AGNTCon + MCPCon Japan 2026: Full Schedule

2026 September 10-11 | Tokyo, Japan
View More Details & Registration

IMPORTANT NOTE: Timing of sessions and room locations are subject to change.

10:05 JST

Stateless MCP: Inside the 2026 Transport Spec - Himanshu Sangshetti, Mem0

Thursday September 10, 2026 10:05 - 10:30 JST

Hall 1F

Most MCP servers in production today are stateful- each client session is pinned to one server instance.

That works on a single node. Add a load balancer and scale horizontally, and sessions start breaking: Kubernetes routes a request to the wrong pod, a Fargate deployment rolls and drops active connections, and NGINX or AWS ALB need special configuration just to keep the server reachable.

The 2026 spec release candidate, locked May 21, fixes this at the transport layer through three SEPs.
- SEP-1442 removes the mandatory init handshake so negotiation folds into the first request.
- SEP-2322 makes elicitation stateless.
- SEP-2243 mirrors routing data into HTTP headers so load balancers can route without parsing the payload.

This session covers what each SEP changes, what breaks in the server you run today, and what to refactor before the spec ships. I'll also show how we externalize session state at Mem0, so a stateless server keeps the memory and context a real agent needs.

You'll leave with a migration checklist and an architecture for stateless-first MCP.

Speakers

Himanshu Sangshetti

AI Engineer, Mem0

Himanshu Sangshetti is an AI Engineer at Mem0 (50k+ Github stars).

With a background in AI, cloud, and DevOps, he builds the memory layer for AI agents and helps engineers design and operate them in production.

An AWS Community Builder, HashiCorp Ambassador, and former AWS Cl... Read More →

Thursday September 10, 2026 10:05 - 10:30 JST
Hall 1F

MCPCon

Audience Level Intermediate

10:40 JST

MCP Auth: Am I Doing It Right? - Paul Carleton, Anthropic

Thursday September 10, 2026 10:40 - 11:05 JST

Hall 1F

Authorization in MCP has been through a number of revisions in the past year. Some major (remember when the authorization server and resource server were expected to be the same?) and some minor. As the specification has stabilized, it can be difficult to know: Am I doing it right?

In this talk we'll briefly recap where MCP Auth came from and where it is now, and then we'll dig into Auth best practices based on evolving discussions and connecting Claude.ai to loads of MCP servers in practice.

We'll cover things like: client registration, progressive authz with challenges, and enterprise managed auth to leverage existing SSO connections.

We'll also explore the latest extensions in development and how to put them together into a cohesive solution for human-in-the-loop but also agentic and on-behalf-of flows.

Lastly, we'll cover how to leverage MCP's conformance testing suite to see how closely you're following best practices, using either client, server or authorization server test suites.

Speakers

Paul Carleton

Member of Technical Staff, Anthropic

Paul Carleton is a Core Maintainer of the Model Context Protocol and Auth Nerd at Anthropic, where he leads auth implementations across Anthropic's clients and the TypeScript and Python SDKs. He drives MCP conformance testing efforts to ensure consistent behavior across the ecosy... Read More →

Thursday September 10, 2026 10:40 - 11:05 JST
Hall 1F

MCPCon

Audience Level Intermediate

11:15 JST

MCP 2026-07-28 Under the Microscope: Security Implications for Stateless Agents - Thejes sree Satheesh kumar, Thoughtworks & Srinivasan Sekar, TestMu AI

Thursday September 10, 2026 11:15 - 11:40 JST

Hall 1F

The MCP 2026-07-28 release candidate introduces a major shift in how agents connect, authenticate and manage state. With a stateless protocol core, first-class extensions and hardened authorization, the new spec improves scalability and interoperability, but it also changes the security model in ways that many builders may not fully anticipate. In this talk, I will examine the release candidate through a defender’s lens and highlight the practical risks that emerge when session state disappears, trust boundaries move and extension-based flexibility expands the attack surface. I will discuss failure modes such as broken state assumptions, capability confusion, unsafe cross-client behavior, and authorization mistakes in real deployments. The session will also cover concrete hardening patterns for secure MCP adoption, including least-privilege tool design, explicit state handling, authorization scoping, telemetry and rollout validation. Attendees will leave with a practical checklist for evaluating stateless MCP systems and defending agent runtimes in production.

