All sessions
AI EngineeringWorkshop (120 min)
Evals Are Your Only Moat: Building Test Suites for LLM Products
Tom Achebe, Hana Sato
- When
- Wednesday, September 1610:30 AM – 12:30 PM · 120 min
- Where
- Workshop LabFort Mason Center, San Francisco
About this session
Model upgrades break prompts silently. In this hands-on workshop you will build an eval pipeline from scratch: rubric design, failure taxonomies, CI wiring, and the regression report that doubles as your product spec. Bring a laptop.
Speakers (2)
Tom Achebe
CTO, Forgeline
Tom co-founded Forgeline after leading platform engineering at two payments companies. He is the reason Forgeline had an evaluation suite before it had a marketing site.
Hana Sato
Research Engineer, Aperture AI
Hana works on small-model distillation and spends most of her week reading evaluation traces. She was a computational linguist before that and it shows in her error taxonomies.
More in AI Engineering
- Test Data Is a Product: Fixtures for Nondeterministic SystemsTime to be announced
- Context Engineering in Production: What Actually Survives Contact With UsersTuesday, September 15 · 9:45 AM – 10:30 AM · Room 2A
- Your AI Pair Programmer Is Lying to You: Verification Patterns That ScaleTuesday, September 15 · 10:30 AM – 11:00 AM · Main Stage
- Multi-Agent Systems Are Just Distributed Systems (And That's Good News)Tuesday, September 15 · 11:15 AM – 11:45 AM · Main Stage
- Prompt Injection Is a Solved Problem (If You Do These Five Things)Tuesday, September 15 · 1:15 PM – 1:45 PM · Main Stage
For developers: this programme is open data — JSON, iCal, schedule XML and an MCP endpoint.Show endpointsHide
- JSONEvery published session and speaker, in one request./ai-builders-summit-2026/feed.json
- iCalSubscribe in Google, Apple or Outlook Calendar./ai-builders-summit-2026/feed.ics
- Schedule XMLfrab / pentabarf — the format conference apps import./ai-builders-summit-2026/feed.xml
- MCP + RESTPoint Claude at the programme. OpenAPI 3.1 included./agents
No key, no signup, CORS open. Everything here is generated from the same data the organisers edit.