Featured Keynote Speakers

Tim O'Reilly

Open Source Pioneer; Founder & CEO

O’Reilly Media

Tim O’Reilly is the founder and CEO of O’Reilly Media, Inc. His original business plan was simply “interesting work for interesting people,” and that’s worked out pretty well. He publishes books, runs online conferences, invests in early-stage startups, urges companies to create more value than they capture, and tries to change the world by spreading and amplifying the knowledge of innovators. He’s perhaps best known for his role in shaping big ideas like open source software, unconferences (Foo Camp), Web 2.0, and government as a platform. His 2017 book WTF? What’s the Future and Why It’s Up to Us explored the role of human agency in shaping the future in the face of the coming AI wave. These days, he’s focused on mechanism design for the human-AI economy. Mechanism design is sometimes described as “reverse game theory,” whereby you start with the outcome you want and then figure out what rules of the game will produce that outcome. He explores these ideas at the nonprofit AI Disclosures Project, which he cofounded with Ilan Strauss. He writes frequently on Substack at the O’Reilly Radar, the AI Disclosures Project’s Asimov’s Addendum, and his own Conversations with AI.

Conference Sessions

• Keynote: The Missing Mechanisms of the AI Economy Oct 23, 2026 • 10:25 AM-10:35 AM Grand Ballroom (Concourse Level)

  Every major technological invention is accompanied by the invention of new economic mechanisms to take advantage of it. Think of how PageRank, pay per click advertising, and seamless online payments became the economic engines of the web, GPS-based location matching marketplaces became the basis for Uber, Lyft and the rest of the smartphone based on-demand economy, and YouTube ContentID for the creator economy. We don't yet have breakthrough market mechanisms for the AI economy. What are some of the missing mechanisms of the AI economy? How does an understanding that they haven't been invented yet change the discussion about AI and jobs for humans?

Thomas Dohmke

Former CEO, GitHub; Co-Founder & CEO

Entire

Fascinated by software development since his childhood in Germany, Thomas Dohmke has built a career creating tools developers love. Based out of Seattle, Washington, Thomas is the CEO and co-founder of Entire, the world's next developer platform in the era of AI. Formerly, Thomas was Chief Executive Officer of GitHub, where he led the company’s growth to over 150 million developers and oversaw the rise of GitHub Copilot — the world’s most widely adopted AI developer tool — now with over 20 million users and counting. Thomas is a celebrated TED speaker and holds a PhD in mechanical engineering from the University of Glasgow, UK.

• Company Website

Conference Sessions

• Keynote: Building the Git Forge of the Future Oct 23, 2026 • 9:50 AM-10:00 AM Grand Ballroom (Concourse Level)

  Coding agents write high-quality code faster than ever and pick up work with growing autonomy, yet the human developer still sits at the center of every pull request while context fragments across chats, prompts, sessions, and branches, leaving agents stateless and developers blind to intent and decisions. Meanwhile bottlenecks build, and the trust gap between collaborators grows wider than ever. It's time for a new git forge built for agent-to-human and agent-to-agent collaboration, one that collapses planning, design, implementation, review and deployment into a continuous loop without sacrificing quality, security or trust. Join Thomas Dohmke, CEO of Entire and previously CEO of GitHub, for a keynote on where developers and agents are headed together in this next generation.

David Soria Parra

Co-creator of MCP

Anthropic

I am David Soria Parra, I am a Member of Technical Staff at Anthropic. I have a rich history in developing and maintaining open source software. I’ve actively contributed to the PHP programming language as a core developer and was responsible for the official releases of PHP 5.4 and PHP 5.5. I actively contributed to Git and Mercurial and developed key features within Mercurial such as bookmarks, pager, shelving and more. Between 2013 and 2017 I was a software engineer at Facebook’s developer infrastructure team. From 2017 I managed increasingly larger teams and organisation within Facebook, with a particular focus on extending our internal tools to new development areas such as VR, AR and ASIC development. In 2021, I moved to London where I lead an organisation of 45+ people across multiple managers, focusing Static Analysis and Simulation-based Testing teams. In 2023 I was an enterpreneur in residence at Sutter Hill Ventures in London. I joined Anthropic in April 2024. I am the co-creator of the Model Context Protocol.

