• Engineering Multiagent Systems — Munindar Singh (10-22 11:10, LL21A) Formal interaction protocols with correctness guarantees; commitments/social meaning first-class (Singh, commitment-protocol lineage). Project: shcv/bspl — BSPL commitment-protocol toolkit (Python, MIT, active). Singh has no personal repo; tooling ships under collaborators.
• Don't Share the Database: Interface Contracts Between Isolated AI Agents — Martin Bliss (10-22 14:55, LL21A) Parnas '72 information hiding: published facades over hidden internals, producer/consumer handshake, refuses to fail silently. Refutation: Could be architecture-astronaut with no enforcement; demand the mechanism that makes silent retrieval failure impossible. Project: no public repo — reads as a concept/architecture talk (speaker identity inferred, not confirmed).
• Trustworthy Context Is Untrusted By Default — Shub Argha (10-22 15:30, 210B) Provenance footers, commit-at-write staleness anchors, write-risk classification, quantified (88.8%->33.3%) with named unmitigated attack classes. Project: speaker is at Arcade.dev (shubcodes); no dedicated repo for these mechanisms (closest: arcade-mcp, an MCP tool framework). Benchmark unpublished.
• Who, May, Did: Composing Agent Identity with Verifiable Proof of What Agents Actually Do — Steven Mih (10-22 16:40, 230C) may/did distinction (approved != executed != confirmed); tamper-evident action records referencing identity/consent by digest, anchored on SCITT/COSE. Project: action-state-group — agent-action-capsule (BSD-3), capsule-emit + scitt-cose (Apache-2.0), implementing his IETF SCITT draft-mih-* drafts. Mih: ex-Alluxio/Ahana/Aviatrix.
• Sponsored Keynote: Coding Agents need Deterministic Correctness — Shadaj Laddad (10-23 10:05, Grand Ballroom; retitled on the 2026-10-13 schedule as "Keynote: Abstractions are Dead, Long Live Abstractions") Deterministic simulation + universal properties via Rust types. Invariants-by-construction for agent-authored distributed systems (Hydro). Refutation: 5-min keynote slot: pointer to the work, not the payload. Project: Hydro — correctness-by-construction distributed systems (Apache-2.0, Rust, ~1.3k stars); the old Hydroflow, now DFIR + hydro_lang. AWS-backed (shadaj.me).
• Your Agent Sandbox Is Built Backwards — Dan Fernandez, Ariadne Conill (10-23 14:55, 230C) Object-capability security for agents: zero authority + injected scoped capabilities; lifecycle IS the audit trail. Refutation: If attenuation is enforced only at grant, not at delegation, it's ambient authority with extra steps. Project: Styrolite + Styrojail — namespace sandboxing for untrusted agents (Edera, Apache-2.0, Rust, active). Conill = Alpine/Wolfi (kaniini).

• Should This Be an AI Agent? A Product Framework for Enterprise Adoption — Takeshwari Kamal (10-22 11:45, LL20C) Explicit blast-radius model: permissions, escalation paths, reversibility, failure tolerance. Refutation: PM-framed; lighter on mechanism.
• Generation-Verification Asymmetry: The Production Failure Pattern Nobody Has Named Yet — Birajendu Sahu (10-22 16:40, LL20A) Names generation/verification cost asymmetry as compounding liability. Refutation: Vendor-demo framing; discount accordingly.
• Bridging Agentic Reasoning and Deterministic Execution — Marcio Klepacz (10-22 10:35, 230A) Agent-authored deterministic, replayable DAGs; reason where flexible, execute where reliable.
• Configured for Autonomy: Making Enterprise Agents Useful and Safe at Scale — Viyat Bhalodia, Casey Silver (10-22 11:10, 230A) Capability profiles + sandbox + LLM-judge escalation + replay of policy against past workflows.
• When Agents Spawn Agents: Securing Recursive Delegation in Multi-Agent Systems — Anishma Mavuram (10-23 12:05, LL20C) Recursive delegation, monotonic least-privilege attenuation, confused-deputy. Composes with the capability model. Refutation: Stacks ~8 RFCs; standards-soup risk.
• The Agentic Orchestration Stack: Durability, Guardrails, and Attestation — Yaron Schneider (10-23 14:55, LL20C) Durable execution + cryptographic attestation + provenance (Dapr lineage).
• Agent Governance Lives in the OS — Alexander Sklar, Roberth Karman (10-23 15:30, LL20C) 'Governance is the goal, OS enforcement is the mechanism.' Composes bubblewrap/seatbelt/AppContainer; honest about non-composition.
• Prove What Your Agent Did: Tamper-Evident Audit Trails for Tool Calls — Vikas Luthra (10-23 16:05, LL20A) Merkle-root/hash-chain tamper-evident audit trails, O(log n) single-action verification.
• Stop Writing Agents, Declare Them: Declarative Agent Architecture in Production — Chris Knuteson (10-23 16:05, 210B) AgentSpec-as-contract, narrow waist, governance/resilience/future-proofing by construction.

