-
09:00 • Keynote: Welcome - Angie Jones, Vice President, Agentic AI Foundation
-
09:05 • Keynote: Mazin Gilbert, Executive Director of Agentic AI Foundation; IEEE Fellow
-
09:20 • Keynote: David Soria Parra, Co-creator of MCP, Anthropic
-
09:30 • Keynote: Reactive Agents: Your Agent Doesn't Need to Be Always On - Clare Liguori, MCP Core Maintainer & Senior Principal Engineer, AWS
-
10:15 • From Personal Agent To Org Catalog: 13 Specialists, One Orchestrator - Nick Veenhof, GitLab
-
10:50 • An Orchestra of Agents: What I Learned Running a Multi-Agent System for 5,000+ Developers - Muhammad Ahsan Ayaz, Scania
-
11:25 • When NOT To Use an Agent: Choosing Between Workflows, Services, and Agent Systems - Jigyasa Grover, Uber & Rishabh Misra, Atlassian
-
12:00 • The Other 90%: Agentic AI for the Legacy Codebases Nobody Wants To Touch - Ayush Bhardwaj & Chitralekha, Siemens
-
12:35 • 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
-
13:10 • What *IS* an Agent's Identity? - Christian Posta, Solo.io
-
14:45 • Welcome Back - Angie Jones, Vice President, Agentic AI Foundation
-
14:50 • Keynote: Marlene Mhangami, Senior Developer Advocate, Microsoft
-
15:05 • Keynote: Inside AI Agents -- Offloading Human Tasks - Maarten Grootendorst, Creator of BERTopic, KeyBERT & PolyFuzz, Member of Technical Staff - Google DeepMind
-
15:20 • Keynote: The Browser Isn't Dead Yet - Rachel-Lee Nabors, Founder, Mima.social
-
15:45 • Six Months of Proof: Independently-Verifiable Records for Agent Actions Under the EU AI Act - Steven Mih, Action State Group, Inc.
-
16:20 • 90 Days To Agentic Engineering - Thomas Schöne, Project Lions Development GmbH
-
16:55 • Distributed Mess: A Production Guide To Multi-Agent Failures - Huong Vu, Databricks
-
17:30 • Verify, Abstain, or Amplify: A Field Guide To Confidently-Wrong Agents - Michal Orzechowski, Sano – Centre for Computational Personalised Medicine
-
10:15 • What Does It Take To Ship a New MCP Spec - Den Delimarsky, Anthropic
-
10:50 • Stateless: The Future of MCP Transports - Kurtis Van Gent, Google & Shaun Smith, Hugging Face
-
11:25 • Call Now, Fetch Later: Durable MCP Tasks on an Event Log - Jeremy Frenay, Lenses
-
12:00 • MCP Conformance Testing V1.0, Testing the 2026-07-28 Spec in SDK's and Online - Paul Carleton & Felix Weinberger, Anthropic
-
12:35 • MCP Doesn't Have a Context Problem - Sam Morrow, GitHub
-
13:10 • Session to be Announced - Florian Bauer, OpenAI
-
15:45 • MCP in Production: Reliability Contracts for Multi-Agent Tool Use - Krishna Chaitanya, Meta Platforms
-
16:20 • MCP, Skills, and the Persistence of AI Agent Compromise - Steven Duckaert, Onyx
-
16:55 • MCP Borrowed LSP's Design. It Skipped LSP's Lesson - Gorkem Ercan, Jozu
-
17:30 • What a Year of Breaking MCP Tells Builders: Protocol Gaps and What Ships Next - Amine Raji, Molntek AB
-
10:15 • The Modern AI Stack: Agents, MCP and Skills - Adewale Abati, Independent
-
10:50 • Legal Implications Under EU Law When Deploying AI Agents - Mirela Takacs, Law Office Takacs Mirela
-
11:25 • CHAP, an Open Protocol for Auditable Human-Agent Collaboration - Dr Arsalan Shahid, Brightbeam AI
-
12:00 • From Opaque To Observable: Tracing Multi-Agent OpenClaw Workflows With OpenTelemetry - Pavan Sudheendra, Cisco Systems
-
12:35 • A2A Goes Stable: What Changed, Why, and What's Next - Sam Betts, Cisco Systems & Kuba Herczyński, Google
-
13:10 • Exploring WebMCP: What Happens When AI Agents Start Using Websites? - Sylwia Laskowska, Atos
-
15:45 • Sandboxing My AI Agent, One Layer at a Time - Juan Antonio Osorio, Stacklok Inc.