Conference Sessions

• Keynote: MCP and the Era of Connectivity Oct 22, 2026 • 9:30 AM-9:40 AM Grand Ballroom (Concourse Level)

Sarah Drasner

Distinguished Engineer & Area Tech Lead, AI & Web Ecosystem, Chrome

Google

Sarah is a Distinguished Engineer, and Area Tech Lead for AI and the Web Ecosystem for Chrome at Google. She's formerly Sr. Director of Engineering at Google, leading the Core Infrastructure teams that power Google apps (Search, YouTube, Workspace, Cloud, etc) on the Web, Android, iOS, Multiplatform, Experimentation, and Client Observability. She was Incident Commander for Core Developer Infrastructure at Google and led the Search mission for Core Developer- working across thousands of engineers to ensure the success of Search with Core Developer Infrastructure. Sarah Drasner is an award-winning Speaker, and she was formerly VP at Netlify and Principal at Microsoft Azure. Sarah is an instructor at Master.dev, and has written two books. She co-organized Concatenate, a non-profit that created free conferences and workshops for Nigerian and Kenyan developers with Chris Nwamba. She likes cheese.

Conference Sessions

• Keynote: The Agentic Web Oct 22, 2026 • 2:00 PM-2:10 PM Grand Ballroom (Concourse Level)

  AI is reshaping the web from a place we navigate ourselves into an environment where agents can discover, interpret, and act on our behalf. This shift is creating new pathways, new user experiences, and new questions about what the web is becoming. In this keynote, we’ll explore the rise of the agentic web: how AI is changing the composition of the internet, how emerging specifications like WebMCP are beginning to define new interaction patterns, and what this shift means for builders, platforms, security, and the future of user experience. Most importantly, we’ll connect the vision to what’s possible today, what’s coming next, and how we can help shape an agentic web that expands what people and software can accomplish together.

• MCP Apps + WebMCP – The Next Era of Interface Oct 23, 2026 • 12:05 PM-12:30 PM 210B (Concourse Level)

  WebMCP is a way for an agent to interact with your website / UI. MCP Apps are a way for a server to return UI to be displayed in the agent – for visualization, branding and the “last mile of interaction”. These two technologies sit on both sides of the agentic-UI spectrum, and combining them completes the full cycle of human-agentic interactions. By combining WebMCP with MCP Apps, you can expose your capabilities directly to an agent that rides alongside the user. This also allows the agent to use WebMCP to control an MCP Apps UI. Walk away from this session with the ability to use WebMCP to let an agent drive your existing website, learn how to expose specific site functions (like "Compare Pricing") that the agent can render as an interactive, on-the-fly widget inside a chat sidecar with MCP Apps and build flows where the user handles the visual interaction, and the agent handles the heavy lifting. Understand the use cases and best practices for WebMCP and MCP Apps, and see how combining them usher in the new era of interfaces.

Thomas Sarlandie

Member of Technical Staff

OpenAI

Angie Jones

Vice President

Agentic AI Foundation

Angie Jones is the VP of Developer Experience at the Agentic AI Foundation where she guides how agentic systems are designed, implemented, and adopted across the global developer ecosystem. Angie is an award-winning teacher and international keynote speaker who shares her wealth of knowledge at software companies and conferences all over the world. As a Master Inventor, Angie is known for her innovative and out-of-the-box thinking style which has resulted in more than 25 patented inventions in the areas of virtual worlds, collaboration software, social networking, smarter planet, and software development processes.

• X
• LinkedIn
• Instagram
• Sessionize
• Blog
• Company Website
• Personal Website

Conference Sessions

• Welcome to AGNTCon + MCPCon North America Oct 22, 2026 • 9:00 AM-9:05 AM Grand Ballroom (Concourse Level)

Dawn Song

Professor, Computer Science, UC Berkeley; Director, Berkeley RDI (Berkeley Center for Responsible Decentralized Intelligence); VP of AI Research, Meta