The real decision is slot contention. Notable overlaps among the curated picks on the 2026-10-13 schedule:

• Day 1 11:10 — Engineering Multiagent Systems (Singh, Tier 1) vs Configured for Autonomy (Bhalodia/Silver, Tier 2).
• Day 1 16:40 — Who, May, Did (Mih, Tier 1) vs Generation-Verification Asymmetry (Sahu, Tier 2).
• Day 2 14:55 — Your Agent Sandbox Is Built Backwards (Fernandez/Conill, Tier 1) vs The Agentic Orchestration Stack (Schneider, Tier 2).
• Day 2 16:05 — Prove What Your Agent Did (Luthra) vs Stop Writing Agents, Declare Them (Knuteson).

The August schedule's Day 1 17:30 three-way collision (Mih, Klepacz, and the Break the Lethal Trifecta workshop) is gone: Klepacz moved to 10:35, and the workshop moved to Day 2 10:55 (230A).

• 10:00 — Arm Create with Google, Google DeepMind, Nota, and Renesas [The Tech Interactive / Special event]

• 08:00 — Registration & Badge Pick-Up [The Hub (Street Level)]
• 18:00 — AI Community Bash featuring DE LA SOUL [Concert Venue (Concourse Level)]

• 07:30 — Registration & Badge Pick-Up [The Hub]
• 07:30 — Zen Zone [The Vision Room]
• 09:00 — Welcome to AGNTCon + MCPCon North America — Angie Jones [Grand Ballroom / Keynote]
• 09:05 — Opening Remarks — Mazin Gilbert [Grand Ballroom / Keynote]
• 09:15 — Keynote: Manik Surtani, CTO, Agentic AI Foundation — Manik Surtani [Grand Ballroom / Keynote]
• 09:25 — Keynote: Tokenomics: Energy to Intelligence to Value — J.R. Storment [Grand Ballroom / Keynote]
• 09:30 — Keynote: David Soria Parra, Co-creator of MCP, Anthropic — David Soria Parra [Grand Ballroom / Keynote]
• 09:45 — Keynote: Building the Human-Agent Workplace — Bradley Axen [Grand Ballroom / Keynote]
• 09:55 — Keynote: MCP in the Wild — Thomas Sarlandie [Grand Ballroom / Keynote]
• 10:10 — Coffee Break; Solutions Showcase opens [Solutions Showcase]
• 10:13 — Demo Theater: Akamai AI Orchestrator — Duan Lightfoot [Solutions Showcase / Demo Theater / Sponsored Session]
• 10:25 — Demo Theater: DO NOT Give AI Agents Credentials! — Christian Posta [Solutions Showcase / Demo Theater / Sponsored Session]
• 10:35 — Workshop: Hands-on A2A: Service Discovery and Multi-Agent Delegation — Sergio Villani, Pedro Melendez, Sirisha Karra, Lavi Nigam [LL21D / Workshop]
• 10:35 — Stop Vibe-Testing: Run Real Agent Evals — Laurie Voss [210C / Evals & Testing / Breakout]
• 10:35 — Evolution, not Revolution: How MCP is Reshaping OAuth — Aaron Parecki [LL20A / MCPCon / Breakout]
• 10:35 — Gotta Catch 'Em All: Agent Skills — Lizzie Siegle [LL20C / Agentic Engineering / Breakout]
• 10:35 — Don't Merge That: An Agentic Approach to Catching Outages at 10,000 PRs a Week — Joris Bonnefoy [LL21A / Building Reliable Agent Systems / Breakout]
• 10:35 — Scaling AI Infrastructure Systems at Meta Scale — Neelakshi Soni [210B / Agentic Engineering / Breakout]
• 10:35 — Bridging Agentic Reasoning and Deterministic Execution — Marcio Klepacz [230A / Agentic Engineering / Breakout]
• 10:35 — From Agent to Infrastructure: The Goose Development Kit — Steve Lee [230C / Open Source Tools / Breakout]
• 10:55 — Demo Theater: Device Connect in Action: Bringing AI Agents to Real-World Devices [Solutions Showcase / Demo Theater / Sponsored Session]
• 11:10 — Generative UI at Scale with A2UI — Alan Blount, Vishal Motwani [210C / Human-Agent Collaboration / Breakout]
• 11:10 — From DCR to CIMD: MCP Client Identity in Production — Alvaro Inckot [LL20A / MCPCon / Breakout]
• 11:10 — Building Agents with Decision Models — Sydney Runkle [LL20C / Agentic Engineering / Breakout]
• 11:10 — Engineering Multiagent Systems — Munindar Singh [LL21A / Multi-Agent & Distributed Systems / Breakout]
• 11:10 — A2A v1 Deep Dive: The Specification, Extensions, and Custom Protocol Bindings — Luca Muscariello, Darrel Miller [210B / Interoperability & Standards / Breakout]
• 11:10 — Securing the Agentic Universe, One Layer at a Time — Aidan Sochowski [210A / Building Reliable Agent Systems / Breakout]
• 11:10 — Demo Theater: Don't Let the Agent Freelance Your API Calls — Tyler Lamparter [Solutions Showcase / Demo Theater / Sponsored Session]
