LangWatch x Altura: Does your AI actually work?

​Join us for "Does your AI actually work?", part of Amsterdam Tech Week 2026

​Panel Discussion — Co-hosted by Altura & LangWatch

​A Builder's Guide to LLM Evals in Production

​Building with LLMs feels different from regular software — and not just because of the hype. In this talk, Altura walks through their real journey: from simple document summarization to answering questions over docs, to full LLM workflows embedded in their product. And the hard-won lesson that eventually hits every team: how do you actually know this stuff works in production?

​We'll get honest about when the need for evals hits, why you're better off starting earlier than you think, and how good evaluation practices improve developer experience along the way.

​Then LangWatch picks up the thread, breaking down what evals are, what to measure, and how to go from zero to a working eval setup without overcomplicating it.

​You'll leave with:

• ​A clear mental model of how AI development differs from traditional software

• ​Practical lessons from a real LLM implementation timeline

• ​A concrete starting point for evals in your own product

​🎤 Speakers

​We'll kick off the night with a talk with Martijn Schouten and Rogério Chaves.

Followed by a panel on context engineering in practice with:
→ Maggie Konstanty (AI PM & Evaluation @ Prosus)
→ Nilay Aishwarya (AI/ML Engineer @ Deeploy)
→ Maxim Svyatov (AI Task Force Officer @ Loyens & Loeff)
→ Ron Kremer (Senior AI Consultant @ ADC & PHD in AI)

​📍 Join us at 5:30 PM at the Altura office

See the full AMS Tech Week calendar.