UC Berkeley; Berkeley RDI; Meta

Dawn Song is a Professor in Computer Science at UC Berkeley and Co-Director of Berkeley Center for Responsible Decentralized Intelligence. Her research interest lies in AI safety and security, Agentic AI, deep learning, security and privacy, and decentralization technology. She is the recipient of numerous awards including the MacArthur Fellowship, the Guggenheim Fellowship, the NSF CAREER Award, the Alfred P. Sloan Research Fellowship, the MIT Technology Review TR-35 Award, ACM SIGSAC Outstanding Innovation Award, and more than 10 Test-of-Time Awards and Best Paper Awards from top conferences in Computer Security and Deep Learning. She has been recognized as Most Influential Scholar (AMiner Award), for being the most cited scholar in computer security. She is an ACM Fellow and an IEEE Fellow, and an Elected Member of American Academy of Arts and Sciences. She obtained her Ph.D. degree from UC Berkeley. She is also a serial entrepreneur and has been named on the Female Founder 100 List by Inc. and Wired25 List of Innovators.

Conference Sessions

• Keynote: Towards Building Safe & Secure Agentic AI Oct 22, 2026 • 1:30 PM-1:40 PM Grand Ballroom (Concourse Level)

  Recent advancements in AI and LLM agents have unlocked powerful new capabilities across a wide range of applications. However, these advancements also bring significant risks that must be addressed. In this talk, I will explore the various risks associated with building and deploying AI and LLM agents and discuss approaches to mitigate them. I will also examine how frontier AI and LLM agents could be misused, particularly in cyber security attacks, and how they may reshape the cyber security landscape. Ensuring a safe AI future demands a sociotechnical approach. I will outline our recent proposal for a science- and evidence-based AI policy, highlighting key priorities to deepen our understanding of AI risks, develop effective mitigation approaches, and guide the development of robust AI policies.

Chi Wang

Founder of AutoGen/AG2 and MassGen; Senior Staff Research Scientist

Google Deepmind

Chi Wang is founder of AutoGen (now AG2), one of the most widely used open-source frameworks for agentic AI, and MassGen, an open-source multi-agent scaling system. He is a Senior Staff Research Scientist at Google DeepMind with 15+ years of research experience across Microsoft Research, Meta, UIUC, and Tsinghua University. He is also the creator of FLAML, a fast library for AutoML and hyperparameter tuning. His work has earned multiple awards, including Best Paper at ICLR'24 LLM Agents Workshop, SIGKDD PhD Dissertation Award, Open100, and TheSequence's pick of 5 favorite AI papers in 2023. AutoGen (AG2) is used by leading organizations including Nvidia, Google, Microsoft, JPMorgan, Walmart, AT&T, and top research institutions including Harvard, MIT, Cambridge, Oxford, Princeton, and Cornell, with over 50,000 GitHub stars. It has achieved top performance in SWE-bench, OSWorld, and WebArena benchmarks for software engineering, computer use, and web automation, and has been applied to scientific discovery across physics, life sciences, chemistry, material science, planetary science, and chip design. Dr. Wang teaches at Stanford, Berkeley, Coursera, and DeepLearning.AI, leads an open-source community with over 21,000 members, and serves as advisor and investor to agentic AI startups.

Conference Sessions

• Keynote: Sutando: My AI Stand Oct 23, 2026 • 9:30 AM-9:40 AM Grand Ballroom (Concourse Level)

  Sutando is an open-source personal AI agent that runs on hardware its owner controls. It hears and speaks, sees the screen, handles mail and calendar, writes and reviews its own code, and keeps upgrading itself — one system doing all of it, for one person, continuously. It recently caught its own alerting pipeline dropping jobs silently and shipped the detector within the hour. Others now run their own, and the agents review each other's code — nobody asked them to. I'll bring the live system and show where it has got to.

Kelly Fang

Member of Technical Staff

Anthropic

Kelly Fang works on product for the Claude Platform at Anthropic. She focuses on the Model Context Protocol (MCP) and the plugin ecosystem that links Claude to the tools and data people use at work, including the Claude directory where developers publish their MCP servers.

Conference Sessions

• Keynote: How Anthropic is Building with MCP Oct 23, 2026 • 10:20 AM-10:25 AM Grand Ballroom (Concourse Level)

  In this keynote, Kelly Fang shares how Anthropic is adopting and building with MCP across all of its products, what the team has learned from running it at scale, and what Anthropic is building next.