Speakers

Thejes sree Satheesh kumar

Quality Analyst, MCP and AI Security Researcher, Thoughtworks

Thejes Sree Satheesh Kumar (she/her) is a Quality Analyst – Consultant at ThoughtWorks specializing in application and AI security testing. A CEH, CompTIA Security+ professional, With a strong background in automation testing (like Playwright), she combines quality engineering and... Read More →

Srinivasan Sekar

Director of Engineering, TestMu AI

Srinivasan Sekar is a Director of Engineering at TestMu AI (formerly LambdaTest). He loves contributing to Open Source. He is an Appium Member and Contributor to various open-source repositories like Selenium, Webdriver.io, taiko, etc. He worked extensively on testing various Microservices... Read More →

Thursday September 10, 2026 11:15 - 11:40 JST
Hall 1F

MCPCon

Audience Level Intermediate

13:30 JST

Do Tools Still Matter? MCP Tool Design in the Age of Code Mode - Ruben Casas, Postman

Thursday September 10, 2026 13:30 - 13:55 JST

Hall 1F

The first wave of MCP adoption was defined by abundance. Every API endpoint became a tool, every workflow became a collection of tool calls, and many servers exposed hundreds of operations directly to agents. It worked, but at a cost: bloated context windows, slower tool selection, and increasingly unreliable agent behaviour.

But then Code Mode appeared!

With approaches Code Mode agents can search an API surface, generate code, and interact with services directly. If models can consume entire APIs and write code to acomplish a task, does tool design still matter?

In this talk, we'll compare three approaches to agent tooling: curated workflow-oriented tools, tool discovery and search, and Code Mode's search-and-execute model. Using real-world examples, benchmarks, and evals, we'll explore the trade-offs in reliability, latency, token usage, and task success.

Attendees will leave with a practical framework for deciding when to consolidate tools, when to expose APIs, and whether the future of MCP is better tools or fewer tools altogether.

Speakers

Ruben Casas

Staff Engineer, Postman

Ruben Casas is a Google Developer Expert and Staff Engineer at Postman. He builds developer tooling, AI agents, and MCP apps, and writes about frontend architecture at scale and AI. Ruben is a podcast guest and has spoken at major conferences, sharing insights from large-scale migrations... Read More →

Thursday September 10, 2026 13:30 - 13:55 JST
Hall 1F

MCPCon

Audience Level Intermediate

14:05 JST

MCP-Powered Crash Investigation: How 11 MCP Servers Help an AI Agent Debug Production Issues at Uber - Kriti Dangi, Uber

Thursday September 10, 2026 14:05 - 14:30 JST

Hall 1F

Debugging eats 42% of developer time — $300B lost globally every year. On an average, fixing an issue takes 15 days. Debug Assist does it in 30 minutes — issue alert to validated, reviewable PR.

Most AI debugging tools stop at root cause analysis. Debug Assist goes much further: it writes a fix, validates it in a loop till correct, and creates the PR. Example, It caught a crash at 5% rollout, landed the fix the same day — preventing it from reaching thousands of users. Built on LangGraph with 11 MCP servers, 5 plugins, and parallel subagents: Sourcegraph for code search, crash analytics, Jira, feature flags, Jaeger, and logging — all one protocol.

Debug Assist even works on user-reported bugs which have minimal information attached. A user complained of battery drain, and Debug Assist traced it to a hot-looping code path, producing an RCA from behavioral evidence alone.
Domain knowledge lives in markdown skill files in a plugin marketplace — any developer can contribute fix patterns with no code, no redeployment.

We'll share how we built this from ground up, scaled to 5,000 RCAs/month across 6 languages, the challenges we hit, and how we improved the acceptance rate from 5% to 30%

Speakers

Kriti Dangi

Senior Software Engineer, Uber, Uber

Senior software engineer on the App Quality and Production Observability at Uber. Spent 3 years working on crash analytics platform, before designing and deploying Debug Assist. I love to dance, swim and travel in my free time. You can often find me chatting away with friends!
... Read More →

Thursday September 10, 2026 14:05 - 14:30 JST
Hall 1F

MCPCon

Audience Level Any

14:40 JST

What Happens When Your MCP Tools Cost Money? - Prakash Rao, AIG Technologies & Marco González, Red Hat

Thursday September 10, 2026 14:40 - 15:05 JST

Hall 1F

What happens when an AI agent has to pay for its tools? Today, nobody knows. Open-source MCP servers run for free, and their maintainers quietly absorb the cost. The x402 protocol changes the model: a server can charge a small payment for each tool call, with no accounts or API keys needed. The plumbing works. The open question is how agents behave once tools have a price.

