talk-data.com

Stream #35: Production-grade AI agents with SurrealDB & Pydantic AI

Explore the practical challenges of taking Graph-RAG agents from experiment to production with SurrealDB and PydanticAI. Unlike simple RAGs, these agents need durable, queryable memory, checked rules for agent requests and responses, and observability that surfaces retrieval and validation drift. In this session SurrealDB and PydanticAI show a compact, reproducible pattern - build a KG, run a typed pai-memory agent via the Gateway, and use Logfire/OTel to trace and diagnose failures.

About SurrealDB Stream SurrealDB Stream is our ongoing developer-focused livestream series on building AI-ready applications with SurrealDB, featuring hands-on demos, code examples and fireside discussions. Explore our past episodes here: https://www.youtube.com/playlist?list=PLvuQflRR4UzblK6jpMoFE_MuJ8JZ2e14_

About the speakers

Samuel Colvin - Pydantic, CEO & Founder Samuel Colvin is a Python and Rust developer and creator of Pydantic. The Pydantic library, which he created is downloaded over 300M/month and is a dependency of many GenAI Python libraries including the OpenAI SDK, the Anthropic SDK, Langchain, AutoGPT, instructor and LlamaIndex.

Tobie Morgan Hitchcock - SurrealDB, CEO & co-founder Tobie Morgan Hitchcock is CEO & Co-Founder of SurrealDB. He is an experienced tech entrepreneur, developer, and software engineer, with 17 years’ experience in the software and cloud-computing industries. In 2021 he founded SurrealDB, with the aim of building the ultimate cloud database for tomorrow's applications. He has experience in a wide range of different software stacks and development languages, with a focus on distributed databases, and highly-available architectures.

Martin Schaer - SurrealDB, Solutions Engineer Martin is a computer science engineer working at SurrealDB and his GenAI startup. He recently worked in lab automation, where he designed and developed a declarative framework for instrument drivers and a 3D visualiser for testing robotic transport solutions. His background also includes founding a successful advertising agency in Costa Rica and extensive work in web development, UX, branding, and digital marketing.

Stream #35: Production-grade AI agents with SurrealDB & Pydantic AI

Explore the practical challenges of taking Graph-RAG agents from experiment to production with SurrealDB and PydanticAI. Unlike simple RAGs, these agents need durable, queryable memory, checked rules for agent requests and responses, and observability that surfaces retrieval and validation drift. In this session SurrealDB and PydanticAI show a compact, reproducible pattern - build a KG, run a typed pai-memory agent via the Gateway, and use Logfire/OTel to trace and diagnose failures.

About SurrealDB Stream SurrealDB Stream is our ongoing developer-focused livestream series on building AI-ready applications with SurrealDB, featuring hands-on demos, code examples and fireside discussions. Explore our past episodes here: https://www.youtube.com/playlist?list=PLvuQflRR4UzblK6jpMoFE_MuJ8JZ2e14_

About the speakers

Samuel Colvin - Pydantic, CEO & Founder Samuel Colvin is a Python and Rust developer and creator of Pydantic. The Pydantic library, which he created is downloaded over 300M/month and is a dependency of many GenAI Python libraries including the OpenAI SDK, the Anthropic SDK, Langchain, AutoGPT, instructor and LlamaIndex.

Tobie Morgan Hitchcock - SurrealDB, CEO & co-founder Tobie Morgan Hitchcock is CEO & Co-Founder of SurrealDB. He is an experienced tech entrepreneur, developer, and software engineer, with 17 years’ experience in the software and cloud-computing industries. In 2021 he founded SurrealDB, with the aim of building the ultimate cloud database for tomorrow's applications. He has experience in a wide range of different software stacks and development languages, with a focus on distributed databases, and highly-available architectures.

Martin Schaer - SurrealDB, Solutions Engineer Martin is a computer science engineer working at SurrealDB and his GenAI startup. He recently worked in lab automation, where he designed and developed a declarative framework for instrument drivers and a 3D visualiser for testing robotic transport solutions. His background also includes founding a successful advertising agency in Costa Rica and extensive work in web development, UX, branding, and digital marketing.

