria Parra\, Member of Technical Staff\, Anthropic
DESCRIPTION:\n
CATEGORIES:KEYNOTE SESSIONS
LOCATION:Auditorium (Ground Level)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:37aeff733c2487b258d861719dcf8f21
URL:http://agntconmcpconeu26.sched.com/event/37aeff733c2487b258d861719dcf8f21
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T130200Z
DTEND:20260917T132500Z
SUMMARY:Keynotes to Announced
DESCRIPTION:\n
CATEGORIES:KEYNOTE SESSIONS
LOCATION:Amsterdam\, Netherlands
SEQUENCE:0
UID:476e11cd76216cff8cfde808f1063d97
URL:http://agntconmcpconeu26.sched.com/event/476e11cd76216cff8cfde808f1063d97
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T132500Z
DTEND:20260917T133500Z
SUMMARY:Keynote: Arun Gupta\, Director\, Open Source Ecosystem & Developer Platform\, NVIDIA
DESCRIPTION:\n
CATEGORIES:KEYNOTE SESSIONS
LOCATION:Auditorium (Ground Level)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:cc4eddf1fe2bce91e12b117686f5e525
URL:http://agntconmcpconeu26.sched.com/event/cc4eddf1fe2bce91e12b117686f5e525
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T134500Z
DTEND:20260917T141000Z
SUMMARY:Your Agent Has a Wallet. Who Has the Receipts? - Bharath Nallapeta\, Mirantis Inc.
DESCRIPTION:In one year\, agents went from unable to pay for anything to spoiled for choice. x402 (Coinbase\, now Linux Foundation) for machine-to-machine. AP2 (Google\, donated to the FIDO Alliance) for signed payment mandates. ACP (OpenAI and Stripe) for checkout. MPP (Stripe and Tempo\, launched March 2026) for streamed micropayments against a pre-authorized session. Four protocols\, four layers\, real volume.\n \n What none of them owns is the part that decides whether an agent is allowed to spend this\, now\, on this. MCP returns HTTP 402 inside a tool call\, but it has no concept of a budget\, an attribution\, or an audit trail. The vendor bolt-ons are already multiplying and fragmenting.\n \n And the question stopped being academic. US regulators now treat agent purchases as ordinary card transactions\, Europe is moving to put liability on whoever deployed the agent unless they can produce the mandate and audit trail. The receipts are now a legal requirement with no standard home.\n \n This talk maps the four-protocol stack\, shows the MCP payment handshake live\, and argues for the one layer the agent economy is still missing.
CATEGORIES:AGENTIC COMMERCE
LOCATION:G104 + G105 (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:9247720f625508b1d66e6846ab0ab949
URL:http://agntconmcpconeu26.sched.com/event/9247720f625508b1d66e6846ab0ab949
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T134500Z
DTEND:20260917T141000Z
SUMMARY:Six Months of Proof: Independently-Verifiable Records for Agent Actions Under the EU AI Act - Steven Mih\, Action State Group\, Inc.
DESCRIPTION:The EU AI Act makes "what did the agent actually do?" a legal obligation: high-risk AI must support automatic record-keeping over its lifetime (Article 12) — for traceability\, human oversight\, and post-market monitoring — with logs retained at least six months (Article 19). But the Act can only require the logs to exist\, not to be trustworthy: a log is only as good as the party that keeps it\, and the operator who ran the action is not a disinterested witness — even an immutable one can be incomplete\, cherry-picked\, or built after the fact. The fix is simple and old: anchoring. Commit each record to a hash\, write that hash to an independent\, append-only transparency log\, and any party can verify what the agent did — without trusting the operator. This session shows how the Agent Action Capsule project uses open transparency-log standards (SCITT/COSE) to produce anchored\, independently-verifiable records of agent actions to the letter of the Act\, plus the trust it can't legislate. \n \n Live demo of the Agent Action Capsule project: emit a record at an action boundary\, anchor it\, verify it with an open verifier\, then tamper and watch verification fail. You'll leave with an open\, framework-agnostic pattern mapped to Article 12/19 — and a running verifier to try.
CATEGORIES:INTEROPERABILITY & STANDARDS
LOCATION:Auditorium (Ground Level)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:adfb289902647c8485080a968335fcc3
URL:http://agntconmcpconeu26.sched.com/event/adfb289902647c8485080a968335fcc3
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T134500Z
DTEND:20260917T141000Z
SUMMARY:MCP in Production: Reliability Contracts for Multi-Agent Tool Use - Krishna Chaitanya\, Meta Platforms
DESCRIPTION:MCP creates a common way for models to use tools\, but production use still breaks down when reliability expectations are left implicit. This talk argues that MCP systems need explicit reliability contracts covering permission boundaries\, tool-call semantics\, retries\, observability\, and recovery behavior. It will show how multi-step failures emerge in real tool-use chains and how traces\, evals\, and protocol-aware safeguards can make those failures debuggable instead of mysterious. The session also covers design patterns for graceful degradation when tools\, transport layers\, or model reasoning do not behave as expected. Attendees will leave with a concrete framework for making MCP-based systems more trustworthy in real deployments.
CATEGORIES:MCPCON
LOCATION:Emerald Room (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:66c6ed6c74c668fb5135086694312c1c
URL:http://agntconmcpconeu26.sched.com/event/66c6ed6c74c668fb5135086694312c1c
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T134500Z
DTEND:20260917T141000Z
SUMMARY:Sandboxing My AI Agent\, One Layer at a Time - Juan Antonio Osorio\, Stacklok Inc.
DESCRIPTION:We hand coding agents our workspace\, our keys\, and a shell\, then walk away while they run code generated at runtime from untrusted input: files in the repo\, docs fetched off the web\, output from MCP servers nobody audited. The obvious fix is isolation: give every agent its own kernel. So we start there\, running Claude Code\, Codex\, and others inside sub-second\, hardware-isolated microVMs (libkrun/KVM)\, where even root in the guest is stuck behind the hypervisor's MMU boundary\, not just a shared-kernel namespace.\n \n But isolation on its own isn't enough. An isolated agent can still read the .env beside your code\, exfiltrate it\, wreck your workspace\, or abuse a tool you never vetted. So we add defenses\, live\, one layer at a time: copy-on-write workspace snapshots with a per-file review gate\, non-overridable secret exclusions\, a DNS-aware egress firewall\, a hardened Wolfi guest (custom Go PID 1\, dropped capabilities\, seccomp\, no-new-privs)\, and an MCP proxy with Cedar authorization profiles. We finish on the attack surface most tools forget: the security tool's own config.\n \n It's all Apache-2.0. The lesson carries to any agent you run: isolation is the floor\, not the ceiling.
CATEGORIES:OPEN TOOLING
LOCATION:G102 + G103 (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:fafe8a807af18ab835c8d7ba5ea212f8
URL:http://agntconmcpconeu26.sched.com/event/fafe8a807af18ab835c8d7ba5ea212f8
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T142000Z
DTEND:20260917T144500Z
SUMMARY:90 Days To Agentic Engineering - Thomas Schöne\, Project Lions Development GmbH
DESCRIPTION:Most software companies are experimenting with AI\, yet many struggle to move beyond isolated chat interactions and proof-of-concepts.\n \n This session presents a practical case study of how a traditional software development organization with little prior AI experience adopted agentic engineering practices within 90 days. Guided by an engineer with hands-on experience in AI agents\, MCP\, RAG systems\, and AI-native development workflows\, the organization moved from sporadic experimentation to productive use of agentic systems in everyday engineering work.\n \n Attendees will learn how high-value use cases were identified\, how MCP-based tools\, agent skills\, and RAG-powered knowledge systems were introduced\, and how trust in agent-driven workflows was established across development teams.\n \n Not every experiment succeeded. Some assumptions proved wrong\, some tools disappointed\, and several approaches had to be reworked. This session shares the lessons learned\, the mistakes made\, and the strategies that ultimately accelerated adoption.\n \n The result was a measurable shift from AI curiosity to AI-enabled engineering\, establishing the foundations for long-term AI-native development.
CATEGORIES:AGENTIC ENGINEERING
LOCATION:Auditorium (Ground Level)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:570eef4043281bc527c2f99d51311ddf
URL:http://agntconmcpconeu26.sched.com/event/570eef4043281bc527c2f99d51311ddf
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T142000Z
DTEND:20260917T144500Z
SUMMARY:Agentic AI for Enterprise Mainframes: From Dead Code Elimination To Business Knowledge - Thamarai Selvi Ravi Kumar\, Legal and General
DESCRIPTION:Enterprise mainframe systems often contain large amounts of unused and unreachable code\, increasing complexity and risk. Safely removing this logic is difficult due to deeply interconnected execution paths.\n \n In this session\, I present a real-world case study where we delivered large-scale dead code remediation into production with zero incidents using an MCP-powered agentic AI approach.\n \n We developed specialised AI agents\, backed by Python tooling\, to analyse code\, detect unused logic\, and support safe\, auditable remediation with human validation. This reduced analysis time from days to under an hour per program.\n \n The same approach was extended to business knowledge enablement using a reverse engineering agent\, generating structured context integrated into Copilot Spaces\, enabling finance teams to query system behaviour using natural language.\n \n Learn how agentic AI can safely modernise legacy systems and bridge developer and business understanding.
CATEGORIES:BUILDING RELIABLE AGENT SYSTEMS
LOCATION:G104 + G105 (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:230aa54bc7e263963b314433a6a9c116
URL:http://agntconmcpconeu26.sched.com/event/230aa54bc7e263963b314433a6a9c116
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T142000Z
DTEND:20260917T144500Z
SUMMARY:What Networking Got Right That Agentic AI Risks Getting Wrong: The Case for an Agent Control Plane - Parisa Foroughi\, Nokia
DESCRIPTION:Every major agent orchestration framework today conflates task execution with the control layer that should govern authority and policy. This talk argues for a cross-domain agent control plane: a runtime layer external to the agent that performs authority checks and policy enforcement at defined boundaries\, independent of the agent’s internal logic. Grounded in inter-domain routing\, it proposes a semantic model built on five invariants: domain boundary as the control unit\, boundary-crossing capability classes as the permission unit\, scope-narrowing delegation with bounded elevation\, unbroken provenance to a registered trust anchor\, and boundary enforcement without inspecting internal behavior or payload content. The model introduces two runtime artifacts: the Agent Control Envelope (ACE) for authorization and the Agent Activity Envelope (AAE) for behavioral constraint. Attendees will leave with a precise mental model\, two concrete artifacts\, and a clear argument for why agent interoperability needs explicit boundary semantics before wire formats harden around the wrong primitives.