Bradley Axen

Creator & Maintainer of Goose; Head of AI Capabilities

Block

Brad is the Lead for AI at Block, where he builds both internal- and external-facing AI agents and tools. He created and maintains goose, the open-source AI agent framework in the AAIF, and was one of the co-creators of Buzz. Brad previously earned his physics PhD from UC Berkeley and worked on processing and analyzing data at the Large Hadron Collider at CERN in Geneva.

Conference Sessions

• Keynote: Building the Human-Agent Workplace Oct 22, 2026 • 9:45 AM-9:55 AM Grand Ballroom (Concourse Level)

  The first generation of AI agents lived in isolated chat sessions. But for agents to contribute meaningful work, they need more than a conversation—they need shared context, durable identity, governed access to tools, and clear paths for delegation and review. At Block, we’re building an integrated environment that connects individual agentic development, team collaboration, and a shared capabilities layer for accessing the systems that run our business. In this keynote, we’ll share the architecture and operating model behind that shift, including how people and agents coordinate work, how permissions and identity carry across tools, and how automation and model routing help the system operate at scale.

• Workshop: The Buzz-Word Is Collaboration 🐝 Oct 22, 2026 • 2:20 PM-3:55 PM LL21D (Lower Level)

  Most teams made a person the API between their agents and everyone else: copy the output into chat, paste the reply back into the harness. This hands-on workshop shows the alternative: put the agents where the work is. We use Buzz, Block's open source, channel-driven workspace where people and AI agents share conversations, repositories, and reviews. We begin in the middle of a live project, with four people and a swarm of agents working across shared channels and code. Then we rewind and bring the room in. Attendees will join a shared Buzz community, work with an agent, form channels with other participants, and practice delegating, steering, reviewing, and coordinating work as it happens. Along the way, we examine how Buzz approaches portable identity, scoped capabilities, signed work, and collaboration across different agent runtimes and models. By the end, the room itself becomes part of the workflow: everyone contributes code, assets, and reviews to one shared project in a Buzz-hosted Git repository. Bring a laptop. Leave with practical experience running many agents in one shared workspace, where the whole team can see, steer, and use them. Space Limited – First Come, First Served. Please bring a fully charged laptop to the workshop

Rao Surapaneni

VP/GM, Business Application Platform & Developer Launchpad

Google

Rao Surapaneni is the VP/GM of the Business Application Platform & Developer Launchpad organization as part of Cloud AI at Google Cloud. He leads the teams building Agent Governance Platform with Apigee and Agent Gateway. He is also evolving Colab, Specialized AI and Vertex AI Studio for the next phase of growth. He led the launch of Agent2Agent protocol from idea to industry adoption and is recognized as He is an active member of Agentic AI Foundation that is defining open source standards for internet of Agents. He is named as one of the honorees in 2026 Okta Identity List for innovating to the dynamic landscape of AI. Prior to joining the Google Cloud team, Rao held leadership roles at ServiceNow, driving AI platform innovation and leading engineering organizations. He brings deep expertise in large language models, generative AI, and scaling platforms for enterprise success. As Country Head for India during the key growth phase of the company he developed organizational capability in India by growing the team from 400 to 2500 in 2 years. Previously, his work at Microsoft focused on speech science and search metrics engineering leadership. Driven by a desire to innovate and delight users, he excels at bringing customer-focused products to market, leveraging disruptive technologies to create exceptional user experiences.

Conference Sessions

• Keynote: Shipping Autonomous Agents Safely with Open Standards, Observability, and Control Oct 23, 2026 • 10:10 AM-10:15 AM Grand Ballroom (Concourse Level)

  Everyone wants more agents in production with higher autonomy, from a solo developer wiring up MCP tools on a laptop to an enterprise CIO governing thousands of workflows. Moving too fast without guardrails creates runaway risk, while heavyweight proprietary gates trap teams in pilot purgatory. In this 5-minute keynote, Google Cloud VP Rao Surapaneni shares how open standards under the Linux Foundation and Agentic AI Foundation (AAIF) turn observability and governance into an enabling platform rather than a speed bump. By combining open protocols like MCP, A2A, and OpenTelemetry with a unified control tower for security and policy enforcement, builders can safely grant agents real production autonomy while feeding live telemetry directly back into continuous product, eval harness, and model improvements.