• 11:10 — Configured for Autonomy: Making Enterprise Agents Useful and Safe at Scale — Viyat Bhalodia, Casey Silver [230A / Enterprise Adoption in Practice / Breakout]
• 11:10 — Rethinking CI/CD Release Gates for Agent-native Software — Prathmesh Patel [230C / Evals & Testing / Breakout]
• 11:22 — Demo Theater: AI Gateway: Route, Govern, and Learn From Every Agent Interaction — Jerod Johnson [Solutions Showcase / Demo Theater / Sponsored Session]
• 11:45 — Auth.md - The Open Protocol for Agentic Registration — Michael Grinich [210C / Interoperability & Standards / Breakout]
• 11:45 — What Your MCP Server Does When Nobody's Looking — Austin Parker [LL20A / MCPCon / Breakout]
• 11:45 — Should This Be an AI Agent? A Product Framework for Enterprise Adoption — Takeshwari Kamal [LL20C / Enterprise Adoption in Practice / Breakout]
• 11:45 — The Sleeper Awakes: Intelligent Hibernation and Wake-Up Strategies for Agent Sandboxes — Zhang Zhen [LL21A / Building Reliable Agent Systems / Breakout]
• 11:45 — There's No Dark Factory Without Better Software Verifiers — Dexter Horthy [210B / Agentic Engineering / Breakout]
• 11:45 — LLMs Are a Commodity. Choice and Control Aren't — Matt Meeboer [210A / Enterprise Adoption in Practice / Sponsored Session]
• 11:45 — The Restraint Pattern: A Reliability Model for Agents That Act in Public — Bharat Patel [230A / Building Reliable Agent Systems / Breakout]
• 11:45 — How Agents Really See the Web — Liad Yosef [230C / Human-Agent Collaboration / Breakout]
• 11:46 — Demo Theater: Smartsheet AI: Building the Future of Work Management, Live! — Brian Gann [Solutions Showcase / Demo Theater / Sponsored Session]
• 11:58 — Demo Theater: Agent Sprawl: Turn One-Off AI Experiments Into Workforce-Wide Results — Vince Berry [Solutions Showcase / Demo Theater / Sponsored Session]
• 12:10 — Attendee Lunch; Prompt à la Carte; Women + Non-Binary Community Gathering [Solutions Showcase]
• 12:15 — Demo Theater: Scale Agents with AX and Substrate — Ivan Nardini [Solutions Showcase / Demo Theater / Sponsored Session]
• 12:27 — Demo Theater: Looping to Optimized Models on Custom Silicon — Mike Chambers [Solutions Showcase / Demo Theater / Sponsored Session]
• 12:39 — Demo Theater: Tokenomics in Ten Minutes: An Open Map of the AI Landscape — Stephen Arthur [Solutions Showcase / Demo Theater / Sponsored Session]
• 13:03 — Demo Theater: Trust, But Verify: Human-in-the-Loop for Agents That Actually Matter — Michael Liendo [Solutions Showcase / Demo Theater / Sponsored Session]
• 13:25 — Keynote: Welcome Back [Grand Ballroom / Keynote]
• 13:30 — Keynote: Dawn Song - UC Berkeley — Dawn Song [Grand Ballroom / Keynote]
• 13:40 — Keynote: The Anything Trap: What to Build When Agents Can Build Everything — Lena Hall [Grand Ballroom / Keynote]
• 13:50 — Keynote: Agents as Actors: Harnessing the Power of Agentic Infrastructure — Idit Levine, Keith Babo [Grand Ballroom / Keynote]
• 13:55 — Keynote: From Black Box to Glass Box: Your 5-step Blueprint to Trustworthy Agents — Abhishek Choudhary [Grand Ballroom / Keynote]
• 14:00 — Keynote: The Agentic Web - Sarah Drasner, Distinguished Engineer, Google — Sarah Drasner [Grand Ballroom / Keynote]
• 14:20 — Workshop: The Buzz-Word Is Collaboration — Morgan Martin, Wes Billman, Taylor Ho, Bradley Axen, Will Pfleger, Tyler Longwell [LL21D / Human-Agent Collaboration / Workshop]
• 14:20 — Programmable LLM Inference for Open Agent Infrastructure — Lin Zhong [210C / Open Source Tools / Breakout]
• 14:20 — MCP Security, Two Years In — Den Delimarsky [LL20A / MCPCon / Breakout]
• 14:20 — Leveraging A2A Protocol to Build Framework Agnostic Multi-Agent System — Sohil Shah [LL20C / Interoperability & Standards / Breakout]
• 14:20 — Why Domain-specific Agents Are the Future — Justin Schroeder [LL21A / Interoperability & Standards / Breakout]
• 14:20 — Skills Assemble: How Superpowered AI Teams Replace Prompt Chaos — Eddie Wassef [210B / Enterprise Adoption in Practice / Breakout]
• 14:20 — Beyond MCP: Building an Enterprise Knowledge Layer for Production AI Agents — Jeremy Adams - Casañas [210A / Enterprise Adoption in Practice / Sponsored Session]
• 14:20 — Demo Theater: Building an MCP Server in 7 Minutes — Matt Meeboer [Solutions Showcase / Demo Theater / Sponsored Session]