We put it to the test. We ran a paid MCP server for several weeks and watched agents act as customers. We changed prices to find the point where agents stop calling a tool. We offered the same tool free and paid, side by side, to see whether agents compare prices or just call the first match. We let spending budgets run out mid-task to see what agents do when money gets tight. And we compared all of this across four agent clients: Google ADK, LangGraph, the OpenAI Agents SDK, and Claude Code.

The result is practical guidance for maintainers: what to charge, where the payment flow breaks, which framework behaviors to expect, and whether per-call payments can realistically fund an open-source MCP server.

Speakers

Prakash Rao

Principal Cloud Engineer, AIG Technologies

Prakash Rao is a Principal Cloud Engineer at AIG Technologies in Japan, designing Google Cloud infrastructure for financial services: hybrid connectivity, enterprise networking, and security architecture. His recent work includes deploying AI agents on Vertex AI Agent Engine and infrastructure... Read More →

Marco González

Sr. Software Engineer, Red Hat

Senior Software Engineer at Red Hat with 13+ years of global experience in 3G, 4G, and 5G network integration. US patent creator and Telco Automation expert. 2026 AAIF ambassador and active CNCF Program Committee member and speaker at KubeCon, Kubedays, and CNCF events. Contributor... Read More →

Thursday September 10, 2026 14:40 - 15:05 JST
Hall 1F

MCPCon

Audience Level Intermediate

15:35 JST

Lessons From Building a Generative UI Runtime for MCP Apps - Rabi Guha, Thesys Inc

Thursday September 10, 2026 15:35 - 16:00 JST

Hall 1F

MCP UI lets servers return interactive application surfaces instead of plain tool results. But it raises a new question: what happens when the interface inside that surface is generated at runtime by the agent?

This talk shares lessons from building a Generative UI layer within MCP UI. MCP UI provides the app/resource boundary and host communication model, while frameworks like OpenUI provide the generated interface inside that boundary: a component registry, model-friendly UI language, streaming validation, form state, and explicit actions that route back to MCP tools.

The key shift is that MCP UI does not have to mean one fixed widget per tool result. A server can expose capabilities and context, the agent can generate the right interface for the task, and the host can still control rendering, permissions, actions, and observability.

The demo uses a data-dashboard workflow: an agent connects to a datasource, inspects data, generates an interactive dashboard with filters and drilldowns, then turns the result into persistent artifacts such as reports, documents, or slide decks.

Speakers

Rabi Guha

Co-Founder & CEO - Thesys, Thesys Inc

Rabi Shanker Guha is Co-Founder and CEO of Thesys, the Generative UI company behind C1 and OpenUI. Previously, he was Head of Engineering and a founding member at DevRev.ai, where he helped scale the engineering team to about 150 people. He has also held roles at Google and Nutanix, and... Read More →

Thursday September 10, 2026 15:35 - 16:00 JST
Hall 1F

MCPCon

Audience Level Beginner

16:45 JST

Running an MCP Proxy at Scale - Camila Rondinini, Anthropic

Thursday September 10, 2026 16:45 - 17:10 JST

Hall 1F

The MCP spec is clear about how one client and one server talk to each other. It says much less about what happens when the client is itself a distributed system, serving millions of people across thousands of third-party MCP remote servers.

At Anthropic, we run a proxy between our products and a large, growing set of remote servers. At that scale, we started running into problems the spec doesn't answer.

This talk is about three of them:

- Authentication: How do we make authentication work across servers that all implement it a little differently? How do we keep people connected when connections drop and credentials expire, without making them sign in again?

- Caching: How do we avoid hammering the MCP remote servers, and which caching strategies make that possible?

- Monitoring: How do we monitor a system where the servers vary widely, from stable production ones to unstable ones still in development? When something breaks, how do we tell whether the fault is ours or the server's?

Speakers

Camila Rondinini

Member of Technical Staff, Anthropic

Camila Rondinini is a Member of Technical Staff on the Connectivity team at Anthropic, where she works on supporting MCP across Anthropic's product surfaces. Her focus is on improving the reliability and monitoring of MCP at scale.

