AGNTCon + MCPCon Japan 2026

___________________________
Presentation Language: English

Japan is rapidly embracing Agentic AI. New products, services, and platforms are emerging as organizations explore how AI agents can transform the way we work and build software.

Yet an important question remains:

Who is building the technologies that define the future of AI agents?

Behind every protocol, specification, and open source project is a community shaping how agents communicate, collaborate, authenticate, authorize, and make decisions. These communities are defining the foundations of the Agentic AI ecosystem.

While participation in upstream communities continues to grow worldwide, Japan's presence in the development of the standards and infrastructure behind this ecosystem remains limited.

As AI agents become more widely adopted, adoption alone is not enough. Open source projects and standards bodies are determining how the ecosystem evolves, and participation in these communities allows organizations and individuals to help shape that future.

The future of Agentic AI is being built today through open source projects, technical standards, and the communities behind them.

Will Japan remain a consumer of that future, or become a contributor to it?

___________________________
Presentation Language: English

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

AI models and agent frameworks are advancing rapidly, but intelligence alone does not make an organisation agentic. To create real value, agents must safely interact with enterprise systems, data, people and business processes.

This keynote explores the architectural challenge beyond the model: building a control and execution layer for enterprise AI. MCP is an important step toward interoperable agent-to-tool interaction, but production systems also require identity, least-privilege access, policy enforcement, human approvals, orchestration, observability and auditability.

The session will offer a practical framework for thinking about how open protocols and agent systems can move from impressive demonstrations to trusted, scalable enterprise action. The central question is not whether an agent can use a tool, but whether an enterprise can safely allow it to do meaningful work.

___________________________
Presentation Language: English

Tool descriptions tell an agent what a tool can do, but not how to orchestrate those capabilities toward a goal, or supplement them with specialized knowledge. Agent skills have become a popular and accessible way to close that gap, and many organizations now ship skills alongside their servers. The community effort to standardize that pairing has drawn 50+ contributors from 25+ organizations across the entire AI infrastructure stack: cloud platforms, data platforms, enterprise SaaS, gateways, and independent implementers. This talk covers where that momentum is headed, and how Extensions let the protocol evolve to meet real-world demand while balancing the stability, security, and developer experience that production systems require.

___________________________
Presentation Language: English

The hardest part of agentic engineering isn't writing the code; It’s proving that a prompt tweak or a new tool schema didn't completely break your agent's routing logic. Traditional unit testing falls short when dealing with non-deterministic agent trajectories.

This session looks at how to build an automated local evaluation and regression testing pipeline for ADK workflows. We will walk through how to programmatically mock tool responses, simulate user edge cases, and run parallel assertions against agent trajectories using open-source evaluation frameworks. Attendees will learn how to catch infinite loops, detect tool-calling degradation, and establish a baseline scoring rubric for agent accuracy before code ever hits a production branch.

___________________________
Presentation Language: English

Most agent memory is a chat log with extra steps. Dump turns into a vector store, retrieve the top-k by cosine similarity, and hope the right context shows up. It usually doesn't, and the agent pays for it three turns later.

Agentmemory MCP Server began as a fix for that. It combines BM25, dense vector search, and a knowledge graph, fuses them with reciprocal rank fusion, and ages stored memories on an Ebbinghaus forgetting curve so old context decays instead of drowning new signal. On LongMemEval-S it reaches 95.2% recall at 5. The repo trended on GitHub, ranked on Product Hunt, got picked up by AlphaSignal, and was recognized by the Agentic AI Foundation, none of it paid for.

This talk covers how it was built and where the easy version breaks. Single-method retrieval looks fine in a demo and falls apart on long histories. I'll show why each method earns its place, how the pieces compose with one engine an agent can query over MCP, and which design decisions held up once real workloads hit them.

You'll leave with a memory model that beats top-k vector search and a clear picture of how to expose it to agents through MCP.

___________________________
Presentation Language: English

AI-powered incident response sounds like the perfect use case for autonomous agents, but giving them unrestricted access to raw alerts and logs can quickly turn automation into hallucination. Whether you're debugging production outages or investigating failed deployments, engineers still spend hours manually correlating signals across disconnected observability tools.

In this talk, we'll break down the anatomy of a reliable agentic incident investigation system and show why structured incident context outperforms raw telemetry, how evidence enrichment improves reasoning, and why bounded context is critical for trustworthy AI agents.

We'll walk through production-ready patterns for building dependable operational agents:
1. Structured evidence gathering from Datadog, New Relic, Splunk, and Prometheus
2. Context engineering through alert correlation and deployment metadata
3. Long-term memory using historical incidents stored in a vector database
4. Human-agent collaboration that validates AI-generated RCAs and continuously improves future investigations.

Thus helping you reduce manual triage, lower MTTR, and build reliable, production-ready AI-driven incident response systems.

___________________________
Presentation Language: English

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

Modern agent workflows rarely finish in a single tool call. Commerce, travel, healthcare, and enterprise operations all require multi-step, stateful, failure-prone transactions that span agents, tools, and time. MCP today excels at stateless tool invocation, but production systems demand more: resumability, idempotency, compensation, human-in-the-loop, and trust boundaries.

In this talk, we present a Stateful MCP architecture for long-running transactions, using Universal Commerce Protocol (UCP) checkout flows as a real-world case study. We’ll walk through patterns for durable context, agent coordination, transaction lifecycles, rollback strategies, and human approvals, and show how MCP can serve as the orchestration layer for multi-agent workflows that behave more like distributed systems than chatbots.