• 14:20 — Beyond Pass/Fail: Measuring the Full Agent Experience — Sean Roberts [230A / Evals & Testing / Breakout]
• 14:20 — Before the Agent Writes Code: Policy-Aware Engines for AI Coding — Nnenna Ndukwe [230C / Building Reliable Agent Systems / Breakout]
• 14:35 — Demo Theater: Beyond Models: Open Source Drives the AI Ecosystem — Wesley Chun [Solutions Showcase / Demo Theater / Sponsored Session]
• 14:55 — Between Intent and Execution — Hemanth hm [210C / Agentic Engineering / Breakout]
• 14:55 — Agentic Messaging Primitives in MCP — Caitie McCaffrey [LL20A / MCPCon / Breakout]
• 14:55 — Building Production-Ready Agents with a Regression Test Suite — Yuki Watanabe [LL20C / Evals & Testing / Breakout]
• 14:55 — Don't Share the Database: Interface Contracts Between Isolated AI Agents — Martin Bliss [LL21A / Multi-Agent & Distributed Systems / Breakout]
• 14:55 — Where Did All My Tokens Go? Using Agentgateway to Keep Your AI Usage Under Control — Shane O'Donnell [210B / Enterprise Adoption in Practice / Breakout]
• 14:55 — The Control Plane Your MCP Gateway Forgot — Alex Salazar [210A / MCPCon / Sponsored Session]
• 14:55 — Demo Theater: Mission-Critical AI in Extreme Environments: An Open-Source Stack for On-Prem — Georgy Okrokvertskhov [Solutions Showcase / Demo Theater / Sponsored Session]
• 14:55 — Governing MCP at Scale: Enforcing Agentic Architecture from Code Generation to Merge — Marc Daniel Registre [230A / MCPCon / Breakout]
• 14:55 — The Autonomous Pipeline: Using Agentic AI to Automate FCRA Compliance from API Spec to Production — Gokul Prabagaren [230C / Enterprise Adoption in Practice / Breakout]
• 15:10 — Demo Theater: From AI Answers to Trusted Expertise: Grounding Enterprise AI in Expert Knowledge — Ro Recio [Solutions Showcase / Demo Theater / Sponsored Session]
• 15:30 — There Is No Loading State: Real-Time Tool Calling for Voice Agents — Amanda Martin [210C / Human-Agent Collaboration / Breakout]
• 15:30 — No New Authority: Publishing and Finding MCP Agents in DNS — Igor Racic, Ingmar Van Glabbeek [LL20A / MCPCon / Breakout]
• 15:30 — Counting Tokens Before They Hatch: Predicting Agent Costs Before Execution — Kirah Sapong [LL20C / Agentic Engineering / Breakout]
• 15:30 — Multi-Agent SRE: What Happens When Your Agents Want Opposite Things — Prakshal Doshi, Aditi Mewada [LL21A / Multi-Agent & Distributed Systems / Breakout]
• 15:30 — Trustworthy Context Is Untrusted By Default — Shub Argha [210B / Building Reliable Agent Systems / Breakout]
• 15:30 — Why API Modernization is the Prerequisite to AI Governance — Amit Shah [210A / Enterprise Adoption in Practice / Sponsored Session]
• 15:30 — Demo Theater: Which Agent Spent That? — Amit Kinha [Solutions Showcase / Demo Theater / Sponsored Session]
• 15:30 — MCP Rug Pulls in the Wild: Live Attacks and How to Stop Them — Advait Patel, Charit Upadhyay [230A / MCPCon / Breakout]
• 15:30 — AI Collaboration Maturity: A Framework Beyond Engineering — Dakota Fabro [230C / Human-Agent Collaboration / Breakout]
• 15:45 — Demo Theater: Unlocking Agents in Production: Enterprise Governance & Cost Control for MCPs & LLMs — Ashwini Vasanth, Laura Jordana [Solutions Showcase / Demo Theater / Sponsored Session]
• 16:00 — Demo Theater: Token by Token: Your AI Agent Has a Metering Problem — Shai Betito [Solutions Showcase / Demo Theater / Sponsored Session]
• 16:05 — Workshop: Keep Infrastructure Out of Your AI Agents and MCP Servers — Lin Sun, Christian Posta [LL21D / Open Source Tools / Workshop]
• 16:05 — Part Man. Part Machine. All Open Source — Russell Spitzer [210C / Open Source Community & Ecosystem Health / Breakout]
• 16:05 — The Other Half of MCP Apps: Building a Secure, Self-Hostable Host for Interactive Agent UIs — Mathew Goldsborough [LL20A / MCPCon / Breakout]
• 16:05 — How Open Standards Become Real: Lessons from Agent Plugins — Jonathan Hefner [LL20C / Interoperability & Standards / Breakout]
• 16:05 — Cut The Noise: Building a Code Reviewer You Can Trust — Joah Gerstenberg [LL21A / Agentic Engineering / Breakout]
• 16:05 — Stop Running Agents as Service Accounts: User-Scoped Access for Enterprise Tool Calls — Masato Kozuka [210B / Enterprise Adoption in Practice / Breakout]