Thursday September 10, 2026 16:45 - 17:10 JST
Hall 1F

MCPCon

Audience Level Intermediate

17:20 JST

Legacy Meets LLM: Giving Frontier Models a Telephone (PSTN) Over MCP - Shinya Saito, Gen-AX Corp

Thursday September 10, 2026 17:20 - 17:45 JST

Hall 1F

A web service exposes /health; a phone line exposes nothing. The telephone is the oldest telecommunication tool still in production — and our LLM voice agents answer customer calls over it, with no way to know whether they are answering, hearing, and behaving correctly right now.

So we gave a frontier model a telephone.

Our MCP server gives any LLM a phone: dial PSTN numbers, speak via TTS, and read the other side via silence-detected transcripts. A frontier model becomes the caller, phoning our production voice agents in an agent-calls-agent loop — one mechanism covering the whole testing spectrum: ping-style health checks, deep evaluation via scripted and adversarial conversations, and load testing with concurrent caller fleets.

We cover the MCP tool design for a domain the spec wasn't written for — tools that block for tens of seconds, turn-taking over live audio, per-call session state — where the spec fought us and what we would feed back, plus what broke: timeout cascades and evaluations that flap.

We are open-sourcing the server. You'll leave knowing how to connect your own agent to the PSTN — and how to ping, probe, and load-test anything that answers a phone.

Speakers

Shinya Saito

Backend Engineer, Gen-AX Corp

Shinya Saito is a Product Engineer at Gen-AX developing X-Ghost, an enterprise voice AI platform. He builds production voice agents and telephony infrastructure, spanning observability, evaluation, and large-scale testing. Recently he has used the Model Context Protocol (MCP) to connect... Read More →

Thursday September 10, 2026 17:20 - 17:45 JST
Hall 1F

MCPCon

Audience Level Beginner

10:05 JST

Skills as Reusable Operational Knowledge - Nimit Savant, DevRev

Friday September 11, 2026 10:05 - 10:30 JST

Hall 1F

The next leap in agent engineering is not bigger models. It's reusable skills.

Today, many agents repeatedly spend tokens rediscovering the same workflow every time a task appears. Whether it's code reviews, incident analysis, documentation generation, or research tasks, the agent often re-plans work it has already solved before.

This talk explores how agent skills are emerging as reusable workflow primitives that package expertise, decision-making patterns, and execution steps into portable capabilities. Instead of relying on increasingly large prompts, teams can teach agents repeatable workflows once and reuse them across tasks, products, and environments.

Key Takeaways

- Why prompts don't scale for repetitive work
- Skills as reusable workflow contracts
- Reducing token consumption through workflow reuse
- How skills and MCP work together
- Building self-improving agent systems

Speakers

Nimit Savant

Developer Evangelist, DevRev

I love to talk about Agentic AI and B2B Developer Advocacy and strategies

Friday September 11, 2026 10:05 - 10:30 JST
Hall 1F

Protocols & Standards

Audience Level Beginner

10:40 JST

You Have 1000 Employees and None of Them Have a Name - Marcus Tenorio, Bitso

Friday September 11, 2026 10:40 - 11:05 JST

Hall 1F

Your agent swarm is running. It's browsing the web, calling APIs, reading files, making decisions, all on behalf of your users and your organisation. But ask yourself: do you know which agent did what? Can you revoke access to just one of them? Can you prove to an auditor that your agents only touched what they were supposed to?

Probably not. Because most agentic deployments treat agents as anonymous processes : no identity, no credentials, no audit trail, no way to fire them when something goes wrong. If a human employee operated this way, you'd call security. For agents, we call it production.

This talk proposes a fundamentally different approach: onboard your agents like employees. Every agent in your swarm deserves a verifiable identity, scoped permissions, a centralised audit trail, and an offboarding process. Drawing from experience securing cloud native and AI infrastructure, this session presents a blueprint for an open source "Okta for agents"! composing Identity Providers, API gateways, and policy engines to bring the same governance we give humans to the systems acting on their behalf.

You hired 1000 people. It's time to learn their names.

