Evals London

Evaluating AI applications, not just models.

A London meetup and community for people who build AI-powered products. Model benchmarks on leaderboards are interesting, but how do you evaluate your specific RAG pipeline in production?

What we tackle

🔍

RAG system quality

Evaluating retrieval quality and end-to-end RAG pipelines in production

⚠️

Production regressions

How to catch and fix problems in deployed AI systems

👥

Human-in-the-loop

Evaluation approaches that combine human expertise with automation

⚙️

Development lifecycle

Integrating evals into development and CI/CD pipelines

Who it's for

ML/AI engineers

You deploy and monitor models in production

Backend developers

You integrate LLMs or RAG into an existing product

Data scientists

You measure and improve the performance of AI systems

Product managers

You need to understand the quality of AI features

AI researchers

You study the reliability and safety of AI

Beginners welcome

Practical interest and curiosity are all you need

Meetup format

LocationLondon — venue TBA
WhenOctober 2026 — date TBA
Format1–3 short talks + discussion
LanguageEnglish
"What broke in production and how we fixed it"— no sales pitches

Partners

[ TBA ]

Venue hosts & sponsors — coming soon.

Want to host the first London meetup or sponsor the night? A room for ~50 people, a projector and some pizza go a long way.

Partner with us

Coming soon

In the works

Speakers, date & venue

The first London line-up is being put together right now. Get on the list and you'll be the first to know when tickets open.

Oct 2026London[ TBA ]
Get notified
A taster

What we'll dig into

  • Error analysis & failure taxonomies
  • Assertion-based evaluation
  • LLM-as-Judge frameworks
  • RAG-specific metrics
  • Evaluating agents & tool use
  • Human evaluation & annotation design
  • Wiring evals into CI/CD