• 16:05 — 5 Ways to Build a Durable Browser Agent in 2026 — Andrew Baker [210A / Building Reliable Agent Systems / Sponsored Session]
• 16:05 — Shipping an MCP Server Nobody Told You How To: PyPI, the Registry, and the Rough Edges — Mesut Oezdil [230A / MCPCon / Breakout]
• 16:05 — Let's Play the Agentic AI Supply Chain Game! — Sarah Evans, Christopher Robinson [230C / Enterprise Adoption in Practice / Breakout]
• 16:15 — Demo Theater: Ready or Not, Here Come the Agents: Is the Web Ready for Its New Users? — Ido Finder [Solutions Showcase / Demo Theater / Sponsored Session]
• 16:30 — Demo Theater: Governing Agents When You Can't Trust the Model — Shub Argha [Solutions Showcase / Demo Theater / Sponsored Session]
• 16:40 — From Pilot to Production: Lessons from Operating Multi-Agent Systems at Scale — Rupal Shirpurkar [210C / Multi-Agent & Distributed Systems / Breakout]
• 16:40 — Generation-Verification Asymmetry: The Production Failure Pattern Nobody Has Named Yet — Birajendu Sahu [LL20A / MCPCon / Breakout]
• 16:40 — Universal Commerce Protocol — Ilya Grigorik, Amit Handa, Greg Smith [LL20C / Agentic Commerce / Panel]
• 16:40 — How AT&T Is Building an Agentic Front Door for Enterprise HR — Natalie Gilbert, Sherman Bell, Emily Williams, Prateek Baranwal, Hector Tejada [LL21A / Enterprise Adoption in Practice / Panel]
• 16:40 — The Frontend Strikes Back: WebMCP and The Agent-Ready Browser — Ryan Roemer [210B / Interoperability & Standards / Breakout]
• 16:40 — Agent Autonomy vs. Capability vs. Security: How to Pick All 3 — Kim Maida [210A / Interoperability & Standards / Sponsored Session]
• 16:40 — Beyond Static DAGs: Orchestrating AI-Generated Multi-Agent Workflows — Cong Wang [230A / Multi-Agent & Distributed Systems / Breakout]
• 16:40 — Who, May, Did: Composing Agent Identity with Verifiable Proof of What Agents Actually Do — Steven Mih [230C / Multi-Agent & Distributed Systems / Breakout]
• 16:45 — Demo Theater: 5 Developers. 45 AI Agents. One workspace. — Phil Conway [Solutions Showcase / Demo Theater]
• 17:15 — Anatomy of a Claude Code Plugin, and Lessons Learned on Creating One — Charlie Lin [210C / Open Source Tools / Breakout]
• 17:15 — One MCP Server, Many Agents: The Identity Gap OAuth Doesn't Close — Mohit Gurnani [LL20A / MCPCon / Breakout]
• 17:15 — AGENTS.md is the New CONTRIBUTING.md: A Field Report from One Year of Agent-Friendly Monorepos — Unnati Mishra [LL20C / Interoperability & Standards / Breakout]
• 17:15 — Connecting the Dots with Context Graphs — Stephen Chin [LL21A / Building Reliable Agent Systems / Breakout]
• 17:15 — Gating High-Risk Agentic Actions at the Relying Party with Exogenous (Out-of-Band) Inputs — Dominic Forrest [210B / Human-Agent Collaboration / Breakout]
• 17:15 — What Production Knows: Closing the Loop Between AI Agents and the Systems They Build — May Walter [210A / Agentic Engineering / Breakout]
• 17:15 — Hand the Agent the Clicker — Giovanni Laquidara [230A / Agentic Engineering / Breakout]
• 17:15 — Harness Engineering: From MAST's Failure Taxonomy to MCP-Native Multi-Agent Production — Jay Mehta [230C / Agentic Engineering / Breakout]
• 17:45 — Attendee Reception [Solutions Showcase]
• 17:45 — Poster: From Data to Meaning: How Microsoft Fabric IQ Grounds Enterprise AI — Girish Dasarathy [Enterprise Adoption in Practice / Poster]
• 17:45 — Poster: A Zero-Trust Identity Model for Production Agents — Jayanth Rajashekariah [Enterprise Adoption in Practice / Poster]
• 17:45 — Poster: Agentic Chartering: a Zero Trust Architecture for Autonomous Execution — Adam Terlson [Multi-Agent & Distributed Systems / Poster]
• 17:45 — Poster: Beyond the Diff: Giving Agents the Why Behind a Commit — Elijah Pettit [Human-Agent Collaboration / Poster]
• 17:45 — Poster: Reliability for Agent Memory: Provenance, Forgetting, and Trust Audits — Ratnopam Chakrabarti, Mahalingam Sivaprakasam [Building Reliable Agent Systems / Poster]
• 17:45 — Poster: Session-Aware Routing for Local Agentic Workflows: Mixture-of-Mode on Intel Workstation GPU — Kushal Mittal [Agentic Engineering / Poster]
