AI Power Pause
Kuukauden paras 30 minuuttia tekoälylle!
Tervetuloa mukaan AI Finlandin AI Power Pause -koulutuskahvihetkeen – uuteen kuukausittaiseen webinaarisarjaan, jossa tarjoamme tiiviin puolituntisen tekoälyn ajankohtaisimmista teknisistä teemoista. Syyskuun session hostaa kumppanimme Brillian, puhujina Samuel Rönnqvist, Lead AI Architect, & Jussi Järvinen, CEO & Co-founder. Englanninkielisen tapahtuman kuvaus:
How to trust LLMs in production
Unlike traditional software, LLMs don’t break loudly. Ensuring your LLM features act like your users intend, you need to constantly monitor and evaluate their output. LLM evaluation is more nuanced than traditional QA testing: it requires judgment about what good looks like and incorporates that into a systematic process.
In this 30-minute online session, Samuel Rönnqvist, Lead AI Architect, and Jussi Järvinen, CEO & Co-founder, from Brillian explore how to evaluate LLM quality over time.
We’ll cover
- How to judge when an AI application is ready to ship
- Why LLMs require a fundamentally different approach to quality assurance than traditional software
- How to define what ”good” output looks like for your use case
- Building a systematic, repeatable process for evaluating LLM output
- How continuous monitoring keeps LLM features aligned with user intent over time
Who is it for? For technology and data experts as well as developers, product leads, and decision-makers who build or oversee AI-driven features and need confidence in their reliability.