Skip to Content
View all events

O’Reilly Demo Day

Published by O'Reilly Media, Inc.

Intermediate content levelIntermediate

Building Robust AI Apps and Agents with MCP

We’re moving from a world of custom integrations and proprietary APIs to a standardized protocol that treats data connectivity as infrastructure. Through recent developments like the Model Context Protocol (MCP), every application becomes a potential collaborator in a larger AI ecosystem rather than a collection of isolated tools requiring custom integration work.

This is big stuff. To demonstrate how MCP is creating the architecture of participation for AI systems, we’ve curated a series of really compelling, fast-paced demos from members of our network of experts who are already building proof-of-concept applications on the bleeding edge of MCP. We’re calling this event O’Reilly Demo Day, and we’d love for you to attend. We’re still pulling together the lineup, but here’s some of what you can expect.

First, Google’s Heiko Hotz and Sokratis Kartakis will demo how the interplay between Agent2Agent (A2A) communication and MCP creates a powerful foundation where specialized agents can be dynamically discovered and safely execute tools on behalf of other agents, all while maintaining clear boundaries and security controls through standardized protocols.

Then Quantmate’s Nicole Koenigstein will show how autonomous agents can use MCP not just to connect with tools but to communicate with each other. She’ll demo a multi-agent coding system where agents collaborate by sharing, correcting, and evolving code together, using MCP as a shared protocol between reasoning agents, enabling structured coordination, reflection, and continuous innovation. It’s a step toward building self-improving AI systems.

Next, DreamFactory's Jason Gilmore will demonstrate how DreamFactory is using MCP as an entirely new way to introduce its product to key decision makers without requiring them to step through a laborious, time-consuming on-premises installation and database requisition process. Jason believes MCP will ultimately pave the way for a new kind of app store, and he’ll introduce a few steps your organization can take today to put your product in front of more prospective customers than ever before.

After that, PagerDuty’s José Côrte-Real will show how his team built a supervisor-style coordinator agent that asks PagerDuty’s agents real-world questions about analytics and shift scheduling, detecting conflicts, and even creating overrides. Jose will discuss two complementary paths they’re pursuing: first-party agents that offer tight integration and low latency, and MCP-based agents that expose APIs and workflows more flexibly. If you’ve ever wrestled with coordinating multiple AI agents—or wondered how to balance autonomy, performance, and extensibility—you won't want to miss this session.

And then to wrap things up, Flipkart’s Virender Bhargav introduces us to an innovative root cause analysis (RCA) and insights copilot designed to help teams move beyond reactive measures by proactively identifying business anomalies and patterns. Can this agent really reduce anomaly detection time from days to hours, cut mean RCA time to under three hours, and improve coverage of previously undetected incidents by 50%? The proof will be in the pudding!

We think that after you see these demos, you’ll agree that the world has shifted from AI simply being an add-on feature to an existing product to AI as integrated infrastructure that enhances every aspect of how we work with information. MCP enables the kind of network effects that made the web so powerful, in how every new MCP-compatible tool increases the value of every other tool in the ecosystem. We hope you’ll join us for Demo Day and get inspired to make your own tools and connections.

Recommended Resources

Schedule

The time frames are only estimates and may vary according to how the class is progressing.

Introduction (5 minutes)

Tim and Jon welcome you to O’Reilly Demo Day.

Demo 1 – Heiko Hotz and Sokratis Kartakis (20 minutes)

Demo 2 – Nicole Koenigstein (20 minutes)

Demo 3 – Jason Gilmore (20 minutes)

Break (5 minutes)

Demo 4 – José Côrte-Real (20 minutes)

Demo 5 – Virender Bhargav (20 minutes)

Closing Remarks (5 minutes)

Jon closes out today’s event.

Your Hosts and Guests

  • Tim O'Reilly

    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 non-profit AI Disclosures Project, which he co-founded 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.

    linkedinXlinksearch

  • Jonathan Hassell

    Jonathan Hassell is content director for data and AI at O'Reilly. He's been writing, editing, and presenting technical content for 25 years, and yet he still can’t remember how to exit Vim.

  • Heiko Hotz

    Heiko Hotz is a generative AI Global Black Belt at Google Cloud. Known for his unique blend of technical depth, strategic insight, and proven delivery in the AI agent space, he drives multimillion-dollar AI initiatives for global clients. He specializes in deploying AI agents at scale, building complex evaluation frameworks, and automating prompt engineering pipelines, directly influencing product development and enabling significant AI adoption for enterprises. With experience at Amazon, AWS, and Google, Heiko holds an MS in physics and an MBA from London Business School.

  • Sokratis Kartakis

    With over 20 years of experience, Dr. Sokratis Kartakis is a leader in generative AI at Google Cloud, specializing in moving generative AI models, applications, and agents into production. His work bridges the gap between complex technical challenges and real-world innovative implementation. He holds a PhD from Imperial College London, and with experience from Yale University, Google, and AWS, he has delivered significant business value by deploying production-ready AI systems for over 180 enterprise clients across diverse sectors.

  • Nicole Koenigstein

    Nicole Koenigstein is an independent data scientist and quantitative researcher as well as an AI consultant, leading workshops and guiding companies from AI concept to deployment. Previously, she was CEO and cochief AI officer at Quantmate. Nicole is the author of the books Mathematics for Machine Learning with NLP and Python and Transformers in Action (Manning) and the forthcoming books AI Agents: The Definitive Guide and Transformers: The Definitive Guide for O’Reilly. She shares her expertise in Python, machine learning, and deep learning as a guest lecturer at various universities.

  • Jason Gilmore

    W. Jason Gilmore is CTO of Adalo, a popular no-code mobile app builder. A technologist and software product leader with over 20 years of industry experience, he previously served as CEO of the coding education platform Treehouse. Jason leads technical M&A due diligence for Xenon Partners and focuses heavily on applying and building solutions around AI coding technologies. He's also the founder of SecurityBot.dev and cofounder of 6DollarCRM.com.

  • José Côrte-Real

    José Côrte-Real is a staff software engineer at PagerDuty where he’s exploring the synergy between distributed systems and machine learning to drive the company’s efforts on automated incident response. He started his career as a researcher in distributed systems at the University of Lisbon and focused his later efforts on defense applications and machine learning for medical devices and vehicular fault prediction.

  • Virender Bhargav

    Virender Bhargav is a seasoned engineering leader whose expertise spans business technology integration, enterprise applications, system design/architecture, and building highly scalable systems. With a deep understanding of technology, he has spearheaded teams, modernized technology landscapes, and managed core platform layers and strategic products. With extensive experience driving innovation at companies like Paytm and Flipkart, his contributions have left a lasting impact on the industry.

Skill covered

DevOps