CATEGORIES:INTEROPERABILITY & STANDARDS
LOCATION:G102 + G103 (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:1bd9df43550978a59ef9d7aec72959c1
URL:http://agntconmcpconeu26.sched.com/event/1bd9df43550978a59ef9d7aec72959c1
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T142000Z
DTEND:20260917T144500Z
SUMMARY:MCP\, Skills\, and the Persistence of AI Agent Compromise - Steven Duckaert\, Onyx
DESCRIPTION:Prompt injection ends when the session ends. Memory poisoning doesn't.\n As enterprise agents mature\, three attack surfaces are converging: MCP server trust\, agent skill libraries\, and long-term memory retrieval. Each is dangerous in isolation. Together\, they create a threat model most teams aren't yet reasoning about.\n \nMCP enables agents to acquire tools dynamically\, including from servers never explicitly authorised. Agent skills package reusable behaviours that can be poisoned at the source. Memory systems built on vector retrieval treat past experience as trusted context\, with limited provenance validation.\n \nThe MINJA research (NeurIPS 2025) demonstrated injection success rates approaching 98% across GPT-4o\, Gemini\, and Llama-based agents. Crucially\, better reasoning models don't solve this - they may amplify it. A more capable model becomes more faithful to a poisoned memory once retrieved.\n \nOWASP's 2026 Agentic Top 10 dedicates a standalone category: ASI06 Memory and Context Poisoning.\n \nThis session maps the attack chain\, shares real enterprise exposure patterns\, and offers a framework for memory provenance tracking\, skill validation\, and MCP server trust evaluation.
CATEGORIES:MCPCON
LOCATION:Emerald Room (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:b083a17508a4b647150c538755633c73
URL:http://agntconmcpconeu26.sched.com/event/b083a17508a4b647150c538755633c73
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T145500Z
DTEND:20260917T152000Z
SUMMARY:We Built an Agent\, We Shipped a Compiler. Here's Why. - Joel Verezhak\, Grafana Labs
DESCRIPTION:We promised our CX team an agent that would write customer success plans. Six months and four architectures later\, we shipped a compiler that calls LLMs in four places.\n \n Each architecture was the right fix for the previous one's failure. The single skill could not enforce quality. The subagents drifted across stages. The scripted prompts hit determinism walls. Only when we accepted that "agentic" was the wrong frame did the output become reviewable\, replay-able\, and trustworthy enough to ship to real customers.\n \n The talk is a tour of the architectural moments where we learned what LLM-driven systems can and cannot own. Specific failures: a real customer plan shipped with the wrong rows\, a quality firewall the LLM kept violating until we made it structural\, and "temperature=0" arriving as a footnote rather than a solution.\n \n You leave with three things. A maturity curve from skill to engine. A working distinction between pipeline work and agent work. And a vocabulary for the conversation with stakeholders who keep asking when the agent will be ready\, when what they actually want is a compiler with an agentic UI.
CATEGORIES:AGENTIC ENGINEERING
LOCATION:G104 + G105 (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:a163cdaa47c9dbb24c6a3615aea9a1a7
URL:http://agntconmcpconeu26.sched.com/event/a163cdaa47c9dbb24c6a3615aea9a1a7
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T145500Z
DTEND:20260917T152000Z
SUMMARY:Skills Need SemVer Too - Pedro Rodrigues\, Supabase
DESCRIPTION:The agent ecosystem is converging on a common way to discover skills\, making it easier for agents to find and load domain-specific knowledge. But discovery only solves the first problem.\n \n Once skills become part of production workflows\, they need to evolve. Instructions change\, best practices improve\, and capabilities grow. Without a way to version and manage those changes\, agents risk relying on outdated or incompatible knowledge.\n \n In this talk\, I’ll explore lessons learned from publishing and distributing skills at scale\, discuss the emerging standards around skill discovery\, and propose a framework for skill versioning\, compatibility\, and evolution. If skills are becoming the package ecosystem for agents\, it’s time to start thinking about dependency management too
CATEGORIES:INTEROPERABILITY & STANDARDS
LOCATION:G102 + G103 (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:7843a525c6c9a3310e57e52edd01a581
URL:http://agntconmcpconeu26.sched.com/event/7843a525c6c9a3310e57e52edd01a581
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T145500Z
DTEND:20260917T152000Z
SUMMARY:MCP Borrowed LSP's Design. It Skipped LSP's Lesson - Gorkem Ercan\, Jozu
DESCRIPTION:MCP borrowed its design from the Language Server Protocol. It skipped LSP’s hardest lesson\, the one about packaging and trust\, and a decade later that lesson is still unlearned.\n \n LSP never standardized how servers were packaged or verified. Each editor invented its own channel\, the VS Code extension format won by default\, and signing was bolted on much later\, marketplace by marketplace. It still has not closed the gap.\n \n MCP repeats this with a larger blast radius. An MCP server runs arbitrary code that reaches into credentials\, data\, and local systems. Today’s packaging work falls short: the official registry delegates trust to npm and PyPI\, the MCPB format repeats the VS Code extension model\, and the provenance that exists is locked inside vendor silos.\n \n What is missing is open\, registry-neutral provenance verified before an agent loads a server. That standard does not need inventing. Packaging MCP servers as OCI artifacts inherits the signing\, attestation\, and policy tooling the container ecosystem already proved. This talk traces that history firsthand\, then shows how to reuse it rather than rebuild it registry by registry.
CATEGORIES:MCPCON
LOCATION:Emerald Room (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:8b497744cd3b147b8c047713bf1d904c
URL:http://agntconmcpconeu26.sched.com/event/8b497744cd3b147b8c047713bf1d904c
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T145500Z
DTEND:20260917T152000Z
SUMMARY:Distributed Mess: A Production Guide To Multi-Agent Failures - Oleksandra Bovkun\, Databricks
DESCRIPTION:Most agent failures don't happen in a model. They happen in the handoff. When a supervisor agent passes a flawed context downstream (wrong tool output\, misrouted state\, a hallucination that looked plausible)\, the receiving agent has no way to know. It continues confidently on a corrupted foundation. In MCP-based systems\, this is structural: tool call responses become shared context across agents that never directly communicate. A bad result upstream poisons every agent that touches it downstream. Traditional end-to-end testing misses this because the final output can still look reasonable.\n \n This session is a technical walkthrough of what that failure mode looks like in production and what you need to catch it: tracing context across agent boundaries (not just individual inference calls)\, distinguishing model errors from routing errors from context corruption\, and evaluating the coordination layer — not just outputs. \n \n This session is not about the future of AI\, but about the unglamorous work of building agentic systems you can actually trust.
CATEGORIES:MULTI-AGENT & DISTRIBUTED SYSTEMS
LOCATION:Auditorium (Ground Level)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:67f7198a5458e7c96354ad1670278017
URL:http://agntconmcpconeu26.sched.com/event/67f7198a5458e7c96354ad1670278017
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T153000Z
DTEND:20260917T155500Z
SUMMARY:The Unix Philosophy for AI Agents: Filesystems as the Context Primitive - Cannis Chan & Daniel Temesgen\, Bloomberg
DESCRIPTION:Every agent framework reinvents context management differently: scratchpads\, artifacts\, or memory stores. This creates distinct storage problems (system config\, user memory\, thread scratch\, task state\, shared workspaces\, external data\, and inter-agent messaging) collapsed under "agent context"\, with no shared vocabulary and a lack of interoperability.\n \n In an attempt to close this gap for the industry at large\, we present a production architecture that models agent context as scoped virtual filesystems. Agents interact through standard filesystem tool calls (read\, write\, and list)\, while the agentic AI platform enforces scope\, lifecycle\, and access control per mount.\n \n The talk covers three layers. First\, scoped state: how four filesystem scopes (system\, user\, thread\, and task) compose across collaborating agents\, using file modes and mount isolation to prevent cross-scope leakage. Second\, external data as mountpoints: turning retrieval into navigable directory trees with ls/cd/cat semantics instead of opaque vector search. Third\, protocol implications: how this maps to the MCP spec today and the case for filesystem operations as a first-class agent interoperability primitive.
CATEGORIES:AGENTIC ENGINEERING
LOCATION:G104 + G105 (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:59ee9a087b20cf90d79d790545d38125
URL:http://agntconmcpconeu26.sched.com/event/59ee9a087b20cf90d79d790545d38125
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T153000Z
DTEND:20260917T155500Z
SUMMARY:Verify\, Abstain\, or Amplify: A Field Guide To Confidently-Wrong Agents - Michal Orzechowski\, Sano – Centre for Computational Personalised Medicine
DESCRIPTION:Your coding agent earns trust because it has an oracle: a compiler and tests catch its mistakes. Most agents don't. They pass their evals and still ship confident\, wrong answers\, because for many tasks\, there's nothing to check against. Two failures hide under "confidently wrong": the model doesn't know (retrieve it)\, or it knows wrong\, a priori it reasserts even against a correct context\, which RAG won't fix. A field guide\, three honest moves. Verify\, when you can check: deterministic checks on the answer\, not the tool calls\, run in the harness. Abstain\, when you can't: make the agent say "I can't verify this\," gated on an external check\, not its own confidence. Amplify\, when there's no right answer\, only judgment: the model collapses toward the average exactly when you want the opposite\, so you push it off and amplify the novelty you put in\, judged by a human. We ground all three in our own builds where the model is reliably wrong: a finance agent\, a genomics agent that invents false-but-plausible mechanisms\, and a microtonal-music agent that keeps dragging toward Western tonality. The move comes down to two questions: can you check the answer\, and is there a right one?
CATEGORIES:BUILDING RELIABLE AGENT SYSTEMS
LOCATION:Auditorium (Ground Level)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:43b5f61a55a17e1550497bb821025b04
URL:http://agntconmcpconeu26.sched.com/event/43b5f61a55a17e1550497bb821025b04
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T153000Z
DTEND:20260917T155500Z
SUMMARY:What a Year of Breaking MCP Tells Builders: Protocol Gaps and What Ships Next - Amine Raji\, Molntek AB
DESCRIPTION:The session opens with the pre-deployment checklist\, seven controls\, no preamble\, then walks through the evidence for why each one exists. This audience deploys MCP in production and needs to leave knowing what to do.\n \n The empirical baseline: 30+ CVEs in 60 days. 24\,008 secrets in public MCP configs. 85% attack success rate against major hosts (MCPSecBench\, ICLR 2026). Reported as lower bounds with stated provenance.\n \n Three attack classes\, demonstrated with lab code. Tool description poisoning: exfiltrates an SSH key simultaneously. Cross-server shadowing: a trusted WhatsApp server weaponised by a malicious daily-facts server\, end-to-end encryption intact. The rug pull: postmark-mcp\, reconstructed.\n \n The protocol gap analysis is the content specific to this audience. I show the SDK code implementing the flat namespace\, the spec text that acknowledges the trust boundary but enforces nothing\, then four protocol changes with concrete JSON-RPC schema diffs: today's schema\, the addition\, the attack class it closes. The finding that changes model selection: more capable models follow poisoned instructions more reliably.\n \n No vendor tools. Source: github.com/aminrj-labs/mcp-attack-labs.