___________________________
Presentation Language: English

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

Agent sandboxes are often described as ephemeral, but real MCP tool workflows are not. Agents edit files, install dependencies, run tests, download inputs, generate reports, and resume after failures. When workspace state is treated as disposable, reproducibility, isolation, and debugging become unnecessarily painful.

This talk presents a practical framework for designing durable volumes in agent sandboxes. Through a structured checklist — covering lifecycle management, tenant isolation, quotas, snapshots, read-only sharing, dependency caches, artifact retention, remount recovery, and audit trails — attendees will learn how to reason about workspace state systematically.

We then map these requirements to Kubernetes PersistentVolumes and explore the tradeoffs using JuiceFS CSI as a concrete open-source example. JuiceFS is used for its strong Kubernetes integration and snapshot capabilities, though the framework applies equally to local containers, serverless environments, and remote tool sandboxes.

___________________________
Presentation Language: English

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

"Every MCP server, skill, and plugin in your coding agent is code or instructions you never really reviewed, running with your access to your database, your repos, and your keys. Three different ways in, and almost nobody is watching any of them."

Most of the agent security conversation is about prompt injection. Meanwhile there are three underserved vectors sitting right inside the tools you use every day:

- **MCP servers** run with the same access you have. One can look clean when you approve it and change its behavior later, or pull in a compromised dependency on the next run.
- **Skills and instruction files** (`SKILL.md`, `AGENTS.md`, `CLAUDE.md`, rules files) are just text. Nothing to install, nothing to flag. They quietly reshape what your agent does, and hidden instructions, zero-width characters, and pipe-to-shell tricks ride in the same way.
- **Plugins** bundle the first two together and ship through marketplaces with uneven vetting, so a single install can bring in both an MCP server and a skill you never opened.

I'll show where each one lives on disk, why the usual tooling misses it.

___________________________
Presentation Language: English

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

AI coding agents are useful in isolated demos; the hard problem is making them controlled enough to ship production code. At Delphi, we built an agentic software factory that turns product specs and engineering tickets into scoped pull requests, then routes those PRs through reviewer agents, CI, browser verification, and merge gates.

This session breaks down the operating system around the agents: how we package repo context, encode architectural rules, isolate attempts in worktrees, make agents cite source-of-truth patterns, prevent drift from legacy code, and decide what should stay human-controlled. I will also cover failure modes we hit in production: stale context, over-broad diffs, flaky tests, review spam, false confidence, and agents copying the wrong pattern.

Attendees will leave with a practical blueprint for moving from “agent writes code” to a controlled delivery pipeline for agent-generated software.

___________________________
Presentation Language: English

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

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.

___________________________
Presentation Language: English

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

There has been a lot of progress in agentic frameworks (such as Langchain, CrewAI, Autogen, among others), most of them written in and targeting Python developers. These frameworks allow you to build multi-agent systems that are co-located inside the same application.

That works well for fast experimentation and building prototypes, but production systems live or die on scalability, security, observability and governance. At the end of the day agents are software that we need to ship, run an operate on production, much like any other type of enterprise software.

In this session we will show how to build distributed agentic, MCP-connected systems that are ready for enterprise scale. We'll cover real production patterns such as agentic orchestration patterns, MCP interoperability, agent/tool coordination, observability and tracing and enterprise integration reusing our existing platforms.

___________________________
Presentation Language: English

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

Open protocols like MCP and A2A let you combine agents and tools from different teams into one system.

But at company-wide scale, new challenges arise: who can access the system, who can call which agent, whether it fails safely, and whether it follows internal governance. Coding agents now write most of the code, so the spec we give them shapes the whole system's quality.

We'll share how we tackled this from two sides on a company-wide MCP × A2A platform.

Architecture side: where to declare per-agent access, how to handle attribute-based authorization, how to split the write and read sides of authorization data, and how to stay fail-closed, mapped to standard authorization-control models.

Development-process side: a multi-stage review of the requirements given to coding agents, covering format, clarity, cross-walk with external standards, and adversarial testing. This catches auth and governance issues, plus input validation flaws and data leakage, before code is written.

You'll come away with ideas for an interoperable MCP/A2A authorization layer, a reusable way to gather enterprise-grade requirements, and a view of specs themselves as security assets.

___________________________
Presentation Language: Japanese

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

Technical debt lives in code. Cognitive debt lives in your head. Intent debt, Addy Osmani's term for the goals, constraints, and rationale behind a decision that never got written down, lives nowhere. It's the one debt agents can't pay down: an agent drafting a spec fills the gap with a confident guess, and the guess is usually wrong.

This talk covers building context graphs that capture the why: connecting decisions to the document threads and ticket discussions where humans actually made them, then exposing that structure to agents alongside code and data. I'll draw on an open-source toolkit that bootstraps context graphs from existing work artifacts (workspace threads, ticket histories) and the modeling questions that turned out hard: what separates a decision from a discussion, and when capture should run as a background process versus an explicit act.

Vendors now race to pitch "context layers for agents." I'll argue the differentiator isn't collection but connection: rationale linked to the entities, people, and prior choices it affects: queryable, not just retrievable.

You'll leave with patterns for making the why available to every agent that touches your work.

___________________________
Presentation Language: English

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