• 17:45 — Poster: ShieldMCP: A Drop-In Runtime Defense for MCP Agent Deployments — Saurabh Yergattikar [MCPCon / Poster]
• 17:45 — Poster: Testing the MCP Matrix: Metrics and Strategies for Multi-Client Evaluation — Marcelo Jimenez Rocabado [Evals & Testing / Poster]
• 17:45 — Poster: The Accidental API: How Accessibility Became Agent Experience — John Hill [Open Source Tools / Poster]
• 17:45 — Poster: When Agents Leave the Model: Reliability Lessons from Tool-Calling Inference Systems — Jigar Kuverji Savla [Building Reliable Agent Systems / Poster]
• 17:45 — Poster: Which Instrumentation Decisions Determine What Your Agents Actually Cost? — John D'Emic [Building Reliable Agent Systems / Poster]

• 08:00 — Registration & Badge Pick-Up [The Hub]
• 08:00 — Zen Zone [The Vision Room]
• 09:00 — Welcome Back & Awards — Mazin Gilbert [Grand Ballroom / Keynote]
• 09:20 — Keynote: Mark Collier, Executive Director, PyTorch Foundation — Mark Collier [Grand Ballroom / Keynote]
• 09:30 — Keynote: Sutando: My AI Stand — Chi Wang [Grand Ballroom / Keynote]
• 09:40 — Keynote: From My Dog's Cancer to a Personalised mRNA Vaccine: Building Across Disciplines with AI — Paul Conyngham [Grand Ballroom / Keynote]
• 09:50 — Keynote: Building the Git Forge of the Future — Thomas Dohmke [Grand Ballroom / Keynote]
• 10:05 — Keynote: Abstractions are Dead, Long Live Abstractions — Shadaj Laddad [Grand Ballroom / Keynote]
• 10:10 — Keynote: Shipping Autonomous Agents Safely with Open Standards, Observability, and Control — Rao Surapaneni [Grand Ballroom / Keynote]
• 10:20 — Keynote: How Anthropic is Building with MCP — Kelly Fang [Grand Ballroom / Keynote]
• 10:25 — Keynote: The Missing Mechanisms of the AI Economy — Tim O'Reilly [Grand Ballroom / Keynote]
• 10:35 — Coffee Break; Solutions Showcase opens [Solutions Showcase]
• 10:45 — Demo Theater: Wake Up, Neo: Debug Agent Memory Across Conversations — Nyah Macklin [Solutions Showcase / Demo Theater / Sponsored Session]
• 10:55 — Workshop: Stack It Yourself: Open Infrastructure for AI Agents, from Compose to Cluster — Brian Benz, Pamela Fox [LL21D / Open Source Tools / Workshop]
• 10:55 — Architecting Agentic Commerce: The Universal Commerce Protocol and Agent Payments Protocol — Amit Handa, Prateek Dudeja [210C / Agentic Commerce / Breakout]
• 10:55 — The MCP Cold-Start Problem: When Your Agent Has 100 Tools and Has to Pick One — Karthik Karunanithi [LL20A / MCPCon / Breakout]
• 10:55 — 1,149 Hackers Tried to Break Our AI Agent Guardrails. 0 Succeeded. Here's Why. — Uchi Uchibeke [LL20C / Interoperability & Standards / Breakout]
• 10:55 — The Agent Has Left the Chat — Harald Kirschner [LL21A / Interoperability & Standards / Breakout]
• 10:55 — How Open Standards Solve the Missing Identity Layer for AI Agents — Aaron Parecki, Danny Zollner [210A / Interoperability & Standards / Sponsored Session]
• 10:55 — Workshop: Break the Lethal Trifecta: Designing Access Boundaries Agents Can't Talk Their Way Past — Zayne Turner, Chris Miller [230A / Interoperability & Standards / Workshop]
• 10:55 — Is Your Agent Any Good? Lessons From a Wide and a Deep Deployment — Ethan Lo, Jason Jiang [230C / Enterprise Adoption in Practice / Breakout]
• 11:30 — Beyond LLMs in a Loop: Building Trusted Agents in Regulated Industries — Lucas Beeler [210C / Enterprise Adoption in Practice / Breakout]
• 11:30 — Protocol Pivoting: How SSRF in MCP Servers Enables Cross-Protocol Lateral Movement — Syed Anas Mohiuddin [LL20A / MCPCon / Breakout]
• 11:30 — Decentralized Discovery: MCP, Skills, and Beyond with AI Catalog — Tadas Antanavicius [LL20C / Interoperability & Standards / Breakout]
• 11:30 — Event-Driven Multi-Agent Orchestration: Fast Path, Smart Path, and Everything in Between — Sijie Guo [LL21A / Multi-Agent & Distributed Systems / Breakout]
• 11:30 — Patterns for Shifting from MCP as a Basic API to MCP as Agent Integration Interface — James Ward, Alexander Ioffe [210B / MCPCon / Breakout]
• 11:30 — Agents, Infrastructure, and the Future of AI-native Applications — Kevin Cochrane [210A / Enterprise Adoption in Practice / Sponsored Session]