-
16:20 • What Networking Got Right That Agentic AI Risks Getting Wrong: The Case for an Agent Control Plane - Parisa Foroughi, Nokia
-
16:55 • Skills Need SemVer Too - Pedro Rodrigues, Supabase
-
17:30 • MAS-Lab: An Open Framework for Spec-Driven, Interoperable Multi-Agent Systems - Jordan Augé, Cisco Systems
-
10:50 • Sponsored Session: Beyond the Easy 80%: Bringing Legacy, Spatial, and Locked-Down Data to MCP - Sanae Mendoza, Safe Software
-
11:25 • Sponsored Session: Agents, Infrastructure, and the Future of AI-native Applications - Kevin Cochrane, Vultr
-
12:00 • Sponsored Session: Building a Sovereign AI Governance Stack with Open Source - Roman Swoszowski, Grape Up
-
12:35 • Sponsored Session: Breaking the Governance Bottleneck: Why Scaling Control Gets Agents to Production - Dr. Rania Khalaf, WSO2
-
13:10 • Your Agents Need a Router: One Integration for Every Model and Tool - Ignasi Barrera, Tetrate.io
-
15:45 • Your Agent Has a Wallet. Who Has the Receipts? - Bharath Nallapeta, Mirantis Inc.
-
16:20 • Agentic AI for Enterprise Mainframes: From Dead Code Elimination To Business Knowledge - Thamarai Selvi Ravi Kumar, Legal and General
-
16:55 • We Built an Agent, We Shipped a Compiler. Here's Why. - Joel Verezhak, Grafana Labs
-
17:30 • The Unix Philosophy for AI Agents: Filesystems as the Context Primitive - Cannis Chan & Daniel Temesgen, Bloomberg
-
09:00 • Keynote: Welcome - Manik Surtani, CTO, Agentic AI Foundation
-
09:10 • Keynote: Getting to Stateless MCP: In Production - Shaun Smith, MCP and Transport Working Group Maintainer, Hugging Face
-
09:25 • Keynote: Agents as Actors: Harnessing the Power of Agentic Infrastructure - Idit Levine, Founder & CEO & Keith Babo, Chief Product Officer, Solo.io
-
09:35 • Keynote: State of the Software Factory - Dexter Horthy, CEO and Co-Founder, HumanLayer
-
10:55 • From "Works on My Prompt" To Production SLOs: Building Agent Observability - Manik Khandelwal, Microsoft
-
11:30 • Governance You Can Run: Checkable Properties for Production Agents - Seshu Tolety & Ayush Bhardwaj, Siemens
-
12:05 • When Agents Run Healthcare: Building Reliable Agentic Systems in Highly Regulated Environments - Janosch Woschitz, BARMER
-
12:40 • Stateless Agents, Stateful Worlds: Designing for Interruption - Arul Kumaran, Luracast / Portel
-
13:15 • Agent-Smith: Never Send a Human To Do a Machine’s Job - Glenn ten Cate, The Linux Foundation & Jorge Carvalho, Nedap
-
15:00 • Welcome Back - Manik Surtani, CTO, Agentic AI Foundation
-
15:05 • Keynote: Three Doors to One Tool: MCP vs WebMCP vs CLI - Frédéric Barthelet, CTO & Co-founder, Alpic & Dominic Farolino, Editor of the WebMCP Specification & Software Engineer, Google
-
15:20 • Keynote: Why Organizations Need an AI Control Plane for Security and Governance - Sheng Liang, Co-Founder & CEO, Obot AI
-
15:45 • How we Reclaimed Significant Engineering Capacity at Salesforce with AI Agents - Axel Uhlig, Salesforce
-
16:20 • Gating High-Risk Agentic Actions at the Relying Party With Exogenous (Out-of-Band) Inputs - Dominic Forrest, iProov
-
16:55 • Shipping a Production App in 10 Days: A Real Measurement of AI-Assisted Development - Julien Dubois, GitHub
-
10:20 • Potential Issues for Cross-domain Multi-hop API Calls and Their Solution Proposal - Takashi Norimatsu, Hitachi, Ltd.