CATEGORIES:MCPCON
LOCATION:Emerald Room (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:5b86373ff4058776789792f7056efdfe
URL:http://agntconmcpconeu26.sched.com/event/5b86373ff4058776789792f7056efdfe
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T153000Z
DTEND:20260917T155500Z
SUMMARY:MAS-Lab: An Open Framework for Spec-Driven\, Interoperable Multi-Agent Systems - Jordan Augé\, Cisco Systems
DESCRIPTION:Building multi-agent systems for production remains challenging\, not only due to integration complexity\, but because validating that systems behave as intended is still largely unsystematic. Teams hand-wire LLMs\, tools\, and memory\, add observability late\, and lack clear ways to ensure agent interactions remain reliable and aligned as systems evolve.\n \n This session introduces MAS-Lab\, an open\, spec-driven framework that makes agent systems composable and verifiable. It extends the integration discipline of protocols like MCP and A2A to all components -- models\, tools\, memory\, messaging\, governance\, and observability -- through declarative specifications. The result is systematic integration\, built-in observability\, and reusable best practices.\n \n During the session\, we demonstrate a multi-agent trip planner and show how a single spec enables teams to compose agents\, apply governance controls such as budgets and guardrails without modifying logic\, and validate behavior by exploring alternative designs through reproducible experiments.\n \n Attendees will leave with practical patterns to ensure agent systems behave predictably\, remain aligned with intent\, and can be trusted in production.
CATEGORIES:MULTI-AGENT & DISTRIBUTED SYSTEMS
LOCATION:G102 + G103 (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:ac4428f4ab50e36d489c0b57995466cb
URL:http://agntconmcpconeu26.sched.com/event/ac4428f4ab50e36d489c0b57995466cb
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260917T160000Z
DTEND:20260917T173000Z
SUMMARY:Attendee Reception
DESCRIPTION:\n
CATEGORIES:SPECIAL EVENTS / EXHIBITS / BREAKS
LOCATION:Solutions Showcase\, Amsterdam\, Netherlands
SEQUENCE:0
UID:6e203dd89ccc059287a8feb2dfd30f83
URL:http://agntconmcpconeu26.sched.com/event/6e203dd89ccc059287a8feb2dfd30f83
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T060000Z
DTEND:20260918T152000Z
SUMMARY:Registration & Badge Pick-Up
DESCRIPTION:\n
CATEGORIES:SPECIAL EVENTS / EXHIBITS / BREAKS
LOCATION:Onyx Lounge (Ground Level)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:b045517d82472f529ac26239df68f8e5
URL:http://agntconmcpconeu26.sched.com/event/b045517d82472f529ac26239df68f8e5
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T070000Z
DTEND:20260918T071000Z
SUMMARY:Keynote: Welcome - Welcome - Angie Jones\, Vice President of Developer Experience\, The Agentic AI Foundation
DESCRIPTION:\n
CATEGORIES:KEYNOTE SESSIONS
LOCATION:Auditorium (Ground Level)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:8aa35b674d30dc00950253805bdb7e04
URL:http://agntconmcpconeu26.sched.com/event/8aa35b674d30dc00950253805bdb7e04
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T071000Z
DTEND:20260918T072000Z
SUMMARY:Keynote to be Announced
DESCRIPTION:\n
CATEGORIES:KEYNOTE SESSIONS
LOCATION:Auditorium (Ground Level)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:9863191944bad057ff0377ffbf2051ca
URL:http://agntconmcpconeu26.sched.com/event/9863191944bad057ff0377ffbf2051ca
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T072500Z
DTEND:20260918T073500Z
SUMMARY:Keynote: Agents as Actors: Harnessing the Power of Agentic Infrastructure - Idit Levine\, Founder & CEO\, Solo.io & Keith Babo\, Chief Product Officer\, Solo.io
DESCRIPTION:Harnessed agents have become the dominant interaction and runtime pattern for agentic AI. Claude Code\, Codex\, and a fast-growing field of open source harnesses integrate models with MCP tools\, skills\, and plugins. These harnesses provide sandboxed execution\, scoped environment access\, and human-in-the-loop controls on the desktop. The industry's next shift is already underway: moving harnessed agents from the desktop onto shared infrastructure\, where security\, observability\, and governance are consistent across every agent interaction. In this talk\, we will explore how open source infrastructure can deliver secure\, scalable harnessed agents beyond the desktop.
CATEGORIES:KEYNOTE SESSIONS
LOCATION:Auditorium (Ground Level)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:42346c9d2353d44346a5dacda2c32abb
URL:http://agntconmcpconeu26.sched.com/event/42346c9d2353d44346a5dacda2c32abb
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T073500Z
DTEND:20260918T074500Z
SUMMARY:Keynote: Dexter Horthy\, CEO and Co-Founder\, HumanLayer
DESCRIPTION:\n
CATEGORIES:KEYNOTE SESSIONS
LOCATION:Auditorium (Ground Level)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:e6f2202aa16c70c2798e835e9a1c7b66
URL:http://agntconmcpconeu26.sched.com/event/e6f2202aa16c70c2798e835e9a1c7b66
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T075000Z
DTEND:20260918T080000Z
SUMMARY:Keynote: Three Doors to One Tool: MCP vs WebMCP vs CLI - Frédéric Barthelet\, CTO & Co-founder\, Alpic & Dominic Farolino\, Software Engineer\, Google
DESCRIPTION:Agents can reach a tool through at least three doors today: an MCP server\, a WebMCP browser page\, or a plain CLI. They overlap\, they compete\, and the discourse around them runs hot. This talk cuts through it.We map the three surfaces along the axes that actually matter: where the code runs (backend\, browser\, model context\, shell)\, who holds state and auth\, latency and trust boundaries\, and how much UI context survives the handoff. Then we get practical: a decision framework for picking the right surface per use case\, the cases where you genuinely want two stacked together\, and the anti-patterns that appear when you pick wrong.
CATEGORIES:KEYNOTE SESSIONS
LOCATION:Auditorium (Ground Level)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:20c12a9f47e6cac34f450f5d9985ae47
URL:http://agntconmcpconeu26.sched.com/event/20c12a9f47e6cac34f450f5d9985ae47
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T080000Z
DTEND:20260918T082000Z
SUMMARY:Coffee Break
DESCRIPTION:\n
CATEGORIES:SPECIAL EVENTS / EXHIBITS / BREAKS
LOCATION:Solutions Showcse - Diamond Lounge\, Amsterdam\, Netherlands
SEQUENCE:0
UID:71937b97ab8b31ceda08f723a5c319d2
URL:http://agntconmcpconeu26.sched.com/event/71937b97ab8b31ceda08f723a5c319d2
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T080000Z
DTEND:20260918T133000Z
SUMMARY:Solutions Showcase
DESCRIPTION:\n
CATEGORIES:SPECIAL EVENTS / EXHIBITS / BREAKS
LOCATION:Diamond Lounge (Ground Level)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:6ebbf7a7b6a12bf8ef4a6f15826e920d
URL:http://agntconmcpconeu26.sched.com/event/6ebbf7a7b6a12bf8ef4a6f15826e920d
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T082000Z
DTEND:20260918T084500Z
SUMMARY:Agentic AI and Hybrid Architecture - Redefining 100+ Applications at Scale - Pradheepa V\, adidas AG
DESCRIPTION:At adidas Europe Market Tech\, a lean team of architects and engineers are making a big difference\, transforming 100+ applications by embedding AI agents into everyday workflows. We leverage AI with clear purpose to shape a new operating model to drive end-to-end efficiency and productivity at enterprise level. In this session\, we share our transformation journey\, challenges we addressed and its impact on business\, people & process. On the technical stack\, we will enlighten you on: – Production proven patterns for running AI tools in parallel\, speedy deployment-ready applications\, architecture reasoning and how we are accelerating our path to realising our north star. – How we benefit from a hybrid AI architecture: cloud models for high-value reasoning\, paired with locally hosted LLMs for implementation. How we balance cost\, latency and efficiency at scale. – What way architecture agents enable continuous\, scalable visibility across complex application landscapes - turning static data into meaningful insights. Ultimately\, the way “Through sport\, we have the power to change lives”\, we believe “Through AI\, we have the power to change the tech landscape to stay future-ready”
CATEGORIES:ENTERPRISE ADOPTION IN PRACTICE
LOCATION:Auditorium (Ground Level)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:69d4cd2eb560f6fc2fd8a3866994dd2b
URL:http://agntconmcpconeu26.sched.com/event/69d4cd2eb560f6fc2fd8a3866994dd2b
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T082000Z
DTEND:20260918T084500Z
SUMMARY:Pull Requests Are Dead\, Long Live Peer Review - Dylan Ratcliffe\, Overmind
DESCRIPTION:When AI writes 80–90% of the code on a team\, peer review breaks. The pull request is produced by a machine you can't argue with\, and the reviewer is auditing a diff instead of talking to a peer. Review has stopped feeling like collaboration\, and most of us have started hating it.\n \n We rebuilt how we deploy AI-assisted development in production. Human review moved off the diff and onto the plan: the intent written before any code gets generated. Engineers review the thinking they care about and let the agent fill in the gaps. When the PR lands\, CI runs the usual checks plus an automated comparison against the approved plan. Only deviations route back to the original reviewer.\n \n This is a case study in integrating AI into a real SDLC without breaking accountability\, quality\, or culture. I'll walk through what broke\, what we automated\, and what stayed human: an in-house MCP server for plan review in the IDE\, deviation-checking on every PR\, and cultural bets (everyone operates as a team lead\; no questions until working code\; customer context radiated to the whole team).\n \n We massively improved our velocity and our lead time\, and our engineers love the job again.