• 11:45 — Demo Theater: Where Did All Your Tokens Go? — Kevin Rhine [Solutions Showcase / Demo Theater / Sponsored Session]
• 12:00 — Demo Theater: Building Plugins for Claude — Tobin South [Solutions Showcase / Demo Theater / Sponsored Session]
• 12:05 — Stop Agents From Leaking Your Secrets - AI Hooks To The Rescue — Dwayne McDaniel [210C / Agentic Engineering / Breakout]
• 12:05 — Why the Heck Aren't Any Agents Supporting MCP Tasks? — Cornelia Davis [LL20A / MCPCon / Breakout]
• 12:05 — When Agents Spawn Agents: Securing Recursive Delegation in Multi-Agent Systems — Anishma Mavuram [LL20C / Interoperability & Standards / Breakout]
• 12:05 — Self-Hosting Agents: What Changes When Models Become Infrastructure — Miriah Peterson [LL21A / Open Source Tools / Breakout]
• 12:05 — MCP Apps + WebMCP - The Next Era of Interface — Liad Yosef, Dominic Farolino [210B / Human-Agent Collaboration / Breakout]
• 12:05 — Breaking the Governance Bottleneck: Why Scaling Control Gets Agents to Production Faster — Dr. Rania Khalaf [210A / Building Reliable Agent Systems / Sponsored Session]
• 12:15 — Demo Theater: Govern the Full AI Data Path with Kong AI Gateway — Deirdre Anderson [Solutions Showcase / Demo Theater / Sponsored Session]
• 12:27 — Demo Theater: Chaos Engineered: How to Build Invincible Agents and MCP Systems — W. Ian Douglas, Melissa Herrera [Solutions Showcase / Demo Theater / Sponsored Session]
• 12:30 — Attendee Lunch; Prompt à la Carte [Solutions Showcase]
• 12:36 — Demo Theater: Intent-based Authorization: "That's Not What I Asked You to Do." — Geoff Goodman [Solutions Showcase / Demo Theater / Sponsored Session]
• 12:51 — Demo Theater: Agents, Infrastructure, and the Future of AI-native Applications — Kevin Cochrane [Solutions Showcase / Demo Theater / Sponsored Session]
• 13:03 — Demo Theater: Are Your Agents Under Control? Prove It | Agent Governance in 10 Minutes — Tori Jeffcoat, Muhammad Ali [Solutions Showcase / Demo Theater / Sponsored Session]
• 13:15 — Demo Theater: AuthZ for Agents — Aaron Tainter [Solutions Showcase / Demo Theater / Sponsored Session]
• 13:45 — Workshop: Governing AI Agent Actions: MCP and Beyond — Shannon Williams, Bill Maxwell [LL21D / Enterprise Adoption in Practice / Workshop]
• 13:45 — Building an Agentic Eval Pipeline: Battle-Tested Lessons with EvalBench — Kurtis Van Gent, Haoyu Wang [210C / Evals & Testing / Breakout]
• 13:45 — One Server, Many Apps: A Composable MCP Architecture for Observability — Anirudha Jadhav, Shenoy Pratik Gurudatt [LL20A / MCPCon / Breakout]
• 13:45 — Interoperable Agent Discovery: AI Catalog, ARD, and the AGNTCY Directory — Luca Muscariello, Junjie Bu [LL20C / Interoperability & Standards / Breakout]
• 13:45 — Your AI Agent Installed Malware Because a SKILL.md Told It To — Liran Tal [LL21A / Building Reliable Agent Systems / Breakout]
• 13:45 — The Agentic SDLC: How We Shipped AI-Native Software at a Legacy Company — Austin Brown [210B / Enterprise Adoption in Practice / Breakout]
• 13:45 — Beyond Scopes: Governing What Agents Are Actually Allowed to Do — Aaron Tainter [210A / Building Reliable Agent Systems / Sponsored Session]
• 13:45 — Hermes Agent: The Agent That Grows With You — Sam Herring [230A / Agentic Engineering / Breakout]
• 13:45 — ID-JAG: Solving OAuth Sprawl for Enterprise AI Agents — Aaron Parecki, Den Delimarsky [230C / Enterprise Adoption in Practice / Breakout]
• 14:20 — Your Agents Need a Router: One Integration for Every Model and Tool — Varun Talwar [210C / Open Source Tools / Breakout]
• 14:20 — Your Tool Is in Another Castle: How Five Frameworks Reshape the Same MCP Server — Thierry Damiba [LL20A / MCPCon / Breakout]
• 14:20 — Shipping Agent Skills Safely: CI/CD, Evals, and Guardrails — Michael Larson [210B / Agentic Engineering / Breakout]
• 14:20 — Ship Your Most Powerful Agent: 7 Factors for Production Guarantees — Zayne Turner [210A / Building Reliable Agent Systems / Sponsored Session]
• 14:20 — Don't Route What You Can't Redact: Sensitivity-Aware LLM Routing — Christopher Nuland, Grace Ableidinger [230A / Open Source Tools / Breakout]
• 14:20 — Mapping Industry Representation and Gaps in Agentic AI Standards — Jake Pineda [230C / Interoperability & Standards / Breakout]
