Course · 5 chapters

Avaliação de LLMs

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.

Paidadvanced5 chapters100 minEnglish + 6 languagesCertificate on completion

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

  1. 1
    Avaliação de LLMs: comece aqui

    Uma orientação de 12 minutos ao skill path de avaliação de LLMs — o capítulo de entrada, depois as três camadas (judges, suites, gates) que transformam eval-por-vibes numa disciplina que entrega resultado.

    12 min
  2. 2
    Fundamentos de Evals: Sua Primeira Eval de LLM em 30 Minutos

    Pare de avaliar outputs na intuição. Monte uma eval executável — dataset golden, scorer determinístico, juiz LLM — e leia o resultado como engenheiro.

    22 min
  3. 3
    LLM-as-Judge: Rubricas, Vieses e Confiabilidade

    Projete juízes que sobrevivem aos vieses CALM, calibre contra humanos e conquiste um lugar no seu CI gate.

    22 min
  4. 4
    Inspect AI: Suítes de Eval em Produção e Escala

    Crie, execute e visualize suítes de eval de nível frontier com o framework open-source do UK AISI.

    22 min
  5. 5
    Eval Gating em CI: Bloqueando Merges Ruins

    Conecte evals por PR no GitHub Actions, defina thresholds que sobrevivem à flakiness e decida quando um gate pertence à main.

    22 min

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.