AGNTCon + MCPCon Europe 2026

AI models are becoming a commodity. GPT-4, Claude, Gemini.  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.  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,  still have no real path to an agent. In most enterprises, that's exactly where the decision-relevant data lives. 
Drawing 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. 

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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