• 14:55 — Memory Isn't learning: What's Everyone Missing in Self-Evolving AI — Sparsh Jain [210C / Agentic Engineering / Breakout]
• 14:55 — From Pain Points to Production: What We Learned Building MCP-Powered ChatGPT Apps — Nikolay Rodionov [LL20A / MCPCon / Breakout]
• 14:55 — The Agentic Orchestration Stack: Durability, Guardrails, and Attestation — Yaron Schneider [LL20C / Agentic Engineering / Breakout]
• 14:55 — Making Swarm Work: Coordination Primitives for Decentralized Multi-Agent Systems — Jodee Varney [LL21A / Multi-Agent & Distributed Systems / Breakout]
• 14:55 — Agentic State Machines: Turning an Agent Loop into an Experimentation Platform — Douwe Osinga [210B / Agentic Engineering / Breakout]
• 14:55 — What Most AI Gateways and Goldfish Have in Common — Amit Naik [210A / Agentic Engineering / Sponsored Session]
• 14:55 — What Happens When You Integrate MCP and A2A at the Infrastructure Layer — Mohamed Maktal [230A / Interoperability & Standards / Breakout]
• 14:55 — Your Agent Sandbox Is Built Backwards — Dan Fernandez, Ariadne Conill [230C / Building Reliable Agent Systems / Breakout]
• 15:30 — Workshop: Secure Agentic Framework (SAF) for Agentic AI — Sarah Evans, Jautau "Jay" White, Frederick Kautz, Laura Guazzelli [LL21D / Interoperability & Standards / Workshop]
• 15:30 — Open Source Has Been Here Before: Sustainability Lessons for Agentic AI — Katherine Druckman [210C / Open Source Community & Ecosystem Health / Breakout]
• 15:30 — Data Agents over S3: Build the Missing Semantic Layer for Files — Dmitry Petrov [LL20A / MCPCon / Breakout]
• 15:30 — Agent Governance Lives in the OS — Alexander Sklar, Roberth Karman [LL20C / Open Source Tools / Breakout]
• 15:30 — How Contexts Fail (and How to Fix Them) — Drew Breunig [LL21A / Open Source Tools / Breakout]
• 15:30 — The Agentic Web for Industry Verticals — Andrew Nolan [210B / Enterprise Adoption in Practice / Breakout]
• 15:30 — Extending AI Agents to Real-World Devices with Device Connect [210A / Agentic Engineering / Sponsored Session]
• 15:30 — Approval Gates for MCP Tool Calls: Human-in-the-Loop Without Bypassing the Standard — Antoni Kozelski [230C / MCPCon / Breakout]
• 15:35 — Authorization After OAuth: Controlling Tools on Hosted MCP Servers You Don't Own — Nick Taylor [230A / Interoperability & Standards / Breakout]
• 16:05 — Reading is Free, Spending is Not: What a Minimal Agent Learns Probing Live Ecommerce Endpoints — Francesco Marinoni Moretto [210C / Agentic Commerce / Breakout]
• 16:05 — Prove What Your Agent Did: Tamper-Evident Audit Trails for Tool Calls — Vikas Luthra [LL20A / MCPCon / Breakout]
• 16:05 — Agentic Workflows Are Distributed Systems: The Multi-Cloud Production Patterns You Cannot Avoid — Praneeth Kamalaksha Patil [LL20C / Multi-Agent & Distributed Systems / Breakout]
• 16:05 — From AI Assistants to Trusted SDLC Agents: FINRA's Agentic Engineering Journey — Geetha Ramachandran [LL21A / Agentic Engineering / Breakout]
• 16:05 — Stop Writing Agents, Declare Them: Declarative Agent Architecture in Production — Chris Knuteson [210B / Building Reliable Agent Systems / Breakout]
• 16:05 — Beyond Chat: Lessons Learned Building Intelligent UIs with MCP Apps — Riley Scheid [230A / Multi-Agent & Distributed Systems / Breakout]
• 16:05 — Governed MCP: Policy Enforcement, Tamper-Evident Audit Chains, and Hardware-Sealed Receipts — Imran Siddique [230C / Enterprise Adoption in Practice / Breakout]
• 16:40 — Beyond Scraping: Building Agent-Ready Documentation Layers for MCP and AI Agents — Ayodeji Ogundare [210C / Agentic Engineering / Breakout]
• 16:40 — From MCP Tool-call to Motor Command: Giving Agents Fleet-scale Control of Real Hardware — Alexander Tsyplikhin [LL20A / MCPCon / Breakout]
• 16:40 — Why Your Agent Is Failing: Failure Modes from 6,000+ Agent Trajectories — Han Xu [210A / Evals & Testing / Breakout]
• 16:40 — Context Is the Substrate: Production Patterns for Knowledge-Graph-Backed Agents — Cassie Shum [230A / Building Reliable Agent Systems / Breakout]
• 16:40 — Breaking the Agentic Loop - Multi-Turn Exploits Against Tool-Using AI Agents — Bar Kaduri [230C / Agentic Engineering / Breakout]