Speakers

Marcus Tenorio

Security Engineering Manager, Bitso

Mart is an Infrastructure Security Manager at Bitso, where he enjoys managing various engineers who teach him every day how to break things and become a better manager and engineer. Mart began his journey in cybersecurity trying to understand why so many people liked prime numbers... Read More →

Friday September 11, 2026 10:40 - 11:05 JST
Hall 1F

Human-Agent Collaboration

Audience Level Intermediate

11:15 JST

The Primitive AI Agents Are Missing: Graph-Based Code Intelligence - John Interlante, Aleutian AI

Friday September 11, 2026 11:15 - 11:40 JST

Hall 1F

Graph-based code intelligence (not GraphRAG) is the infrastructure primitive that AI coding agents need to reason about large codebases without burning tokens. In this session, we'll evaluate various approaches and identify where the field is converging.

Agents fall back to grep because retrieval solutions return a probabilistic approximation of the code at a given point in time. The context goes stale on changes and loses fidelity when going from code to embeddings. By exposing a call graph, based on established compiler theory, to the LLM through a series of functions and tools, the LLM doesn't need to waste tokens because it has access to deterministic, structured, quick access data from which it can get cheap, reliable answers.

Sourcegraph, Meta's Glean, Google's Kythe, GitHub's Stack Graphs, and newer efforts like GitNexus and Aleutian Trace are all building graph based offerings for LLMs. This session provides a deep dive into the problems faced by agents working in large codebases, maps the solution space of graph based coding tools vs more common LLM solutions— RAG, GraphRAG, pure traversal, embeddings — and then shows where each wins or breaks.

Speakers

John Interlante

Managing Director / Founder, Aleutian AI

Founder of Aleutian AI, former Apple Data Engineering Manager, Former McKinsey Data Engineer. Focused on data and AI privacy research for large scale data processing and analysis.

Friday September 11, 2026 11:15 - 11:40 JST
Hall 1F

Building Reliable Agent Systems

Audience Level Intermediate

11:50 JST

The Model and the Mask: An Actor's Method for Engineering Agent Character - Nick Howden-Steenstra, Independent

Friday September 11, 2026 11:50 - 12:15 JST

Hall 1F

Every agent system is two things: the model, which you rent, and the mask - the character - which is yours. The industry keeps upgrading the model and expecting the mask to improve. It doesn't work that way.

I'm a LAMDA-trained actor turned agent engineer. This talk is the actor's toolkit applied to shipped systems. Case one: a comms pipeline in production at a major crypto protocol - the generating model does Stanislavski table-work (super-objective, through-action, lining) before writing a word; a separate director model audits it blind; and voice is scored by a Laban Movement Analysis classifier that grades the human-written corpus and the machine's output on the same instrument. Brand voice becomes a falsifiable measurement. Case two: the home lab - eleven agents built with a Stanislavski character method, orchestrated over MCP, running my actual work.

You'll leave with the model/mask distinction, a character pipeline you can copy, and the failure modes: drift, voice collapse, paint-by-numbers slop.

Speakers

Nick Howden-Steenstra

Agent-Systems Engineer, Independent

Nick Howden-Steenstra trained at LAMDA and spent years building characters on stage; now he builds them as infrastructure. At a major crypto protocol he made brand voice falsifiable - generation gated by Stanislavski table-work, output graded by a Laban Movement Analysis classifier... Read More →

Friday September 11, 2026 11:50 - 12:15 JST
Hall 1F

Human-Agent Collaboration

Audience Level Intermediate

13:30 JST

From Clicks To Context: Building an Open-Source Evaluation Pipeline for AI Agents - Inês Bolaños, PagerDuty

Friday September 11, 2026 13:30 - 13:55 JST

Hall 1F

The AI industry has moved so fast that we are still evaluating probabilistic software using the same deterministic metrics we applied to traditional code. As a Product Analyst working on AI agents at PagerDuty, I saw a critical need for a new observability standard, one that moves beyond clicks to measure true reasoning and reliability. To address this, I’ve developed and open-sourced a specialized framework designed to help teams decide, with data, when to hire, train, or fire an AI agent. In this session, I will walk through the H.I.R.E. Framework methodology and share the technical architecture of an evaluation pipeline that turns qualitative conversational data into structured, actionable product insights. I will share the open-source repository containing these metric definitions and templates, providing resources for the community to move past agent-washing and toward building verifiable, trustworthy agentic systems.

Speakers

Inês Bolaños

Senior Product Analyst, PagerDuty

Inês Bolaños focuses on the intersection of AI, product strategy and data reliability. With almost a decade of experience, she specializes in turning complex data into actionable product decisions. Combining a background in Communication with a Master’s in Big Data, Inês os helping... Read More →

Friday September 11, 2026 13:30 - 13:55 JST
Hall 1F

Evaluation & Testing

Audience Level Intermediate

14:05 JST

What's Missing in the Open Agentic Stack: Lessons From OSS Integration - Tatsuya Sato & Satoshi Ito, Hitachi, Ltd.