Shadaj Laddad

Research Lead, Hydro at AWS

AWS

Shadaj is the research lead for the Hydro team at AWS. His work explores techniques that enable agentic coding for distributed systems, powered by Hydro: a Rust framework that enforces distributed correctness at compile-time. Previously, Shadaj received his PhD at UC Berkeley co-advised by Alvin Cheung and Joe Hellerstein, where he designed Hydro and its semantics. Shadaj is a founder and co-organizer of the SF Systems Club, which runs meetups and coffee chats for systems enthusiasts. When not researching, you'll find him playing the sitar, editing travel photos, or hiking around the Bay Area.

Conference Sessions

• Keynote: Predictable Correctness for Unpredictable Code Oct 23, 2026 • 10:05 AM-10:10 AM Grand Ballroom (Concourse Level)

  As coding agents become increasingly autonomous, the bottleneck has shifted to verification: how do we know if the code is correct? Code review cannot scale to the throughput of modern agents. And unit tests often miss issues that materialize across distributed services. Two techniques offer a path forward: deterministic simulation and universal properties. Distributed simulation makes it possible to test end-to-end systems with production conditions like network failures. Universal properties, like null-pointer freeness and durability, enable tests that are independent of application specifics and naturally scale with your codebase. At AWS, we are putting these ideas together into Hydro: a distributed systems framework designed for agentic coding. Hydro offers a built in deterministic simulator that explores network interleaving, failures, and other sources of distributed bugs. And it uses the Rust type system to enforce universal properties of memory safety and determinism. In this talk, we'll explore the core principles behind Hydro, how it empowers agents to autonomously build correct systems, and take a peek at protocols for agent state we are building with Hydro!

Manik Surtani

CTO

Agentic AI Foundation

Manik Surtani is the co-founder and CTO of the Agentic AI Foundation (AAIF.io). A mission-driven technologist and longtime advocate of open source, he previously served as Head of Open Source at Block and VP of Engineering for Platform and Cloud at Cash App, and played a foundational role in the birth of gRPC. He founded Infinispan.org, has been a Sequoia Scout, Red Hat veteran, angel investor, and startup advisor, and is a published author and frequent speaker on AI, infrastructure, and open collaboration.

Conference Sessions

• Keynote: Who Keeps It Open? Oct 22, 2026 • 9:15 AM-9:25 AM Grand Ballroom (Concourse Level)

J.R. Storment

Executive Director

Tokenomics Foundation

Conference Sessions

• Keynote: Tokenomics: Energy to Intelligence to Value Oct 22, 2026 • 9:25 AM-9:30 AM Grand Ballroom (Concourse Level)

  Every autonomous agent you ship is also an autonomous buyer, spending tokens on models, tools, and retries that nobody explicitly approved. But tokens are only half the ledger. At scale the binding constraint is energy, and the metric that matters shifts from tokens consumed to intelligence delivered per watt. Both are the same question: how much useful value are we getting per unit of spend? That question belongs in your design reviews next to latency and reliability, and the discipline to answer it (Tokenomics), has to be neutral, open, and community-built.

Lena Hall

Senior Director Developers and AI

Akamai

Lena Hall is a Senior Director Developers and AI at Akamai and an expert in practical AI adoption, data engineering, cloud and pragmatic architecture, leading large, high-performing technical teams. Lena has 15+ years of deeply technical background as a solution architect, technical leader in large-scale data, analytics, machine learning, and cloud computing. Prior, Lena worked as Head of Developer Experience, North America at Amazon Web Services and led Big Data DevRel at Microsoft. She is the Founder of Droid AI, where she helps businesses get real results from AI. She frequently shares practical knowledge on her YouTube channel (youtube.com/@lena-hall) and at industry conferences as an international keynote speaker.

Conference Sessions

• Keynote: The Anything Trap: What to Build When Agents Can Build Everything Oct 22, 2026 • 1:40 PM-1:45 PM Grand Ballroom (Concourse Level)

  Agents made implementation nearly free — for you and for everyone pointing the same models at the same data. That's the Anything Trap: when anything can be built, everything converges. This keynote argues the value moved up the stack, from building to choosing. The one decision AI can't make is what deserves to exist. Five minutes on conviction, signal, and why agents build — but you choose.