CATEGORIES:HUMAN-AGENT COLLABORATION
LOCATION:G102 + G103 (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:3cc6e8d9193ef68045614f9ebd1d5233
URL:http://agntconmcpconeu26.sched.com/event/3cc6e8d9193ef68045614f9ebd1d5233
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T082000Z
DTEND:20260918T084500Z
SUMMARY:Potential Issues for Cross-domain Multi-hop API Calls and Their Solution Proposal - Takashi Norimatsu\, Hitachi\, Ltd.
DESCRIPTION:When an MCP server calls an API server requiring an access token in a different domain\, elicitation in URL mode is defined by the MCP. Furthermore\, token exchange is also used in real-world use cases. We describes the security and operational issues associated with these two methods and proposes solutions.\n \n Elicitation in URL mode may cause user swapping. Moreover\, even if an authorization server performing the initial authorization securely perform it by following MCP spec\, the well-known attacks may succeed if the other authorization server performing the external authorization does not care about security.\n \n Token exchange may cause information leaks\, fraudulent access token use\, and availability problems.\n \n In both methods\, there are two access tokens: for accessing the MCP server\, for accessing the API server. To detect user swapping\, it is needed to ensure that both users bound with the first and second token are the same. However\, even if the same user registered in both different domains\, their user identifiers are usually different. Therefore\, simply matching them exactly is not effective.\n \n We describe these issues and propose their solutions.
CATEGORIES:MCPCON
LOCATION:Emerald Room (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:0770cc90e78433d82a1db81ad49c7ffb
URL:http://agntconmcpconeu26.sched.com/event/0770cc90e78433d82a1db81ad49c7ffb
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T082000Z
DTEND:20260918T095500Z
SUMMARY:Workshop: Keep Infrastructure Out of Your AI Agents: The Agent Gateway Pattern - Lin Sun\, Solo.io
DESCRIPTION:As AI agents move into production\, engineering teams face a growing set of challenges. How do you secure and govern MCP servers without modifying them? Route and fail over across multiple LLM providers? Enforce rate limits\, access controls\, and governance policies? Observe agent traffic\, and scale operations across environments?\n \n Rather than embedding these capabilities into every agent\, MCP server\, and application\, organizations can adopt a single architectural pattern: the agent gateway.\n \n An agent gateway acts as a unified control plane for AI systems. It can function as an MCP gateway\, LLM gateway\, inference gateway\, and traditional API gateway\, centralizing security\, observability\, routing\, resilience\, and policy enforcement across agents\, tools\, models\, and services.\n \n In this hands-on workshop\, you'll learn how to secure and federate MCP servers without code changes\, route and fail over LLM traffic across providers\, enforce authentication and usage policies\, and gain end-to-end visibility into agent interactions. Through practical exercises\, you'll see how a single gateway layer simplifies operations while enabling secure\, scalable\, and governable AI systems.
CATEGORIES:WORKSHOP
LOCATION:G106 + G107 (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:f02f2421e61934028560c59c1e1599fa
URL:http://agntconmcpconeu26.sched.com/event/f02f2421e61934028560c59c1e1599fa
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T085500Z
DTEND:20260918T092000Z
SUMMARY:From "Works on My Prompt" To Production SLOs: Building Agent Observability - Manik Khandelwal\, Microsoft
DESCRIPTION:hen we shipped an AI agent powered by Cosmos DB's MCP server internally at Microsoft\, it passed every test we threw at it—until real users found creative ways to break it. The agent would silently degrade: returning plausible-but-wrong query results\, calling tools in inefficient loops\, or burning through token budgets without completing tasks. Traditional monitoring showed green dashboards while users filed complaints. We needed observability designed for agents.\n \n This talk presents the observability and evaluation stack I built to make agent failures visible\, measurable\, and catchable before users notice—combining OpenTelemetry instrumentation\, LLM-as-judge evaluation\, and automated regression gates in CI/CD.
CATEGORIES:AGENTIC ENGINEERING
LOCATION:Auditorium (Ground Level)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:a02c01c8ef268dcbe45fb87ef06303be
URL:http://agntconmcpconeu26.sched.com/event/a02c01c8ef268dcbe45fb87ef06303be
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T085500Z
DTEND:20260918T092000Z
SUMMARY:From MCP Playground To Org-Wide Infrastructure: Lessons From Building Booking.com's Agent Foundry - Anushka Bhandari\, Booking.com
DESCRIPTION:Most MCP talks stop at the gateway. This one starts there. The barrier to contributing has never been lower — agents write code\, PMs ship tools\, designers prototype integrations. But newcomers don't carry the institutional knowledge from a 2am production incident: the performance edge cases\, the security gotchas\, the failure modes that only show up under real load. Most MCP projects die between proof of concept and production. The gap isn't technical\, it's organizational. Who owns the servers? Who reviews contributions? How does a UX designer\, PM\, and autonomous agent share the same infrastructure without ten different logins? Booking.com's Agent Foundry closed that gap. A two-tier MCP gateway with 20+ org-wide servers (Grafana\, Honeycomb\, Atlassian\, Slack\, GitLab). One OAuth flow for humans and agents alike. A skills registry with AI-reviewed contributions. Composable profiles that bundle MCPs and skills into workflow-specific harnesses. Every skill one team contributes compounds value for every team that follows. We'll share what the architecture got right\, what broke\, and what a small team can realistically own at this scale.
CATEGORIES:ENTERPRISE ADOPTION IN PRACTICE
LOCATION:G102 + G103 (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:0f9752d63e73d41c5686b1a693cc9f85
URL:http://agntconmcpconeu26.sched.com/event/0f9752d63e73d41c5686b1a693cc9f85
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T085500Z
DTEND:20260918T092000Z
SUMMARY:Outcome Engineering: Why Your Agentic Architecture Doesn't Matter (Yet) - Kierra Dotson\, Further
DESCRIPTION:The open agentic ecosystem is technically brilliant and strategically incomplete. Engineers across the enterprise are deploying multi-agent systems\, integrating MCP\, and building sophisticated context infrastructure — and yet the majority of it never reaches production at scale\, fails to earn sustained organizational investment\, or generates no measurable competitive value. This stems from looking at model and tool selection as the outcome instead of business value produced.\nOutcome Engineering is the discipline of designing agentic systems backward from competitive strategy\, instead of forward from technical capability. It is the difference between building impressive infrastructure and building systems that are indispensable. It is the difference between an agent that gets demoed and an agent that gets shipped. And it is the difference between an engineer who just builds things and an engineer who changes what a business is capable of.\nThis session challenges a widely held belief in the engineering community: that deploying the most advanced agentic architecture is the end goal. It is not. The end goal is winning disproportionately because your AI systems are connected to proprietary data\, embedded in proprietary workflows\, and architected around prioritized business goals and competitive positions that cannot be replicated by any organization running the same off-the-shelf stack.\nThis session will expose the critical disconnect between how engineers build agentic systems and how those systems actually survive contact with business reality. We will cover how to map technical architecture directly to strategic outcomes — why proprietary data and institutional knowledge are the most defensible moats in the agentic era\, and what it actually takes to build systems the business cannot afford to turn off.\nAttendees will leave with a clear framework for reverse-engineering their agent architecture from the outcome back to the infrastructure. Ultimately\, the engineers who define this era will be the ones who build systems so embedded in how the business wins that replacing them becomes a risk no one is willing to take.\n
CATEGORIES:ENTERPRISE ADOPTION IN PRACTICE
LOCATION:G104 + G105 (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:b3bd2b0999b7bf7a13dc033713015553
URL:http://agntconmcpconeu26.sched.com/event/b3bd2b0999b7bf7a13dc033713015553
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T085500Z
DTEND:20260918T092000Z
SUMMARY:ID-JAG: Solving OAuth Sprawl for Enterprise AI Agents - Joey Orlando\, Archestra.AI & Aaron Parecki\, Okta
DESCRIPTION:Enterprise AI agents are moving from demos into production\, and auth is becoming a blocker. Demo agents can connect to tools with OAuth\, but real enterprise agents may need SaaS services for thousands of employees. Per-user\, per-service consent does not scale.\n \n This session explains ID-JAG\, the Identity Assertion JWT Authorization Grant pattern behind MCP's Enterprise-Managed Authorization extension. ID-JAG turns an existing SSO login into centrally governed\, auditable access to approved MCP servers\, without repeated OAuth prompts.\n \n We'll cover the production problem\, protocol flow\, and lessons from implementing ID-JAG support in Archestra\, one of the first MCP clients to support it. We'll also discuss what identity provider support enables.\n \n Attendees will leave with a model for production agent auth: one SSO login\, centralized policy\, scoped MCP-native access tokens\, fewer consent screens\, and a cleaner security review story.\n \n We'll close with the missing piece: SaaS provider adoption. To unlock enterprise deployments\, authorization servers need to support this flow so agents can access approved business systems without key-sharing\, manual credentials\, or one-off integrations.
CATEGORIES:MCPCON
LOCATION:Emerald Room (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:844a5bec76e451edb714493aba75801f
URL:http://agntconmcpconeu26.sched.com/event/844a5bec76e451edb714493aba75801f
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T093000Z
DTEND:20260918T095500Z
SUMMARY:Agents Can Pay. Can They Prove It? - Diego Zuluaga & Saurabh Goyal\, Open Mobile Hub
DESCRIPTION:This is the EUDI Wallet architecture\, running inside an agent\, 18 months before the Dec-2026 mandate.\n \n Every "agent that verifies you" or "agent that pays" demo skips the hard part: how does an AI agent request a real\, government- or bank-grade credential from your device\, on any phone\, any wallet\, Android or iOS\, and prove who authorized it?\n \n We'll run the full chain live. An MCP server renders a verifier inside Claude and ChatGPT\; the W3C Digital Credentials API requests a credential over OpenID4VP\; FIDO caBLE carries it cross-device to your phone\; the wallet returns an mdoc or SD-JWT credential held in hardware (StrongBox\, TEE\, Secure Enclave)\; an AP2 mandate binds your intent.\n \n Identity is the headline\, age\, membership\, passport\, healthcare\, with payments as one example. And it's not a stage trick: it's an open-source Digital Credential MCP server\, soon to be released and donated\, that you can clone\, point at your own credential\, and ship. Built on open standards\, across every platform\, with UCP & ACP conformance on the roadmap.\n \n Here are some examples of the demos we're planning to showcase: https://github.com/dzuluaga/mcp-apps-shopping-demo
CATEGORIES:AGENTIC COMMERCE
LOCATION:G104 + G105 (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:d64f761d0ed3fdcf9533ec5c55aa6aab
URL:http://agntconmcpconeu26.sched.com/event/d64f761d0ed3fdcf9533ec5c55aa6aab
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T093000Z
DTEND:20260918T095500Z
SUMMARY:I Was the Bottleneck\, Not the Agent - Vincent Ysmal\, Datadog
DESCRIPTION:Running 4 to 8 parallel agent coding sessions sounds like a superpower. It nearly broke me. I was spending more time switching context to check what each agent had done than I would have spent writing the code myself. Manual testing\, staging deployments\, code reviews just to understand what the agent had built: I had become the bottleneck. The agents were fast. I wasn't. This talk is about how our team redesigned the workflow around one principle: the agent should be able to prove its own work. That means agents that deploy themselves\, run their own test suites\, watch CI and fix failures\, and produce PRs with enough evidence that a reviewer can approve with confidence\, without reading every line. I'll share what it concretely took to get there\, and where humans still need to stay in the loop and why.
