-
10:20 • Skills as Reusable Operational Knowledge - Nimit Savant, DevRev
-
10:55 • You Have 1000 Employees and None of Them Have a Name - Marcus Tenorio, Bitso
-
11:30 • MCP-Powered Crash Investigation: How 11 MCP Servers Help an AI Agent Debug Production Issues at Uber - Kriti Dangi, Uber
-
12:05 • The Model and the Mask: An Actor's Method for Engineering Agent Character - Nick Howden-Steenstra, Independent
-
13:40 • From Clicks To Context: Building an Open-Source Evaluation Pipeline for AI Agents - Inês Bolaños, PagerDuty
-
14:15 • What's Missing in the Open Agentic Stack: Lessons From OSS Integration - Tatsuya Sato & Satoshi Ito, Hitachi, Ltd.
-
14:50 • The Conductor Pattern: Multi-Granularity Feedback for Creative Agents - Yusuke Shibui, MLOps/LLMOps/AgentOps Community
-
15:35 • Built for Two: What Design Systems Are Missing When AI Agents Become the Third User - Karen Ng, Endor Labs
-
16:10 • Build Your Own Open-Source Claude Code With Local LLMs - Daniel Oh, Red Hat
-
16:45 • Externalizing Agent State: Memory and Filesystem Management for Sandboxed Coding Agents - Tadatoshi Sekiguchi, PingCAP
-
17:20 • From Logs to Proofs: Cryptographic Compliance for Agentic Payments - Aggre Hiroyuki, Lemma Oracle
-
09:00 • Keynote: Welcome - Mazin Gilbert, Executive Director, The Agentic AI Foundation
-
09:10 • Sponsored Keynote: From Consumers to Contributors: Why Japan Must Join the Agentic AI Upstream - Yoshiyuki Tabata, Chief OSS Consultant, Hitachi
-
09:25 • Sponsored Keynote: Beyond the Model: Control and Execution for Enterprise AI - Allan Teng, Founder & Senior Advisor, APAC & Japan | General Manager & Vice President, Workato Japan, Workato
-
09:40 • Keynote: Skills Over MCP: From Experiment to Extension - Ola Hungerford, Principal Engineer, Nordstrom
-
10:20 • Building Local Regression Testing and Evals for ADK Agents - Thu Ya Kyaw, Google
-
10:55 • Architecture Behind the Most Viral Agent Memory Open Source Project - Rohit Ghumare, DEVREL AS SERVICE & Vinuja Khatode
-
11:30 • The 3 AM Page: Turning Chaos Into Context With Bounded AI and Structured Evidence - Madhu Patel & Sudhanshu Sah, Adobe
-
12:05 • Your Agent Starts the Checkout. Then What? - Muskan Jain, Independent
-
13:40 • Stateful Sandboxes for Stateless Agents: Designing Durable Volumes for MCP Tool Workspaces - Rui Su, Juicedata
-
14:15 • What's Actually Running in Your Coding Agent: The Shadow AI Stack - Alexander Frazer, Runlayer
-
14:50 • Building an Agentic Software Factory - Valentin De Matos, Delphi
-
15:35 • Governed Agent Autonomy: Building a Control Plane for Agentic Systems - Nnenna Ndukwe, Qodo AI
-
16:10 • Beyond Prototypes: Building Enterprise-scale Agentic Systems - Kevin Dubois, IBM & Mauricio "Salaboy" Salatino, Dash0
-
16:45 • MCP × A2A Platform for the Enterprise: Security by Spec - Masaki Tsukada, Mitsubishi Electric Corporation
-
17:20 • Your Agent Inherits Code, Not Decisions: How To Use Context Graphs for Intent - Nyah Macklin, Neo4j