Paul Conyngham

Founder

Gamgee Technologies

Paul Conyngham is an AI-innovation leader whose personal journey to help his dog Rosie through complex cancer treatment sparked broader conversations around personalised veterinary medicine and AI-supported care pathways. Following national media attention, Paul has engaged with veterinarians, clinics, researchers, and pet owners across Australia and internationally to explore how emerging technologies and personalised approaches may support vets managing complex or non-responsive oncology cases. His work focuses on collaboration, innovation, and empowering veterinary professionals with additional tools and insights while keeping vets central to patient care. Paul brings a unique perspective that combines emotional lived experience, AI-innovation, and visionary thinking around the evolution of veterinary treatment.

Conference Sessions

• Keynote: From My Dog’s Cancer to a Personalised mRNA Vaccine: Building Across Disciplines with AI Oct 23, 2026 • 9:40 AM-9:50 AM Grand Ballroom (Concourse Level)

  When my dog Rosie developed cancer and chemotherapy, immunotherapy and surgery were not enough, I used my background in machine learning to help develop a personalised mRNA cancer vaccine for her. The work crossed genomics, bioinformatics, immunology, software engineering and manufacturing- became the starting point for Gamgee. In this talk, I will share that journey and explore what it reveals about building in the age of AI agents. Agents give individuals and small teams a growing ability to work across disciplines, connect specialised tools and reason about how the parts of a complex solution fit together. Using Rosie’s vaccine as a concrete example, I will discuss where AI helped, where scientific and clinical collaborators were essential and what it takes to turn an ambitious idea into something that can be manufactured and tested. The wider opportunity is designing across an entire system: moving between the desired outcome, the underlying science and the practical constraints. Attendees will leave with a perspective on how agents can expand what a small team can attempt-and why some of the most consequential applications may emerge at the boundaries between fields.

Mazin Gilbert

Executive Director

Agentic AI Foundation

Mazin Gilbert is the Executive Director of the Agentic AI Foundation, part of the Linux Foundation. An IEEE Fellow with a Ph.D. in Artificial Intelligence and a Wharton MBA, Mazin brings 25+ years of experience driving AI innovation from research to global-scale deployment. His career spans senior leadership at Google as Director of Engineering for Google Distributed Cloud AI/ML, and at AT&T as VP of Network Analytics and Automation. Mazin has built production-grade GenAI, machine learning, and agentic AI platforms at scale. He co-founded open-source landmarks including ONAP, Akraino, and Acumos, and helped found the LF Networking, LF Edge, and LF AI. He has served on the boards of the Open Network Foundation, NSF MLWINS, and the International Computer Science Institute at Berkeley. Mazin holds 260+ U.S. patents, has authored 100+ research papers, and became an IEEE Fellow in 2012 for pioneering contributions to speech processing.

Conference Sessions

• Building The Internet of Agents in The Open Oct 22, 2026 • 9:05 AM-9:10 AM Grand Ballroom (Concourse Level)
• Welcome Back & Awards Oct 23, 2026 • 9:00 AM-9:20 AM Grand Ballroom (Concourse Level)

Jonathan Bryce

Executive Director of Cloud & Infrastructure

The Linux Foundation

Jonathan Bryce is the Executive Director of Cloud & Infrastructure at the Linux Foundation, where he leads both the Cloud Native Computing Foundation (CNCF) and the OpenInfra Foundation—two of the largest and most influential open source communities in the world. With over 15 years of open source leadership, Jonathan co-founded the OpenStack project, guiding its evolution into a global ecosystem that supports a multi-billion-dollar market and serves as the de facto standard for open cloud infrastructure. Before his open source career, Jonathan spent over a decade in data center infrastructure and co-founded one of the industry’s earliest cloud computing companies, which grew into a billion-dollar business following its acquisition by Rackspace. Passionate about open collaboration, infrastructure innovation, and empowering users, contributors, and ecosystems worldwide, Jonathan frequently speaks at international conferences on open source strategy, infrastructure modernization, cloud-native technologies, and open source AI initiatives.