CATEGORIES:AGENTIC ENGINEERING
LOCATION:G102 + G103 (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:5c333228cfbd2e521cd8abc590ec1651
URL:http://agntconmcpconeu26.sched.com/event/5c333228cfbd2e521cd8abc590ec1651
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T093000Z
DTEND:20260918T095500Z
SUMMARY:Governance You Can Run: Checkable Properties for Production Agents - Seshu Tolety\, Siemens
DESCRIPTION:Most agent governance lives in documents nobody can enforce. The agent ships\, the policy sits in a wiki\, and no one can answer the question that matters in production: is this running system compliant right now? This talk presents governance built the other way around\, as properties you can check on a live agent system rather than promises on a slide. We decompose any agentic system into a small three-object model\, define properties that are individually testable against a running deployment\, and rank failure modes into the handful of Tier-1 risks that actually cause incidents. Regulatory mappings (EU AI Act\, ISO/IEC 42001\, GDPR) fall out as a consequence of satisfying those properties\, not as the starting point. You leave with a vendor-neutral framework you can apply to your own agents the same week\, independent of stack or model provider.
CATEGORIES:ENTERPRISE ADOPTION IN PRACTICE
LOCATION:Auditorium (Ground Level)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:f08fe743a891f35332ef7dc3438bf6ef
URL:http://agntconmcpconeu26.sched.com/event/f08fe743a891f35332ef7dc3438bf6ef
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T093000Z
DTEND:20260918T095500Z
SUMMARY:Economies of Scale for MCP and Agents: Why You Need an Identity Broker - Magnus Jungsbluth & Jan Brennenstuhl\, Zalando SE
DESCRIPTION:Drawing from lessons of how to scale an enterprise to thousands of microservices\, we make the case that pushing concerns to the infrastructure for agentic systems should be a no-brainer when planning to scale agentic systems. \n This talk explores how Zalando tackled this challenge by building and open-sourcing our own agentic identity broker as part of our broader agentic platform initiative. We will share how it supports delegation chains across third-party and in-house applications\, integrates with the CNCF project agentgateway and how it allows us to keep these pesky authentication / authorization concerns on the infrastructure and keep MCP servers and agents simple. \n We will dive into the technical mechanics\, how it integrates into a larger enterprise and allows us to apply just enough governance to stay ahead of the game. We will cover practical applications and limitations of dynamic client registration. \n A closing outlook will illustrate how tool approvals and human-in-the-loop can be enforced centrally without agent authors or MCP authors having to build anything. Practical examples of CIBA and intent-based access will complete the session.
CATEGORIES:MCPCON
LOCATION:Emerald Room (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:2b03f52f8aba6b86adbc4b03f16628b2
URL:http://agntconmcpconeu26.sched.com/event/2b03f52f8aba6b86adbc4b03f16628b2
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T100500Z
DTEND:20260918T103000Z
SUMMARY:Governed Agent Autonomy: Building a Control Plane for Agentic Systems - Nnenna Ndukwe\, Qodo AI
DESCRIPTION:We see how quickly AI coding tools and agent harnesses are improving. But how can the surrounding system keep that autonomy governable once an agent starts planning\, executing tools\, changing files\, and consuming budget on a team’s behalf? In this talk\, I break down a technical case study based on a real AI coding control-plane architecture and show how serious systems structure autonomy through explicit boundaries: plan gates\, permission controls\, trust review\, independent verification\, and runtime observability. I will walk through the patterns and production-grade examples\, explain why telemetry and quota tracing are integral to code governance\, and show why integrity failures can still happen even with strong coding workflows. This session gives engineering leaders and practitioners a framework for evaluating AI coding tools. The goal is to achieve agent governance that teams can trust\, audit\, and scale.
CATEGORIES:BUILDING RELIABLE AGENT SYSTEMS
LOCATION:G102 + G103 (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:d6a87bbca849484e30fbdbcaa1b81499
URL:http://agntconmcpconeu26.sched.com/event/d6a87bbca849484e30fbdbcaa1b81499
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T100500Z
DTEND:20260918T103000Z
SUMMARY:When Agents Run Healthcare: Building Reliable Agentic Systems in Highly Regulated Environments - Janosch Woschitz\, BARMER
DESCRIPTION:The public statutory health insurance system in Germany faces a dual challenge: demographic change is creating a shortage of skilled professionals while operational pressure continues to rise due to an aging population. Healthcare organisations must therefore automate high-volume processes without compromising reliability\, governance\, or trust. This session presents BARMER’s journey from governed data and analytics platforms to production-oriented agentic systems supporting real operational workflows. Rather than focusing on isolated chatbots or copilots\, it explores how agentic systems can be embedded into core enterprise processes in highly regulated environments. The talk highlights key design patterns including workflow orchestration\, agent runtime separation\, observability\, and human-in-the-loop escalation. It also demonstrates why many early agent architectures fail under regulatory constraints and what changes are required to meet enterprise standards for compliance\, auditability\, and resilience.
CATEGORIES:ENTERPRISE ADOPTION IN PRACTICE
LOCATION:Auditorium (Ground Level)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:7d087d5cd9f8906ff25ef09f52e3bad2
URL:http://agntconmcpconeu26.sched.com/event/7d087d5cd9f8906ff25ef09f52e3bad2
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T100500Z
DTEND:20260918T103000Z
SUMMARY:Testing Agents and Their Tools: Offline Evaluation\, Synthetic Tasks\, and A/B Experiments - Ksenia Bobrova\, GitHub
DESCRIPTION:A three-layer evaluation strategy for AI agents and their tools\, from experience operating across multiple LLM providers and runtimes. Offline evaluation: designing benchmark suites with curated requests\, expected tool selections\, and arguments. Computing precision\, recall\, F1 scores\, confusion matrices for tool mix-ups\, and argument hallucination rates to pinpoint description problems. End-to-end benchmarks: multi-tool flows where the agent chains several calls to complete a task\, catching integration regressions that single-tool evaluation misses. Production A/B experiments: a case study of tool search experiments across OpenAI and Anthropic through staged rollouts. Challenges we hit: caching bugs under real traffic\, tool discovery failures\, and data skew making early results inconclusive. How we decided whether to advance\, pause\, or roll back. These layers compensate for each other's blind spots\, forming a testing pyramid that enabled us to safely ship changes to MCP and agent across model providers. Attendees leave with a reusable playbook for testing MCP servers\, agents\, and running A/B experiments.
CATEGORIES:EVALUATION & TESTING
LOCATION:G104 + G105 (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:4511e26b5b7d543477af76bfcc8f685d
URL:http://agntconmcpconeu26.sched.com/event/4511e26b5b7d543477af76bfcc8f685d
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T100500Z
DTEND:20260918T103000Z
SUMMARY:MCP Apps and the Nearly Headless Web - Liad Yosef\, MCP Apps
DESCRIPTION:MCP Apps are the last piece in moving toward a new web - one that's "nearly" headless. Autonomous agents\, not humans\, will interact with most websites through MCP\, APIs\, and other data channels. Websites and browsers become obsolete\, replaced by personal assistants that orchestrate tasks on our behalf. In rare cases\, agents will fall back to browser capabilities to navigate sites that aren't yet agent-ready.\n But we'll still need the last mile.\n Some moments still require human eyes and human input: choosing a seat at a venue\, completing a check-in\, reviewing a 3D model\, verifying intent on important decisions. This is where MCP Apps come in - letting tools\, websites\, and services send composable\, interactive chunks of UI directly to agents\, exactly when needed\, maintaining brand and identity.\n We'll explore the full cycle of this nearly headless web: the infrastructure required to support autonomy and trust\, the new UI layer\, and how assistants are becoming the new browsers.\n MCP Apps redefine the web's interface. Headless\, but with a human eye at the end.
CATEGORIES:MCPCON
LOCATION:Emerald Room (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:0ce2cfec5a226a96deab5d3bf77d33e4
URL:http://agntconmcpconeu26.sched.com/event/0ce2cfec5a226a96deab5d3bf77d33e4
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T100500Z
DTEND:20260918T114000Z
SUMMARY:Workshop: Harness Engineering: Building the System Around Your AI Coding Agent - Ji Darwish\, Lunatech
DESCRIPTION:AI coding agents feel like magic. It is easy to assume there is something exotic inside\, some secret sauce that makes agents reliable. Well\, there isn't\, the core of every AI coding agent is dead simple: send a message to a model\, parse tool calls\, execute them\, feed the results back\, repeat. Everything else (context management\, permissions\, observability\, safety guardrails) is engineering layered on top of it that we should be building.\n \n In this deep dive\, we build that engine from scratch (in Java!)\, live on stage. Not to build the best agent\, but to understand how the pieces fit together. We point it at a real codebase\, and watch what happens. It compiles. Tests pass. And it violates every convention the team agreed on. So we iterate. We add context\, constraints\, and feedback\, and at each step we examine what changed\, why it helped\, and what it maps to in the tools you already use.\n \n The goal is a mental model. By the end\, you will understand the components inside the AI coding tools you use every day\, what you can layer on top to get smoother results and safer expectations\, and where the honest limits still are\, the gap no amount of engineering has closed yet.
