Course · 5 chapters
Valutazione degli LLM
Build runnable LLM evals you can trust: golden datasets, deterministic scorers, calibrated LLM judges, Inspect AI suites, and CI gates. 5 chapters, advanced, for engineers.
What you'll be able to do
- Build a runnable LLM eval from scratch
- Design judge rubrics that resist bias
- Calibrate LLM judges against humans
- Run eval suites with Inspect AI
- Gate bad merges with CI evals
- Set thresholds that survive flaky judges
What's inside
- 1Valutazione LLM: parti da qui
Un orientamento di 12 minuti al percorso Valutazione LLM — il capitolo di ingresso, poi i tre strati (judge, suite, gate) che trasformano l'eval a sentimento in una disciplina che rilascia.
- 2Le basi degli eval: il tuo primo eval LLM in 30 minuti
Smetti di controllare gli output a sentimento. Costruisci un eval (valutazione) che gira davvero — golden dataset, scorer deterministico, judge LLM — e leggi il risultato da ingegnere.
- 3LLM-as-Judge: rubriche, bias e affidabilità
Progetta judge che sopravvivono ai bias CALM, calibrati contro gli umani, e che si guadagnano un posto nel tuo gate in CI.
- 4Inspect AI: suite di eval in produzione, a scala
Scrivi, esegui e visualizza suite di eval di livello frontiera con il framework open-source di UK AISI.
- 5Eval Gating in CI: bloccare i merge sbagliati
Collega gli eval per-PR a GitHub Actions, scegli soglie che reggono alla flakiness e decidi quando un gate ha senso su main.
Frequently asked questions
- What will I learn in this LLM evaluation course?
- You build evaluation across three layers: a first runnable eval with a golden dataset and scorer, reliable LLM-as-judge rubrics calibrated against human ratings, and eval suites wired into CI as a merge gate. The path uses UK AISI's open-source Inspect AI framework and GitHub Actions.
- Who is this course for?
- It is for engineers building production AI features who need to test LLM outputs rigorously instead of checking them by vibes. The level is advanced, with a focus on software engineering and AI reliability.
- Do I need to code to take this course?
- Yes. This is a hands-on engineering path that involves writing eval scripts, configuring the Inspect AI framework, and setting up GitHub Actions workflows, so comfort with code and CI is expected.
- How long is the course and is there a certificate?
- The path has 5 chapters totaling about 100 minutes, starting with a 12-minute orientation. On completion you earn an AI Academy by Anthropos certificate.
- Is this course free?
- No, this is a paid skill path included with an AI Academy by Anthropos subscription.
Earn a certificate
Complete all chapters to receive your certificate of completion.