Obsidian Metadata
| type | reading-path |
| source | https://hamel.dev/notes/llm/evals/start/new-to-evals/index.html |
Reading Path: I’m New to Evals
“I’ve heard the term, but I’m not sure what evals involve or whether I need them.”
- Source - Your AI Product Needs Evals → Three Levels of Evaluation, Rechat Lucy
- Video: Teresa Torres, From Noob to Automated Evals In A Week (as a PM) (Video Library)
Getting started: Product Evals vs Model Benchmarks · Minimum Viable Eval Setup · Traces · Error Analysis · When to Build an Automated Evaluator
Working with your team: Internal Eval Platforms · Team Collaboration on Evals · Making the Case for Evals
Planning the investment: Budget reality · Will this still matter in 5–10 years?
Then: the Eval Playbook.