CATEGORIES:WORKSHOP
LOCATION:G106 + G107 (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:500a575f16f790892fe1e991bd0195c7
URL:http://agntconmcpconeu26.sched.com/event/500a575f16f790892fe1e991bd0195c7
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T104000Z
DTEND:20260918T110500Z
SUMMARY:Stateless Agents\, Stateful Worlds: Designing for Interruption - Arul Kumaran\, Luracast / Portel
DESCRIPTION:Anthropic just announced MCP is going stateless. Most agent frameworks assume long-running\, uninterrupted sessions. Real deployments face forced interruptions every hour: rate limits\, auth refreshes\, network partitions\, process restarts\, the laptop lid closing. When a session dies mid-task\, most agents start over. That is not a model problem. It is a runtime design problem. This talk covers the patterns that make agents resumable: idempotent tool calls that can safely re-execute\, checkpoint-first execution that captures decisions before side effects\, explicit continuation tokens that let a new session pick up an interrupted task\, and the specific primitives a TypeScript runtime on Cloudflare Workers exposes to make all of this cheap. Every pattern shown is running in production on Photon\, an open-source agentic tool runtime deployed to edge infrastructure. Attendees leave with a concrete checklist: five changes to their agent architecture that make it survive the real world\, not just the happy path.
CATEGORIES:BUILDING RELIABLE AGENT SYSTEMS
LOCATION:Auditorium (Ground Level)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:1aeda8353eb881af1a96332fea0aa415
URL:http://agntconmcpconeu26.sched.com/event/1aeda8353eb881af1a96332fea0aa415
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T104000Z
DTEND:20260918T110500Z
SUMMARY:Beyond Vibe-Testing: Engineering Deterministic Agent Skills - Shuva Jyoti Kar\, Palo Alto Networks
DESCRIPTION:The AI ecosystem suffers from a critical engineering immaturity: deploying stochastic models via manual "vibe checks." Operating autonomous agents at enterprise scale requires abandoning ad-hoc observation for strict\, distributed systems rigor. This session introduces a deterministic\, CI/CD-native evaluation architecture for Agent Skills\, shifting from indeterministic to reliable software execution. By adhering to the formalized capability standards defined by agentskills.io\, we will deconstruct the transition from subjective testing to hermetic\, code-driven audits. Attendees will learn to engineer scenario matrices that enforce strict cognitive boundaries via negative testing—guaranteeing agents safely reject out-of-scope triggers. We will demonstrate isolating execution within sandboxed environments to capture pristine telemetry: deterministic tool-call structures\, system exit codes\, and exact token utilization. Crucially\, we address the anti-pattern of relying on "LLM-as-a-judge" for critical path assertions. Instead\, we architect a framework grading system invariants via AST parsing and JSON Schema enforcement to achieve instantaneous\, hallucination-immune evaluation.
CATEGORIES:EVALUATION & TESTING
LOCATION:G104 + G105 (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:7f141da0193cec99df059c84f78b0e2e
URL:http://agntconmcpconeu26.sched.com/event/7f141da0193cec99df059c84f78b0e2e
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T104000Z
DTEND:20260918T110500Z
SUMMARY:From API Catalogs To Agent Catalogs: Solving MCP Server Discovery With Open Resource Discovery - Vyshnavi Gadamsetti & Sebastian Wennemers\, SAP SE
DESCRIPTION:As MCP servers multiply\, the ecosystem is hitting the fragmentation problem APIs hit a decade ago: every server is a point-to-point integration with no shared way to discover or describe it. Live introspection over a connected session does not scale to the catalogs\, registries\, and gateways that need to reason about thousands of servers without starting each one up. Open Resource Discovery (ORD) solved this for APIs\, events\, and data products. Each resource publishes a static\, machine-readable description at a well-known endpoint. Aggregators crawl those descriptions and build catalogs that registries and gateways can query without connecting to the resource. Recent ORD work applies the same shape to agents and the MCP servers they depend on\, scoping the dependency to the tools and prompts an agent uses. The same pattern fits MCP. The talk walks through a Server Card design that serves tools\, prompts\, and resources alongside metadata from a well-known endpoint\, so registries and gateways can reason about a server before any agent connects. The design has been contributed into the open MCP community via SEP-2127\, with a public renderer and playground demonstrating it end-to-end.
CATEGORIES:MCPCON
LOCATION:Emerald Room (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:81bfe9fe9764e0fcdd1faa03ecc53790
URL:http://agntconmcpconeu26.sched.com/event/81bfe9fe9764e0fcdd1faa03ecc53790
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T104000Z
DTEND:20260918T110500Z
SUMMARY:Agents Talking To Agents: MCP\, A2A\, and the Reality of Multi-Agent Orchestration in Production - Willem Berroubache\, Orange
DESCRIPTION:Building a multi-agent system in a notebook is straightforward Running one on production infrastructure\, where a wrong handoff triggers a real incident\, is a different problem entirely. This talk shares hard-won lessons from deploying autonomous agents using both MCP and A2A protocols in a large-scale\, regulated environment. We move past the happy path and focus on what actually breaks: agents that lose task context mid-chain\, trust boundaries that collapse during agent-to-agent delegation\, tool conflicts between concurrent agents\, and orchestration failures that only surface under real load. We walk through three patterns that emerged from this work. How to split responsibilities between MCP and A2A so each protocol does what it is actually good at. How to scope agent authority using MCP server boundaries without creating coordination bottlenecks. And how to design agent-to-agent handoffs that degrade gracefully when part of the chain fails mid-task. No toy examples. No vendor pitches. Concrete decisions\, the tradeoffs behind them\, and what we would change today. Attendees leave with patterns they can apply the next day\, regardless of their agent framework.
CATEGORIES:MULTI-AGENT & DISTRIBUTED SYSTEMS
LOCATION:G102 + G103 (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:07026965f649ece584f3dbb80cfc8cc9
URL:http://agntconmcpconeu26.sched.com/event/07026965f649ece584f3dbb80cfc8cc9
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T111500Z
DTEND:20260918T114000Z
SUMMARY:Agent-Smith: Never Send a Human To Do a Machine’s Job - Glenn ten Cate\, The Linux Foundation & Jorge Carvalho\, Nedap
DESCRIPTION:Most AI security agents are wrappers around fixed scripts. Agent-Smith takes a different approach: reusable skills encode security methodology\, while the model determines how to investigate\, chain tools\, validate findings\, and select its next action. This session presents the architecture and lessons behind Agent-Smith\, an open-source\, MCP-enabled autonomous penetration-testing agent spanning web\, cloud\, Active Directory\, source-code review\, threat modeling\, and AI red teaming and more. We will examine MCP tool exposure\, methodology-as-code\, autonomous skill chaining\, model portability\, ephemeral Docker sandboxes\, and server-side controls for cost\, execution time\, and tool calls. A practical demonstration will show Agent-Smith progressing from reconnaissance to a verified finding\, reproducible proof of concept\, remediation guidance\, and code patch. Attendees will leave with concrete patterns for building capable agents without sacrificing isolation\, observability\, human oversight\, or control. “Never send a human to do a machine’s job.”
CATEGORIES:BUILDING RELIABLE AGENT SYSTEMS
LOCATION:Auditorium (Ground Level)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:02d6108bab3c8392031b60f69a5548b1
URL:http://agntconmcpconeu26.sched.com/event/02d6108bab3c8392031b60f69a5548b1
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T111500Z
DTEND:20260918T114000Z
SUMMARY:From Vibes To Data: Evaluating Agents on Your Real Work - Ville Hellman\, Datadog
DESCRIPTION:Frontier labs are spending billions making agents better at SWE-Bench. But how much of your engineering work actually looks like SWE-Bench? At Datadog we kept seeing agents that crushed public benchmarks fail on our codebase: missing our conventions\, reaching for the wrong internal libraries\, technically correct but doing the work the wrong way. To get past demos and gut feel\, we built an evaluation platform that measures agents on tasks drawn from our real work\, and gave our platform teams a way to encode best practices as evals. Teams shipping skills\, steering docs\, agent harnesses\, and MCP servers can now see whether their changes actually moved the needle. In this talk I'll share how SOTA and open-weight models actually compare on real work\, what their cost-performance profiles look like\, tooling decisions that can shift token usage by 10% or more\, and how a surprisingly small eval suite can produce stable signal. You'll leave with a clearer way to think about model choice as a tradeoff between performance you actually need and tokens you're willing to spend\, and a sharper sense of what makes an eval keep paying off over time instead of becoming a one-off exercise.
CATEGORIES:EVALUATION & TESTING
LOCATION:G104 + G105 (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:5afb0b4976e22b92d7979a974d8ffbb6
URL:http://agntconmcpconeu26.sched.com/event/5afb0b4976e22b92d7979a974d8ffbb6
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T111500Z
DTEND:20260918T114000Z
SUMMARY:Beyond Chatbots: Agentic UI With Open Standards - Manfred Steyer\, ANGULARarchitects
DESCRIPTION:Integrating agentic AI into the UI easily leads to ad hoc integrations\, tight coupling to backend technologies\, and vendor lock-in. So how do we design scalable\, maintainable interactions between agents and users? This session shows how open standards like AG-UI\, A2UI\, and MCP Apps enable a protocol-driven approach to Agentic UI\, establishing clear\, message-based boundaries that decouple UI\, agent logic\, and tools. You’ll learn how to apply these standards\, leveraging dynamic UI generation\, tool integration\, and Human-in-the-Loop patterns. By the end\, you’ll understand how to design Agentic UI using open standards and integrate them through clear\, protocol-based boundaries.
CATEGORIES:HUMAN-AGENT COLLABORATION
LOCATION:G102 + G103 (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:db32aa8283d37bb218713f49b6353143
URL:http://agntconmcpconeu26.sched.com/event/db32aa8283d37bb218713f49b6353143
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T111500Z
DTEND:20260918T114000Z
SUMMARY:Spotify’s Bet on MCP and Investment in Open Source - Oliver Soell & Yannick Epstein\, Spotify
DESCRIPTION:Spotify’s workforce went from zero to near universal use of MCP servers in breakneck time. It was only possible due to the MCP gateway - custom code written in a weekend to support the urgent need to expose Spotify’s extensive internal API ecosystem to AI agents.\n \n The MCP gateway rapidly became a victim of its own success\; multiple teams were committing significant changes to the codebase\, and domain ownership and on-call support for the gateway were somewhat uncertain. From a sustainability perspective\, the MCP gateway was becoming a big risk.\n \n In this talk you’ll learn how Spotify successfully rebased its highly custom MCP gateway use case onto OSS technologies\, while retaining deep integration into Spotify’s infrastructure management plane\, service discovery\, and microservice ecosystem. Hear how kgateway\, the Envoy proxy\, kro\, and the Gateway API were used to build the new MCP gateway\, enabling it to be better sustained by the right teams contributing their specific expertise.