-
10:55 • ID-JAG: Solving OAuth Sprawl for Enterprise AI Agents - Joey Orlando, Archestra.AI; Aaron Parecki, Okta & Paul Carleton, Anthropic
-
11:30 • Economies of Scale for MCP and Agents: Why You Need an Identity Broker - Magnus Jungsbluth & Jan Brennenstuhl, Zalando SE
-
12:05 • MCP Apps and the Nearly Headless Web - Liad Yosef, MCP Apps
-
12:40 • From API Catalogs To Agent Catalogs: Solving MCP Server Discovery With Open Resource Discovery - Vyshnavi Gadamsetti & Sebastian Wennemers, SAP SE
-
13:15 • Spotify’s Bet on MCP and Investment in Open Source - Reinoud Kruithof & Yannick Epstein, Spotify
-
15:45 • Attribution by Design: Skills, MCP, and Where Provenance Gets Built In - Ola Hungerford, Model Context Protocol
-
16:20 • Most MCP Servers are Empty - David Golverdingen, Warmtebouw
-
16:55 • MCP Challenges & Opportunities - Sam Morrow, GitHub; Angie Jones, Agentic AI Foundation; Shaun Smith, Hugging Face; Shub Argha, Arcade
-
10:20 • Pull Requests Are Dead, Long Live Peer Review - Dylan Ratcliffe, Overmind
-
10:55 • From MCP Playground To Org-Wide Infrastructure: Lessons From Building Booking.com's Agent Foundry - Anushka Bhandari, Booking.com
-
11:30 • I Was the Bottleneck, Not the Agent - Vincent Ysmal, Datadog
-
12:05 • Governed Agent Autonomy: Building a Control Plane for Agentic Systems - Nnenna Ndukwe, Qodo AI
-
12:40 • Agents Talking To Agents: MCP, A2A, and the Reality of Multi-Agent Orchestration in Production - Willem Berroubache, Orange
-
13:15 • Beyond Chatbots: Agentic UI With Open Standards - Manfred Steyer, ANGULARarchitects
-
15:45 • The Serving Layer Is the Agent's Bottleneck - Swapnil Tiwari, AWS
-
16:20 • Infrastructure Red Teaming With Abliterated Models: What Actually Stops Agent Attacks - Roy Belio, Red Hat
-
16:55 • No Central Brain - Fausto Albers, WonderWhy
-
10:20 • Self-Healing Agents Need Observability - Marcelo Trylesinski, Pydantic
-
10:55 • Outcome Engineering: Why Your Agentic Architecture Doesn't Matter (Yet) - Kierra Dotson, Further
-
11:30 • Agents Can Pay. Can They Prove It? - Diego Zuluaga, Open Mobile Hub
-
12:05 • Testing Agents and Their Tools: Offline Evaluation, Synthetic Tasks, and A/B Experiments - Ksenia Bobrova, GitHub
-
12:40 • Beyond Vibe-Testing: Engineering Deterministic Agent Skills - Shuva Jyoti Kar, Palo Alto Networks
-
13:15 • From Vibes To Data: Evaluating Agents on Your Real Work - Ville Hellman, Datadog
-
15:45 • Giving Your Agentic Coding AI a Security Brain - Liran Tal, Snyk
-
16:20 • Autonomous Organisations: Starting Small - Floris Fok, Prosus
-
16:55 • The Autonomous Enterprise – Scaling Computer Use With Holo3 and HoloTab - Pierre-Louis Cedoz, H Company
