← Back to the homepage

For speakers

Edition #2 · February–March 2027 · Date and venue to be confirmed

Edition #2

The next Evals London is planned for February or March 2027. The shape of the evening depends on who signs up: one or two talks, maybe discussion tables, maybe not. Pitch whatever fits what you have to share.

Option AGive a talkEdition #2 will have one or two talks. We agree the length with you once the line-up takes shape. Live demos are welcome but not required.
Option BLead a discussion tableIf the evening has tables: 15–20 people around one topic. You open with a few minutes on how you approach the problem, then the group works through its own cases. No slides.
Option CNot sure yetTell us what you want to share and we'll work out the format together.

Everything is in English. For reference, edition #1 (11 November 2026): a keynote from Samuel Colvin, then six discussion tables.

Who's in the room

Mostly engineers shipping LLM products, plus product people and researchers. Pitch it at people who build these systems day to day.

House rules

  • Talk about systems you've worked on yourself.
  • Share real numbers, including the embarrassing ones.
  • No sales pitches, from the stage or at the tables.

Mention where you work and what you build, but keep the focus on what you learned: what broke in production and how you fixed it.

Topics we'd love to hear

As a talk or as a table.

01

Case study

How you evaluate a specific RAG system, agent or LLM feature in your product: the metrics, the pipeline, and the hardest problems you hit.

02

Tooling deep dive

Frameworks, internal tools or infrastructure for evaluating, testing, monitoring or logging AI systems, and how you wired them into CI/CD.

03

Research & experiments

Papers, internal reports or experiments with practical consequences for people building production systems.

04

Open problems

Where current tools fall short: evaluating without ground truth, measuring hallucinations, judging agent behaviour. You don't need the answer.

Want to take part?

Send a short note and we'll get back to you. You don't need to pick a format up front. Happy to talk an idea through before you commit.

Email Šimon

simon@podhajsky.net

What to include

  • What you'd share (2–3 sentences)
  • Talk, table, or open to either
  • Why it matters for evals
  • Your background and company

Not sure your topic fits? Write anyway.

Where this comes from

Evals London is the sister meetup of Evals.cz in Prague, run by Šimon Podhajský and Veronika Pešková. Prague has held four editions since February 2026, and each one filled up with a waitlist.

Prague editions

  • #1 3 Feb 2026 at Apify
  • #2 15 Apr 2026 at Shoptet
  • #3 17 Jun 2026 at Make
  • #4 1 Oct 2026 at Truhlárna (Miton)

Watch edition #4

A joint evening with Miton AI Times: three talks, all on evals. Full recording on YouTube

  • The Weird and Wonderful World of Cybersecurity EvalsEvelina Gabašová · Watch · Slides
  • Evaluating Open Models on Your Task and in Your LanguageAntonín Hoskovec · Watch · Slides
  • Generating Synthetic Evaluation Data for Search AgentsMichal Spiegel · Watch · Slides