CATEGORIES:MCPCON
LOCATION:Emerald Room (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:8129b2e34ca83d8b31453ad4a25af594
URL:http://agntconmcpconeu26.sched.com/event/8129b2e34ca83d8b31453ad4a25af594
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T114000Z
DTEND:20260918T125000Z
SUMMARY:Lunch (Provided Onsite for Attendees)
DESCRIPTION:\n
CATEGORIES:SPECIAL EVENTS / EXHIBITS / BREAKS
LOCATION:Solutions Showcse - Diamond Lounge\, Amsterdam\, Netherlands
SEQUENCE:0
UID:eff203d119416838e208e000af346f9b
URL:http://agntconmcpconeu26.sched.com/event/eff203d119416838e208e000af346f9b
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T125000Z
DTEND:20260918T131000Z
SUMMARY:Keynote: Marlene Mhangami\, Senior Developer Advocate\, Microsoft
DESCRIPTION:\n
CATEGORIES:KEYNOTE SESSIONS
LOCATION:Auditorium (Ground Level)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:4c6e214e5b3874b7b3c16e12295d160f
URL:http://agntconmcpconeu26.sched.com/event/4c6e214e5b3874b7b3c16e12295d160f
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T125000Z
DTEND:20260918T125000Z
SUMMARY:Welcome Back - Angie Jones\, Vice President of Developer Experience\, The Agentic AI Foundation
DESCRIPTION:\n
CATEGORIES:KEYNOTE SESSIONS
LOCATION:Auditorium (Ground Level)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:94e889e3ad3b5c7474bef76b353aef46
URL:http://agntconmcpconeu26.sched.com/event/94e889e3ad3b5c7474bef76b353aef46
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T131000Z
DTEND:20260918T132000Z
SUMMARY:Keynote: Why Organizations Need an AI Control Plane for Security and Governance - Sheng Liang\, Co-Founder & CEO\, Obot AI
DESCRIPTION:How can organizations secure and govern AI agents they do not fully trust? MCP gateways can intercept and filter tool calls\, but that alone is not enough. Organizations also need complete visibility into agent activity\, consistent policy enforcement\, and centralized control. In this talk\, we explain how to move beyond MCP gateways and build an AI control plane for enterprise-wide security and governance.
CATEGORIES:KEYNOTE SESSIONS
LOCATION:Auditorium (Ground Level)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:153562e35e20f47bf2acb1a157ec089a
URL:http://agntconmcpconeu26.sched.com/event/153562e35e20f47bf2acb1a157ec089a
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T132500Z
DTEND:20260918T133500Z
SUMMARY:Keynote: MCP Made Local Models Viable - Rachel-Lee Nabors\, Developer Experience\, Arize
DESCRIPTION:By building agentic workflows that brick the moment they lose connectivity\, we've circled back to the 1980s: the dumb terminal\, the mainframe in someone else's building\, intelligence rented by the minute. The first capable models were enormous\, so we metered them by the token and shipped our context off-device. Tool bloat forced us to engineer economical harnesses: 50 tools can burn ~70k tokens\, and selection quality collapses past a few dozen options. So we built progressive tool discovery\, the wrapper pattern\, retrieval\, and routers that load only the tools a task needs. We engineered the problem down to something consumable by SAGE (Small And Good-Enough) models. On-device\, free\, private\, these smaller models are increasingly capable of running agentic workflows and calling tools.This talk covers the progress SLMs are making\, efforts like DS4\, and MCP client and server patterns built for the rise of local model adoption.
CATEGORIES:KEYNOTE SESSIONS
LOCATION:Auditorium (Ground Level)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:62fd1975975b275115e7552ba6d5c26f
URL:http://agntconmcpconeu26.sched.com/event/62fd1975975b275115e7552ba6d5c26f
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T134500Z
DTEND:20260918T141000Z
SUMMARY:Giving Your Agentic Coding AI a Security Brain - Liran Tal\, Snyk
DESCRIPTION:AI can generate a week’s worth of code before lunch and just as quickly ship SSRF\, RCE\, and path traversal vulnerabilities into prod. Rules and “/security-review” prompts aren’t enough: they’re costly\, brittle\, and non-deterministic. Run them three times\, get three answers. Meanwhile\, who vets hallucinated npm packages as the agent installs them? Oh you’re running the agent with “--dangerously-skip-permissions”? Color me surprised\, sigh. Well the good news is you don’t have to trade speed for security\, let me show you how. This talk shows a concrete\, developer-first pattern: learn how to use MCPs & Hooks to give agents real security superpowers. We’ll wire in just-in-time package health checks and deterministic code reviews via pluggable AI components\, with clear contextually engineered details for your agent. You’ll leave with a better understanding of the security dangers relying on agentic coding tools alone and a reliable and deterministic agentic workflow to make AI coding fast and safely shippable.
CATEGORIES:BUILDING RELIABLE AGENT SYSTEMS
LOCATION:G104 + G105 (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:d54fa540c8bb137f2d946e8ef40e847d
URL:http://agntconmcpconeu26.sched.com/event/d54fa540c8bb137f2d946e8ef40e847d
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T134500Z
DTEND:20260918T141000Z
SUMMARY:How We Reclaimed 20% of Engineering Capacity at Salesforce With AI Agents - Axel Uhlig\, Salesforce
DESCRIPTION:We built and deployed an AI Agent at Salesforce designed to triage production alerts using service logs. After months of iteration\, we achieved an accuracy level that earned the trust of our DevOps personnel. Today\, the agent reclaims approximately 20% of weekly engineering capacity for the teams using it.\n \n Here are our top 5 takeaways for building agents that perform consistently at high accuracy:\n 1. Specialization beats generalization: For high-accuracy tasks\, purpose-built solutions outperform generic models every time.\n 2. Provide "Proof of Work": Make it effortless for humans to verify the agent's logic. Transparency builds trust.\n 3. Minimize friction: We used Slack as the primary interface. Don't require local setups to boost adoption and usage\n 4. Build in public: Operating in shared channels allows for seamless human-agent cooperation (and agent-to-agent orchestration).\n 5. Hosted &gt\; Local: Local scripts are great for individuals\, but standardized\, team-wide automation requires a hosted environment to scale.
CATEGORIES:ENTERPRISE ADOPTION IN PRACTICE
LOCATION:Auditorium (Ground Level)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:6d0f47ae9bfc9b8d8ee9954b27dafa45
URL:http://agntconmcpconeu26.sched.com/event/6d0f47ae9bfc9b8d8ee9954b27dafa45
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T134500Z
DTEND:20260918T141000Z
SUMMARY:Attribution by Design: Skills\, MCP\, and Where Provenance Gets Built In - Ola Hungerford\, Model Context Protocol
DESCRIPTION:Agents increasingly draw on specialized human knowledge at inference time\, and the infrastructure delivering it is converging around Skills\, MCP\, and very often a mix of the two. That makes these standards a decision point: provenance either travels with the knowledge or its absence becomes the default.\n \n The MCP community is standardizing two complementary efforts: Interceptors (deterministic hooks in clients\, servers\, and gateways) and how\, why\, and when to serve Skills over MCP. This talk shows how the two fit together to standardize attribution for human expertise and other content encoded as Skills and related inference-time formats.\n \n The talk showcases two examples:\n - An attribution gateway that validates and records authorship in a centralized control plane\n - A standardized client-side hook to log and credit authors when Skills are invoked
CATEGORIES:MCPCON
LOCATION:Emerald Room (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:1968b6a3a0ea04871766fb34cc3b678d
URL:http://agntconmcpconeu26.sched.com/event/1968b6a3a0ea04871766fb34cc3b678d
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T134500Z
DTEND:20260918T141000Z
SUMMARY:The Serving Layer Is the Agent's Bottleneck - Swapnil Tiwari\, AWS
DESCRIPTION:I've spent the past year tuning open-source inference stacks (vLLM\, SGLang) for production agent systems. The same failure modes keep appearing\, and they all live in the serving layer.\n \n Biggest one: KV cache thrashing. Agents rebuild thousands of tokens of system prompt + tool schemas every turn. Prefix-aware caching fixes this in six lines of config. I've measured 55-65% latency reduction on turn 2+ across twelve deployments. Almost nobody enables it.\n \n Second: batch-of-one paralysis during tool-calling loops. Each LLM call is a single request\, GPU 80%+ idle. Disaggregated prefill/decode with continuous batching unlocks 3-5x throughput. Requires ~40 lines of change in most agent frameworks.\n \n Third: agent latency is bimodal (short tool-selection turns vs long reasoning turns). A single timeout threshold wastes GPUs or kills valid turns. Two-tier serving handles both.\n \n Open configs. Real numbers from workloads I instrumented. If you're building agents and haven't looked below the orchestrator\, this fills the gap.
CATEGORIES:OPEN TOOLING
LOCATION:G102 + G103 (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:e6911f73f4e2b8ebe6422449aa73df02
URL:http://agntconmcpconeu26.sched.com/event/e6911f73f4e2b8ebe6422449aa73df02
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T134500Z
DTEND:20260918T152000Z
SUMMARY:Workshop: Governing AI Agent Actions: MCP and Beyond - Shannon Williams & Chris Urwin\, Obot AI
DESCRIPTION:Enterprise adoption of the Model Context Protocol is accelerating\, and MCP has become the primary way agents connect to enterprise tools and data. But MCP is only part of how agents act. Agents also run CLIs\, execute Skills\, and generate code that calls APIs directly. Governing MCP well matters. Governing everything else agents can do matters just as much.\nBuilding MCP servers and writing Skills isn't particularly hard. The real challenges are deciding which actions agents are allowed to take\, controlling who can take them\, and proving it all later. These are architectural questions\, and they need answers before agents scale across an organization.\nIn this workshop\, we will:\n1.⁠ ⁠Show how to control agent actions with policies that apply across MCP servers\, CLIs\, Skills\, and agent-generated code — including allowlists\, access control by users and groups\, and human-in-the-loop approvals.\n2.⁠ ⁠Explain why enterprises need managed registries for MCP servers and Skills\, and how admin review and approval change the trust model.\n3.⁠ ⁠Work through audit and compliance requirements: capturing complete logs of agent and tool activity\, exporting to enterprise storage\, and generating reports.\n4.⁠ ⁠Demonstrate how to discover shadow AI — unmanaged agents\, MCPs\, and Skills already running in your organization — and how to block them or bring them under management.\n5.⁠ ⁠Look at token usage and spend visibility by agent\, user\, and group.\nYou'll leave with a clear picture of the architectural decisions ahead of you\, and a better sense of what your security team will require before signing off on scaling AI agents across your organization.\n
CATEGORIES:WORKSHOP
LOCATION:G106 + G107 (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:e5a5b1efda4bf7473be2fc9719ab9954
URL:http://agntconmcpconeu26.sched.com/event/e5a5b1efda4bf7473be2fc9719ab9954
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T142000Z
DTEND:20260918T144500Z
SUMMARY:Autonomous Organisations: Starting Small - Floris Fok\, Prosus
DESCRIPTION:What does it take to let AI agents run a real business? Before handing over an entire restaurant\, our team started with something much smaller: a network of vending machines.In this session\, we'll share what we've learned by giving AI agents responsibility for real world operational decisions\, including pricing\, inventory management\, and marketing. The vending machine serves as a practical testbed for exploring how autonomous organizations behave under real customer demand\, where mistakes have real consequences but the risks remain manageable.We'll discuss how this work evolved from simulated restaurant environments into live deployments\, what worked\, what failed\, and why small scale experiments are the fastest path toward larger autonomous operations. We'll also look ahead to the next phase\, including autonomous restaurants and the role robotics may play.Attendees will leave with a practical framework for experimenting with autonomous organizations\, along with lessons learned from taking AI agents out of the lab and into the real world.
