AGNTCon + MCPCon Japan 2026

As AI agents move from answering questions to taking actions across enterprise systems, reliability cannot be achieved through model quality alone. A practical production architecture separates non-deterministic reasoning from deterministic execution.

This session explores how to define that boundary with MCP-enabled tools. Agents can interpret ambiguous requests, gather context, and choose among bounded options. Deterministic workflows, services, and policy checks can then perform repeatable operations such as validation, approvals, system updates, notifications, audit logging, and recovery.

Using common enterprise action patterns, we will examine how this division of responsibility improves output quality while reducing unnecessary reasoning, latency, and token cost. We will also discuss how to design action interfaces with clear intent, constrained outcomes, and recoverable execution.

Rather than treating agents and workflows as competing approaches, this session presents them as complementary parts of a single execution architecture. Attendees will leave with a practical framework and checklist for designing reliable, cost-aware MCP capabilities across open-source agent frameworks and enterprise environments.

---

In order to facilitate networking and business relationships at the event, you may choose to visit a third party's booth or access sponsored content. You are never required to visit third party booths or to access sponsored content. When visiting a booth or participating in sponsored activities, the third party will receive some of your registration data. This data includes your first name, last name, title, company, address, email, standard demographics questions (i.e. job function, industry), consenting to receipt and use of such data by the third-party recipients, which will be subject to their own privacy policies.

___________________________
Presentation Language: Japanese

Captioning will be available for attendees in 50+ languages through Wordly. See instructions in each room to utilize captioning.

In this workshop, we’ll talk about goose and goose development kit, and look at the building blocks that make it possible to build your own agentic applications with goose.

We’ll start with goose and the **Goose Reference Client (GRC)**, looking at how the reference client demonstrates the capabilities and patterns of the goose ecosystem. We’ll then dive into the **Goose Development Kit (GDK)** and explore how developers can use its APIs and libraries to incorporate goose capabilities into their own applications.

Through a step-by-step walkthrough and live examples, we’ll look at how the GDK can be used to work with model providers, stream model responses, handle tool calls, and build application-specific experiences on top of goose. We’ll also explore how the reference client and GDK fit together and where different layers of the goose stack make sense for different use cases.

By the end of the workshop, attendees will have a clearer understanding of goose, the role of the Goose Reference Client and GDK, and how they can start using the GDK as a foundation for building their own agentic applications and experiences.

___________________________
Presentation Language: English

DevOps and Platform teams now work with hundreds of AI Agents in their internal systems. These Agents usually run with credentials that can touch everything, including your production servers. This could lead to problems.

This workshop will teach you how to add delegated authorization to your AI Agents, at scale.

We'll build a DevOps deploy agent on goose - the open-source agent from the Agentic AI Foundation and then give it fine-grained permissions using Relationship-Based Access Control (ReBAC). Along the way you'll get hands-on with the Google Zanzibar model of fine-grained authorization (ReBAC) and why it fits AI agents: scoped delegation, expiring grants, instant revocation, and hierarchical permissions where revoking staging access automatically suspends production too, something role-based systems can't express cleanly.

This is a self-guided, hands-on workshop, and everything runs locally with open-source tooling.

Prerequisites:

• Docker (can build a GitHub devcontainer as well)

• Python 3.10+

• goose installed, plus an API key for any LLM goose supports

___________________________
Presentation Language: English

Captioning will be available for attendees in 50+ languages through Wordly. See instructions in each room to utilize captioning.

Teams are moving coding agents onto self-hosted open-weight models to control inference cost, and real sessions routinely span tens of turns and hundreds of thousands of tokens. But the only common signal for judging those models is the static accuracy benchmark, which says little about how a model behaves across a real, multi-turn session.

This session closes that gap with a trace-based evaluation method built on open technology: OpenTelemetry for capture and MLflow for analysis. Through a case study tracing real Claude Code sessions on a 120B-class open-weight model and a frontier model, it surfaces behaviors no leaderboard reports. For example, in the sessions we traced, the model's logged reasoning recorded a user's constraint, and the same turn violated it. An accuracy score sees only the wrong action; the trace shows the model had the rule in hand and did not follow it.

Attendees leave with a reusable observability architecture for their own agents, metrics that go beyond accuracy, and a clear view of what running a coding agent on open weights actually costs, in reliability and not only in dollars.

___________________________
Presentation Language: English

Captioning will be available for attendees in 50+ languages through Wordly. See instructions in each room to utilize captioning.

As AI agents move from local tests to real-world use, developers face a big problem: How do we easily find, direct, secure, and track AI traffic going to MCP servers? Standard API gateways do not understand LLM tool calls, and writing static lists of agents is too hard to manage.

In this hands-on workshop, we will connect AI agents and external tools easily using the standalone versions of Solo.io’s agentgateway and AgentRegistry. We will show you how to build a strong control layer for the Model Context Protocol (MCP) using simple local tools like Docker.

Participants will learn how to:

• Discover: Run AgentRegistry locally to list, version, and find MCP servers dynamically.

• Control: Set up agentgateway as a smart proxy to catch and manage agent requests.

• Secure: Add AI-specific rules, like rate limits and basic access control, to agent tool calls.

• Observe: See exactly which tools the agents are using and how fast they respond.

Join us to learn how to build a safe, easy-to-run foundation for your multi-agent systems right on your laptop!

___________________________
Presentation Language: English

Captioning will be available for attendees in 50+ languages through Wordly. See instructions in each room to utilize captioning.