Stream #35: Production-grade AI agents with SurrealDB & Pydantic AI

Explore the practical challenges of taking Graph-RAG agents from experiment to production with SurrealDB and PydanticAI. Unlike simple RAGs, these agents need durable, queryable memory, checked rules for agent requests and responses, and observability that surfaces retrieval and validation drift. In this session SurrealDB and PydanticAI show a compact, reproducible pattern - build a KG, run a typed pai-memory agent via the Gateway, and use Logfire/OTel to trace and diagnose failures.

About SurrealDB Stream SurrealDB Stream is our ongoing developer-focused livestream series on building AI-ready applications with SurrealDB, featuring hands-on demos, code examples and fireside discussions. Explore our past episodes here: https://www.youtube.com/playlist?list=PLvuQflRR4UzblK6jpMoFE_MuJ8JZ2e14_

About the speakers

Samuel Colvin - Pydantic, CEO & Founder Samuel Colvin is a Python and Rust developer and creator of Pydantic. The Pydantic library, which he created is downloaded over 300M/month and is a dependency of many GenAI Python libraries including the OpenAI SDK, the Anthropic SDK, Langchain, AutoGPT, instructor and LlamaIndex.

Tobie Morgan Hitchcock - SurrealDB, CEO & co-founder Tobie Morgan Hitchcock is CEO & Co-Founder of SurrealDB. He is an experienced tech entrepreneur, developer, and software engineer, with 17 years’ experience in the software and cloud-computing industries. In 2021 he founded SurrealDB, with the aim of building the ultimate cloud database for tomorrow's applications. He has experience in a wide range of different software stacks and development languages, with a focus on distributed databases, and highly-available architectures.

Martin Schaer - SurrealDB, Solutions Engineer Martin is a computer science engineer working at SurrealDB and his GenAI startup. He recently worked in lab automation, where he designed and developed a declarative framework for instrument drivers and a 3D visualiser for testing robotic transport solutions. His background also includes founding a successful advertising agency in Costa Rica and extensive work in web development, UX, branding, and digital marketing.

Stream #35: Production-grade AI agents with SurrealDB & Pydantic AI

Explore the practical challenges of taking Graph-RAG agents from experiment to production with SurrealDB and PydanticAI. Unlike simple RAGs, these agents need durable, queryable memory, checked rules for agent requests and responses, and observability that surfaces retrieval and validation drift. In this session SurrealDB and PydanticAI show a compact, reproducible pattern - build a KG, run a typed pai-memory agent via the Gateway, and use Logfire/OTel to trace and diagnose failures.

About SurrealDB Stream SurrealDB Stream is our ongoing developer-focused livestream series on building AI-ready applications with SurrealDB, featuring hands-on demos, code examples and fireside discussions. Explore our past episodes here: https://www.youtube.com/playlist?list=PLvuQflRR4UzblK6jpMoFE_MuJ8JZ2e14_

About the speakers

Samuel Colvin - Pydantic, CEO & Founder Samuel Colvin is a Python and Rust developer and creator of Pydantic. The Pydantic library, which he created is downloaded over 300M/month and is a dependency of many GenAI Python libraries including the OpenAI SDK, the Anthropic SDK, Langchain, AutoGPT, instructor and LlamaIndex.

Tobie Morgan Hitchcock - SurrealDB, CEO & co-founder Tobie Morgan Hitchcock is CEO & Co-Founder of SurrealDB. He is an experienced tech entrepreneur, developer, and software engineer, with 17 years’ experience in the software and cloud-computing industries. In 2021 he founded SurrealDB, with the aim of building the ultimate cloud database for tomorrow's applications. He has experience in a wide range of different software stacks and development languages, with a focus on distributed databases, and highly-available architectures.

Martin Schaer - SurrealDB, Solutions Engineer Martin is a computer science engineer working at SurrealDB and his GenAI startup. He recently worked in lab automation, where he designed and developed a declarative framework for instrument drivers and a 3D visualiser for testing robotic transport solutions. His background also includes founding a successful advertising agency in Costa Rica and extensive work in web development, UX, branding, and digital marketing.

full schedule here: https://ai.engineer/schedule

thanks @yashgargk for timestamps:

0:00:00 - start 0:15:15 - Welcome to AI Engineer - Laurie Voss (LlamaIndex) 0:22:17 - Designing AI-Intensive Applications - Shawn Wang (Latent Space) 0:35:46 - Spark to System: Building the Open Agentic Web - Asha Sharma (Microsoft) 0:59:02 - State of Startups and AI 2025 - Sarah Guo (Conviction) 1:24:44 - 2025 in LLMs so far - Simon Willison (Datasette) 1:43:20 - Agentic GraphRAG - Stephen Chin (Neo4j), Andreas Kollegger (Neo4j) 1:47:58 - Track Intros - Laurie Voss (LlamaIndex) 1:51:00 - Break 2:29:26 - MCP Track Intro - Henry Mao (Smithery) 2:31:16 - MCP Origins & RFS - Theodora Chu (Anthropic) 2:49:47 - What we learned from shipping remote MCP support at Anthropic - John Welsh (Anthropic) 3:03:51 - Full Spectrum MCP: Uncovering Hidden Servers and Clients Capabilities - Harald Kirschner (VS Code, Microsoft) 3:18:54 - MCP isn’t good, yet - David Cramer (Sentry) 3:36:34 - Break 5:08:05 - MCP is all you need - Samuel Colvin (Pydantic) 5:25:43 - Observable tools - the state of MCP observability - Alex Volkov (Weights & Biases), Benjamin Eckel (Dylibso) 5:43:00 - The rise of the agentic economy on the shoulders of MCP - Jan Curn (Apify) 6:02:05 - Break 7:08:00 - Buffer 7:09:28 - Closing thoughts on Agentic GraphRAG + Demo - Stephen Chin (Neo4j), Andreas Kollegger (Neo4j) 7:15:22 - Building Agents at Cloud-Scale - Antje Barth (AWS) 7:34:26 - Windsurf everywhere, doing everything, all at once - Kevin Hou (Windsurf) 7:50:31 - Buffer 7:51:30 - #define AI Engineer - Greg Brockman (OpenAI), Shawn Wang (Latent Space)

September edition! We will be at Kraken Tech (Octopus Energy Group) London office!

Talks:

Empowering Django with Background Workers by Jake Howard

There's a lot more to a web application than just the request/response cycle. Running tasks in the background, whether on a trigger or schedule unlocks a lot of extra functionality, performance and reliability. Whilst Django is a web framework, it doesn't have a good first-party story for background workers right now. When most people think of background workers, they lean immediately to Celery, but other tools are out there which might be better and easier to work with. The lack of first-party support results in diverging implementations, added complexity for developers, and a learning cliff for new developers. If Django had a first-party solution, it could help unify these implementations, and make Django more "batteries included". The lack of first-party support is also a challenge to Wagtail, where many potentially intensive tasks have to be run in the request/response cycle, slowing down user actions.

Pydantic Logfire — Uncomplicated Observability by Samuel Colvin

From the team behind Pydantic, Logfire is a new type of observability platform built on the same belief as our open-source library — that the most powerful tools can be easy to use.

In this talk we'll introduce Logfire, then demonstrate how it can make understanding and fixing your app faster and more enjoyable with a live demo. We'll touch on some of the most useful integrations including: Django, Postgres and OpenAI.

I'm also happy to take any questions on Pydantic the library, or the experience of starting a company around open source.

-------- To propose a talk for our events, fill in our speaker form.

Agenda: • 6:15pm Doors open, socialising • 6:30pm Food and drinks offered by our sponsor • 7:00pm Doors close ** • 7:15pm Introduction, News, Talks • 8:30pm Socialising • 9:30pm Fin ** Please make sure to arrive between 6:15 PM and 6:55 PM. If you arrive earlier than 6:15 PM or later than 6:55 PM, you can take a seat in the seating area located in the downstairs reception. Please note that we cannot accommodate arrivals after 7:15 PM. Our meetups are governed by a Code of Conduct. Please take a few minutes to read it. This meetup is sponsored by: • Kraken Tech (Octopus Energy Group): "Kraken is a revolutionary energy tech platform built with predominantly Python & Django. We Serve 54 million households worldwide and have 38GW of contracted capacity." • JetBrains: "We make professional software development a more productive and enjoyable experience." Website: https://djangolondon.com Twitter: twitter.com/djangolondon Github: github.com/djangolondon Open Collective: opencollective.com/the-london-django-meetup-group