CATEGORIES:BUILDING RELIABLE AGENT SYSTEMS
LOCATION:G104 + G105 (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:476e50508e46770ac755d6c59b3c7153
URL:http://agntconmcpconeu26.sched.com/event/476e50508e46770ac755d6c59b3c7153
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T142000Z
DTEND:20260918T144500Z
SUMMARY:Gating High-Risk Agentic Actions at the Relying Party With Exogenous (Out-of-Band) Inputs - Dominic Forrest\, iProov
DESCRIPTION:A Confused Deputy arises when a trusted system with legitimate authority is induced to use that authority for a high-risk or irreversible action that the Agent's principal did not intend\, creating a relying-party (RP) risk of repudiation. The Agent may arrive with valid Tokens\, passkeys\, inherited session\, or tool credentials\, even if instructions have been shaped by prompt injection or model miscomprehension. Whilst the request is authenticated\, human consent to the means taken is not.\n \n This session develops how RPs can deploy a gatekeeper to distinguish authorised access from authorised actions and produce a legally auditable record. When proving the principal is present and consenting\, it assumes that any signal produced by the agent or its device remains endogenous to the compromised context. This requires an exogenous proof that the agent cannot generate\, evaluated by the RP before execution.\n \n The talk presents a decentralised\, open-source\, relying-party pattern that does not require the agent or its operator to have onboarded to or used the scheme. It composes with OAuth\, MCP\, and passkeys\, adding the missing intent boundary for agent-mediated workflows.
CATEGORIES:BUILDING RELIABLE AGENT SYSTEMS
LOCATION:Auditorium (Ground Level)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:f2b8e059699ca51e4395c0f27a521a5c
URL:http://agntconmcpconeu26.sched.com/event/f2b8e059699ca51e4395c0f27a521a5c
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T142000Z
DTEND:20260918T144500Z
SUMMARY:Infrastructure Red Teaming With Abliterated Models: What Actually Stops Agent Attacks - Roy Belio\, Red Hat
DESCRIPTION:Safety-aligned models refuse adversarial prompts\, so you can't test whether your infrastructure controls actually work\, but the models are all still susceptible to jail-breaking. I removed that variable with an abliterated Qwen3.5 model to get zero refusals and 100% cooperation. Ran full suite of prompts with custom garak probes across three hardening tiers on an OpenClaw agent running in OpenShift. I found out what worked and what gave false sense of security. Sandbox isolation dropped credential exfiltration entirely in one step. NetworkPolicy killed cluster escalation. The prompt injection classifier caught encoding-based attacks. Three of four attack categories were fully stopped by Tier 2 (injection classification+isolation). Memory poisoning was the exception. Probes that instruct the agent to write attacker content into its own memory continued to succeed across all tiers. OWASP added this as ASI06 to its 2026 Agentic Top 10. No deployed control addresses it today. I'll present the full probe results\, the defense configurations\, and the open problem current agent architectures don't solve.
CATEGORIES:EVALUATION & TESTING
LOCATION:G102 + G103 (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:63ddbdb4ddd5f0405c976d1d829516d8
URL:http://agntconmcpconeu26.sched.com/event/63ddbdb4ddd5f0405c976d1d829516d8
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T142000Z
DTEND:20260918T144500Z
SUMMARY:Observability Meets MCP: Patterns\, Gaps\, and Standards - Matthias Loibl\, Polar Signals
DESCRIPTION:Almost every observability project and vendor has shipped an MCP server in the past year.\n Prometheus\, Jaeger\, and OpenTelemetry sit next to Grafana\, Datadog\, Honeycomb\, Polar Signals\, and a long list of others. This talk puts a few dozen of them side by side: how they handle transport\, auth\, tool design\, and read/write access\, and which ones do something genuinely interesting.\n \n The data is what makes observability hard. Time series\, distributed traces\, and profiles are dense\, high-cardinality\, and deeply nested\, and wrapping a JSON API in a few tools doesn't make any of that easier for an LLM to read. We'll look at how different servers represent these\n signals\, and what makes one format easy for a model to reason over while another just fills up the context window. We won't be proposing a new standard. The goal is to surface the best implementation patterns the industry has already converged on\, so the audience can judge which observability MCP server to adopt (or build a better one themselves).
CATEGORIES:MCPCON
LOCATION:Emerald Room (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:7a2e65d89dfdb111b414f64f27986e2d
URL:http://agntconmcpconeu26.sched.com/event/7a2e65d89dfdb111b414f64f27986e2d
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T145500Z
DTEND:20260918T152000Z
SUMMARY:No Central Brain - Fausto Albers\, WonderWhy
DESCRIPTION:Who decides what an agent treats as true? Nothing does\, and that is the point. In every system that stays reliable\, from a cell to an immune system to a market\, correctness isn't assigned by a designer\; it's selected. The parts hold competing variants\, and an external pressure culls the wrong ones. A more capable part doesn't escape this. It just gets better at exploiting whatever pressure you actually applied. You can't make the pressure random the way nature does\, but you can design it: the goal\, the loss\, the verifier\, the loop the agent runs inside. So stop dictating answers and start shaping the environment that selects them. We introduce five design laws\, each learned by building real-world agents and memory systems that had to stay honest under a pressure they couldn't game.
CATEGORIES:BUILDING RELIABLE AGENT SYSTEMS
LOCATION:G102 + G103 (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:f5511d725b5025f549b7fe6e88af1dff
URL:http://agntconmcpconeu26.sched.com/event/f5511d725b5025f549b7fe6e88af1dff
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T145500Z
DTEND:20260918T152000Z
SUMMARY:Shipping a Production App in 10 Days: A Real Measurement of AI-Assisted Development - Julien Dubois\, GitHub
DESCRIPTION:We've all seen the AI coding demos. But what does it really cost to ship a production application with an AI agent\, and how much time does it actually save? This talk answers that with hard numbers from a real\, open-source project: BootUI ( https://github.com/jdubois/boot-ui )\, a multi-module Java project with roughly 40 deeply-integrated feature panels\, an embedded Vue 3 console\, ~83\,000 lines of code\, ~116 test suites\, and a full release pipeline. It was built through a tagged 1.0.0 release in about 10 calendar days by a single developer driving the GitHub Copilot coding agent\, at a sustained pace of ~20 merged pull requests per day. Using git history\, PR metadata\, and code metrics\, we reconstruct two timelines: what the project actually took with AI (~80-110 hours of human effort)\, and a grounded estimate of what the same scope would take a senior developer by hand (~6.5-8.5 months). You'll leave with a realistic mental model of where AI coding delivers 10x-plus leverage on Java projects\, where it doesn't\, and the practices that let you safely accept high agent throughput.
CATEGORIES:ENTERPRISE ADOPTION IN PRACTICE
LOCATION:Auditorium (Ground Level)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:f1a95c1d795bd1a5dec2e7932e3a77d5
URL:http://agntconmcpconeu26.sched.com/event/f1a95c1d795bd1a5dec2e7932e3a77d5
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T145500Z
DTEND:20260918T152000Z
SUMMARY:MCP Challenges & Opportunities - Sam Morrow\, GitHub; Angie Jones\, Agentic AI Foundation; Shaun Smith\, Hugging Face
DESCRIPTION:Join Jeremiah Lowin (Fast MCP)\, Shaun Smith (fast-agent) and Sam Morrow (GitHub MCP) for a panel on the challenges and opportunities of shipping MCP\, hosted by Angie Jones\, VP of Developer Experience at the AAIF.\n \n By bringing perspectives from server\, SDK and agent harness developers together in the same panel\, you’ll see where their experiences align\, l where they diverge\, where they see the protocol heading and what they’re excited about.
CATEGORIES:MCPCON
LOCATION:Emerald Room (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:307f39bf0e2950072d4dbd0eacf8719f
URL:http://agntconmcpconeu26.sched.com/event/307f39bf0e2950072d4dbd0eacf8719f
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260724T131628Z
DTSTART:20260918T145500Z
DTEND:20260918T152000Z
SUMMARY:The Autonomous Enterprise – Scaling Computer Use With Holo3 and HoloTab - Pierre-Louis Cedoz\, H Company
DESCRIPTION:H Company is the leading agentic AI startup in Europe\, based in Paris\, specialized in computer use.\n \n The AI landscape is shifting rapidly from passive text generation to active execution. The frontier belongs to Agentic AI\, systems that don't just chat\, but autonomously navigate digital environments to complete complex workflows.\n \n At H Company\, we bridge this gap between frontier research and production-grade deployment. We will explore how H Company built Holo3\, our state-of-the-art model family designed specifically for "Computer Use" (GUI perception\, planning\, and OS navigation). Moving from theory to practice\, we will demonstrate how these compact\, high-efficiency models power our latest enterprise tools—including HoloTab\, our autonomous AI browser companion. Finally\, we will unpack the unified infrastructure model required to train\, deploy\, and scale these agents securely across multi-cloud environments.
CATEGORIES:OPEN TOOLING
LOCATION:G104 + G105 (Level 1)\, Amsterdam\, Netherlands
SEQUENCE:0
UID:2471231f345eea2b362764214d8254b1
URL:http://agntconmcpconeu26.sched.com/event/2471231f345eea2b362764214d8254b1
END:VEVENT
END:VCALENDAR