Conference Sessions

• Keynote: From Bigger Models to Better Systems: Accelerating Open Intelligence Oct 23, 2026 • 9:20 AM-9:25 AM Grand Ballroom (Concourse Level)

  For years, progress in AI was closely tied to scale: bigger models, more data and more compute. But that equation is changing. Smaller and specialized models are becoming dramatically more capable, and new approaches to continual learning are enabling AI systems to improve from real-world experience after deployment. In this keynote, Jonathan Bryce explores what this shift means for the next generation of intelligent and agentic systems. Using examples of models that learn from production feedback to become faster, cheaper and more capable, he’ll show why the future of AI will depend not on any single model, but on an open set of technologies for building, optimizing, serving and continuously improving intelligence. He’ll also look at the growing role of the PyTorch Foundation in bringing those technologies together, creating an open foundation that gives developers the freedom to build with any model, on any chip and across any cloud.

Keith Babo

Chief Product Officer

Solo.io

Keith Babo is the Chief Product Officer at Solo.io, where he leads product strategy and execution, enabling enterprises to build and scale the next generation of cloud-native and agentic infrastructure for AI-driven applications. Prior to Solo.io, Keith held leadership roles in product management and engineering at Red Hat, Sun Microsystems, and Intel Corporation.

Conference Sessions

• Keynote: Agents as Actors: Harnessing the Power of Agentic Infrastructure Oct 22, 2026 • 1:50 PM-1:55 PM Grand Ballroom (Concourse Level)

  Harnessed agents have become the dominant interaction and runtime pattern for agentic AI. Claude Code, Codex, and a fast-growing field of open source harnesses integrate models with MCP tools, skills, and plugins. These harnesses provide sandboxed execution, scoped environment access, and human-in-the-loop controls on the desktop. The industry's next shift is already underway: moving harnessed agents from the desktop onto shared infrastructure, where security, observability, and governance are consistent across every agent interaction. In this talk, we will explore how open source infrastructure can deliver secure, scalable harnessed agents beyond the desktop.

Abhishek Choudhary

CTO

TrueFoundry

Abhishek Choudhary is the co-founder & CTO of TrueFoundry, an AI+MCP Gateway used by F500 enterprises. Before founding TrueFoundry, Abhishek spent time at Meta, leading teams responsible for large-scale video and caching infrastructure. Recognized speaker at top AI conferences including MachineCon, Agentic AI Summit, CIVO Navigate, GenAI Summit, DataHack Summit & Cypher. Through his speaking engagements, combined with his hands-on experience scaling systems for billions of users at Meta and entrepreneurial success with TrueFoundry, Abhishek is one of the most influential voices bridging cutting-edge research with practical enterprise AI implementation, and regularly shares practical insights on distributed systems, AI gateways and the engineering challenges of operating agentic AI at enterprise scale. He holds a degree in Computer Science from IIT Kharagpur

Conference Sessions

• Demo Theater: Bounded Autonomy: It's Earned, Not Granted Oct 22, 2026 • 12:51 PM-1:01 PM Solutions Showcase (Concourse Level)

  EchoStar's Director of AI shows how a single AI Gateway governs every call — LLMs, MCP tools, agents, Claude Code, Codex — with explicit boundaries. A demo of runtime governance that moves from observe → alert → throttle → hold → stop. **** 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), and details about the sponsored content or resources you interacted with. If you choose to interact with a booth or access sponsored content, you are explicitly consenting to receipt and use of such data by the third-party recipients, which will be subject to their own privacy policies.

• Keynote: From Black Box to Glass Box: Your 5-step Blueprint to Trustworthy Agents Oct 22, 2026 • 1:55 PM-2:00 PM Grand Ballroom (Concourse Level)

  Every token spent, every tool call made, every action taken inside a sandbox, every credential used – all of it should be visible, all the time, to the people responsible for that agent. Not buried across five dashboards after something breaks, but streaming through one place, in real time, before it becomes an incident. The fix isn't inside the agent's code – it's at the network layer. Intercept every call an agent makes, swap in short-lived scoped credentials instead of handing it real secrets, and log the tokens, tools, and sandbox actions through that same choke point. One vantage point. One trail. No blind spots. In 5 minutes: why ""trust the agent"" is the wrong model, and what it actually takes to make agent behavior as transparent as it needs to be – for the person debugging it at 2am, and the person who has to explain it to a regulator.