Friday September 11, 2026 14:05 - 14:30 JST

Hall 1F

In the agentic AI space, standards like MCP and A2A and a growing OSS ecosystem are evolving. Yet building a real multi-agent system requires more than a single framework or protocol. It involves integrating multiple OSS components and adjacent specifications across areas such as agent-to-agent communication, orchestration, authentication, and observability. There is limited shared understanding of how to combine them and what architectural considerations and integration gaps emerge.

This session shares our work on organizing the landscape of OSS-based agentic AI stacks, and on designing architectures built around MCP, A2A, and representative OSS, including prototyping through reference implementations. We explore several architectural patterns from a whole-system perspective. With enterprise use in mind, our scope also covers cross-cutting concerns such as authentication and observability. (LLMs are currently proprietary.)

Through this work, we examine what each OSS layer solves and does not solve, and highlight cross-layer concerns that emerge only when components are integrated as a multi-agent system. We share these observations with a demo of the reference implementation.

Speakers

Tatsuya Sato

Chief Researcher, Hitachi, Ltd.

Tatsuya Sato is a Chief Researcher at Hitachi, Ltd. His research focuses on agentic AI platforms, blockchain platforms, system operations, and OSS. He has been an active OSS contributor for many years. He has contributed extensively to the LFDT and Hyperledger communities and continues... Read More →

Satoshi Ito

Researcher, Hitachi, Ltd.

The speaker is a researcher and engineer at Hitachi, engaged in open-source software development. Initially focused on blockchain technologies, they have worked on Self-Sovereign Identity (SSI), Decentralized Identifiers (DID), and NFTs. In recent years, their research has shifted... Read More →

Friday September 11, 2026 14:05 - 14:30 JST
Hall 1F

Open Infrastructure and Tooling

Audience Level Intermediate

14:40 JST

The Conductor Pattern: Multi-Granularity Feedback for Creative Agents - Yusuke Shibui, MLOps/LLMOps/AgentOps Community

Friday September 11, 2026 14:40 - 15:05 JST

Hall 1F

Most "human-in-the-loop" agent systems assume the human can specify success up front: a passing test, green CI, a structured eval. What if the human's taste is the spec?

This talk presents YouAndOrchestra (YaO), an open-source agentic music composition system on Claude Code. YaO orchestrates seven role-based subagents — Producer, Composer, Harmony Theorist, Rhythm Architect, Orchestrator, Mix Engineer, Adversarial Critic — turning natural language into a score evaluated across six dimensions, every note carrying provenance.

https://github.com/shibuiwilliam/YouAndOrchestra

Three collaboration patterns from iteration:
1. Three-tier feedback. Users rewrite the YAML spec, regenerate a section, or pin feedback to a bar, beat, and instrument. Choosing the level is itself a UX problem.
2. Conductor loop with a critic gate. Generate, evaluate, adapt, regenerate runs up to three iterations, with critics gating before notes are placed.
3. Provenance as trust substrate. /explain queries an append-only causal graph — "why did the chorus modulate to the relative minor?"

Attendees leave with patterns and open-source code for agent systems where the human stays in the seat of judgment.

Speakers

Yusuke Shibui

Community owner, MLOps/LLMOps/AgentOps Community

Yusuke Shibui works across MLOps, data, infrastructure, backend, research engineering, and tech sales — and lives with two cats. His current focus is putting generative AI and AI agents into production. He is the author of "Machine Learning System Design Patterns" and "A Practical... Read More →

Friday September 11, 2026 14:40 - 15:05 JST
Hall 1F

Human-Agent Collaboration

Audience Level Intermediate

15:35 JST

Built for Two: What Design Systems Are Missing When AI Agents Become the Third User - Karen Ng, Endor Labs

Friday September 11, 2026 15:35 - 16:00 JST

Hall 1F

AI coding agents now generate UI from component libraries. Most teams write component markdown files and expect agents to take it from there. The docs were complete. Agents still got it wrong.

Sitting with engineers in code review, the same things kept surfacing: the agent picked a visually similar but wrong component; it invented props; it read "Tag" as a UI primitive when the codebase meant a security concept. One author. No review process. A library too large for any agent to navigate without a map.

