Dance break PYai ! PERSES AT GOTCHAPOP4 #GOTCHAPOP4xPERSES #NAY_PERSES #JUNG_PERSES #PERSES_TH

Thanks Samuel! Really enjoyed our episode we filmed back in September and enjoyed chatting about Monty at PyAI Conf earlier this year.

pyai! pyai! (ぴゃい! ぴゃい〜!) ※感動詞　一人称単数

Saw you from afar at @pydantic PyAI but we never got to say "hi" face to face 🥲

"95% of GenAI pilots show no measurable P&L impact. Not because the models aren't capable. Because the infrastructure layer hasn't caught up." @htahir111 talk from ZenML at PyAI is now live on Youtube. youtu.be/2WJQRcAuH40

The recording from @pydantic 's PyAI event is live now! What's new in FastAPI for AI 😎 I presented (among other things) the first idea of Library Skills and how FastAPI already bundles them, there's now a CLI to install them: library-skills.io uvx library-skills

Pablo Galindo Salgado and David Hewitt's PyAI London talk is now on YouTube: "Maintaining OS in the age of AI" What open source stewardship looks like now that AI is in the picture? A humorous rant and some hard questions about sustainability, contribution, and trust in open source, now that AI is in the picture. 👉youtu.be/4J-YZ-IMcJU

@marlene_zw PyAI London talk is on YouTube. "A practical guide to agentic coding" — MCP, Pydantic AI, GitHub Copilot, and agents that actually complete tasks end-to-end. youtu.be/7wGB_59ZDD4

@shifra_dev's PyAI London talk is on YouTube. "What your AI pipeline does when you're not looking" A live demo of a RAG pipeline with Pydantic AI, Logfire, and Render. Full observability, self-correcting loops, SQL-queryable telemetry. youtu.be/KaQNo3BSfZM

"There is a dopamine hit you get when you see your sub flow fan out into a bunch of things and then come together at the end." Nithin Krishnamurthi | @shywalla , Software Engineer at @SnorkelAI, walks through how they replaced a tangled mess of Redis queues with Prefect as their chief orchestrator. His PyAI Conf 2026 talk covers the custom worker architecture that brought observability and sanity to a wildly diverse compute stack spanning on-prem model training, RL evals, and 24-hour packaging scripts. Full talk here: youtube.com/watch?v=y09YK1xh…

@samuelcolvin's PyAI London talk is on YouTube. "Controlling the wild: from tool calling to computer use" youtu.be/UQ73L5WcDD4

Was a pleasure to speak at PyAI conf last march! The talk is now up - take a peek inside @AirbyteHQ's connector factory!

"What good would an integration platform be if we don't connect to all those different places where your data is at?" @pedroslopez, Software Engineer at @AirbyteHQ, breaks down how his team built an automated connector factory: an AI-powered assembly line that builds and maintains 600 data connectors at scale. His PyAI Conf 2026 talk covers their three phases (discovery, build-and-test, acceptance), hard-won lessons on why verification layers matter more than the agent itself, and what happened when they tried handing it all to Claude Code and hoping for the best. Full talk here: youtube.com/watch?v=_CDb0ZeY…

A lightning talk from @VstormCommunity : @antonikozelski, CEO and Co-founder, has shipped 30 production agent solutions across industries. In his PyAI Conf 2026 talk, he walks through three open source tools Vstorm is releasing back to the community, including a @pydantic Logfire AI assistant that lets anyone (even non-technical folks) interrogate their agent systems through natural language in a Chrome extension. 📺 Full talk here: youtube.com/watch?v=GBpOsV0W…

"Why are we still creating feature pipelines by hand?" Chang She @changhiskhan, CEO and Co-founder of @lancedb and original co-author of the pandas project, sees a world where software engineers have stopped writing most of their code manually but data teams are still debugging distributed pipeline failures at 2 AM and watching their OpenAI bills spike over the weekend. In his PyAI Conf 2026 talk, Chang breaks down the ten biggest pain points of feature engineering for AI and makes the case that our data infrastructure was built for the last generation. Full talk here: youtube.com/watch?v=dv4vZQ4K…

Absolute gentleman and most handsome of actors. Also very punctual on sets as well and worked without ego. Terrific dancer as well. Check out Kehne ki yehi baat from Pyai kiya jaa back in 1960s. Obviously some great movies with AB in 70s like Deewar/Trishul.

"Unlike code, data is non-local by default. If you change something, there's a bunch of production systems that depend on what you change. And unfortunately, we do not have git." @GreCo_CiRo, Co-founder and CEO at @Bauplan_labs, explains why AI coding assistants hit a wall when they try to touch production data and what to do about it. Every pipeline run is an isolated branch, merges are atomic, and failed runs never reach production. His PyAI Conf 2026 talk includes a live demo of an AI agent building and deploying a data pipeline with full git-like version control for your data lake. 📺 Full talk here: youtu.be/WnqvGcO2-nA

"If someone hands you a Jupyter notebook, you might die a little inside if they said, get this in production." @DylanMadisetti, Software Engineer at @marimo_io, at PyAI Conf 2026. Dylan shows why Python notebooks don't have to be a production nightmare. marimo builds a compute graph behind every notebook, eliminates hidden state, enables reactive widgets, and stores everything as pure Python you can lint, test, and import like any other module. Full talk here: youtu.be/xDY3APX9qp8

"If you actually go put an agent in front of a consumer, if they don't see something happening in literally two seconds, most of them will just navigate away and do something else." Bradley Axen, Tech Lead for AI at @Square and maintainer of @goose_oss, breaks down the three architectural patterns that actually matter when building with MCP, skills, and MCP Apps: progressive disclosure, output optimization, and human-in-the-loop done right. His PyAI Conf 2026 talk includes a live demo of Goose ordering a Uji Matcha Latte from a real Square MCP server. Full talk here: youtube.com/watch?v=2RrF8kK5…