Welcome to the AI meetup in London, in collaboration with Snowflake. Join us for deep dive tech talks on AI, GenAI, LLMs and Agents, hands-on experiences on code labs, workshops, and networking with speakers and fellow developers.

Agenda:
* 6:00pm~6:30pm: Checkin and Networking
* 6:30pm~6:45pm: Welcome/community update
* 6:45pm~8:30pm: Tech talks and Q&A
* 8:30pm~9:30pm: Open discussion & Mixer

Tech Talk: Optimize your Agent's GPA with Coding Agents
Speaker: Kris Jenkins (Snowflake)
Abstract: In this talk, we will share how coding agents help developers build high quality agents faster.
A key insight from building agents in production is that high quality agents operate with their goals, plans and actions aligned. We introduce the Agent Goal-Plan-Action or Agent GPA framework to capture this insight, which achieved state of the art benchmarks on TRAIL/GAIA with 95% error coverage and 86% error localization.
This framework goes beyond examining the agent's final results to assessing the agent's process: Was the goal achieved efficiently? Did the plan make sense? Were the right tools used? Did the agent follow through? Without visibility into these steps, teams risk deploying agents that look reliable but create hidden costs in production. Inaccuracies can waste compute, inflate latency and lead to the wrong business decisions, all of which erode trust at scale.
This approach to agent evaluation enables effective and fast optimization with coding agents. We will also show how to use coding agents to automate the process of measuring and improving an Agent's GPA by using agent optimization skills that take advantage of the GPA evaluation framework.
By the end, attendees will be able to use coding agents and the GPA framework to identify common agent failures, improve their agent and make it ready for production.

Tech Talk: Optimising RAG Pipelines for Voice AI
Speaker: Gaurang Torvekar (Kytona)
Abstract: In this talk, Gaurang will share his journey of building open-source AI agents and dev tools with RAG pipelines. Everyone building AI agents reaches for the same playbook: chunk your docs, embed them, store them in a vector database. He started with the same assumptions, building a production voice RAG pipeline with Qdrant, hybrid retrieval, and markdown-aware chunking for ElevenLabs voice agents. It worked, but embedding large docs was painfully slow, token overhead was brutal, and the simplest component, BM25 keyword search, was quietly outperforming the expensive vector embeddings on every documentation query.
In this talk, he'll walk through what he built, why he ripped it out, and what he replaced it with: a SQLite-based approach that's faster, simpler, and cuts documentation token overhead by 60-90%. If you're building agents that need to reference docs, you might not need that vector database.

Speakers/Topics:
Stay tuned as we are updating speakers and schedules.
If you have a keen interest in speaking to our community, we invite you to submit topics for consideration: Submit Topics

Venue:
Snowflake, 3 Crown Pl, London EC2A 4EB, United Kingdom.

Sponsors:
We are actively seeking sponsors to support AI developers community.  Whether it is by offering venue spaces, providing food, or cash sponsorship. Sponsors will not only speak at the meetups, receive prominent recognition, but also gain exposure to our extensive membership base of 20,000+ AI developers in London and 500K+ worldwide.

Local and Global AI Community on Discord
Join us on discord for local and global AI tech community:
- Events chat: chat and connect with speakers and global and local attendees;
- Learning AI: events, learning materials, study groups;
- Startups: innovation, projects collaborations, founders/co-founders;
- Jobs and Careers: job openings, post resumes, hiring managers;