Not a component library talk. A talk about what the workflow was missing when the docs were already done.

I'll walk through the workflow that came out of those sessions: why a component file needs more than one author before agents can trust it; how an index changes what agents can find; and the naming decision that was invisible to humans and catastrophic for agents. Including the moment the team realized the problem wasn't the docs.

You'll leave with one reframe: a component library has always had two users. It now has a third. Here is what the workflow looks like when you build for all three.

Speakers

Karen Ng

Principal Product Designer, Endor Labs

Karen Ng designs AI-driven products for security engineers and oncologists. She leads UX at Endor Labs, where she has built AI agent governance, code scanning, and security workflow products from scratch. A three-time internal hackathon winner, she prototypes in code as readily as... Read More →

Friday September 11, 2026 15:35 - 16:00 JST
Hall 1F

Human-Agent Collaboration

Audience Level Intermediate

16:10 JST

Build Your Own Open-Source Claude Code With Local LLMs - Daniel Oh, Red Hat

Friday September 11, 2026 16:10 - 16:35 JST

Hall 1F

AI coding assistants are becoming part of everyday development, but many enterprises cannot send source code, internal APIs, or project context to external services. They need the productivity of coding agents while keeping models, repositories, prompts, and actions under their control.

In this session, we’ll show how to build an open-source, Claude Code-like assistant using local or privately hosted LLMs, Models as a Service, OpenCode, and AI guardrails. Developers will be able to explore a codebase, generate changes, review explanations, and trigger controlled actions without exposing sensitive data.

We’ll also cover the guardrails needed for real use: secrets protection, data leakage checks, unsafe command blocking, insecure code detection, and policy-based action control.

You’ll leave with a practical blueprint for building a private, secure coding assistant that improves developer productivity without compromising trust, privacy, or compliance.

Speakers

Daniel Oh

Senior Principal Developer Advocate, Red Hat

Java Champion, CNCF Ambassador & TAG DevEX Co-Chair, AAIF Ambassador, Microsoft MVP, Developer Advocate, Technical Marketing, Keynote Speaker, Published Author

Friday September 11, 2026 16:10 - 16:35 JST
Hall 1F

Open Infrastructure and Tooling

Audience Level Beginner

16:45 JST

Externalizing Agent State: Memory and Filesystem Management for Sandboxed Coding Agents - Tadatoshi Sekiguchi, PingCAP

Friday September 11, 2026 16:45 - 17:10 JST

Hall 1F

Coding-agent harnesses such as Claude Code, Codex, and OpenCode are widely used as general-purpose agent platforms, customized with Skills and Tools and run inside sandboxes. But these agents are stateless by design: when a session ends or a sandbox is torn down, context and artifacts disappear. Running them in production for many users over months turns memory and artifact management into hard problems.

This session shares how we run multiple harness-based agents in sandboxes, and introduces two open-source tools we built to externalize agent state. mem9 (github.com/mem9-ai/mem9) records sessions through harness hooks and, at the next session, runs hybrid retrieval over past sessions from the user's instruction, injecting only relevant history—persisting sessions while compressing context and cutting token usage. drive9 (github.com/mem9-ai/drive9) is a cloud filesystem FUSE-mounted into each sandbox, persisting artifacts beyond sandbox lifetimes, auto-attaching metadata, and enabling semantic search over outputs.

Attendees will leave with a vendor-neutral, open-source architecture for agent memory and storage that works across any harness, plus lessons from real operation.

Speakers

Tadatoshi "Seki" Sekiguchi

Technology Evangelist, PingCAP

Tadatoshi "Seki" Sekiguchi is a Technology Evangelist at PingCAP Japan, promoting PingCAP's AI technologies through public talks and hands-on workshops, and driving TiDB/NewSQL adoption since 2022. He has 20+ years in financial-services systems as an architect, DBA, and PM, with senior... Read More →

Friday September 11, 2026 16:45 - 17:10 JST
Hall 1F

Open Infrastructure and Tooling

Audience Level Beginner

10:05 JST

10:40 JST

11:15 JST

13:30 JST

14:05 JST

14:40 JST

15:35 JST

16:45 JST

17:20 JST

10:05 JST

10:40 JST

11:15 JST

11:50 JST

13:30 JST

14:05 JST

14:40 JST

15:35 JST

16:10 JST

16:45 JST

Get help with the event