#evaluation

Intermediate tutorial: Use one table to see the five layers of an AI product, from compute to agents, and decide how deep to go based on your target role. Then have your AI agent coach you with scenario questions about a product you know, run a side-by-side test of two options on the same task, and turn the results into a one-page trade-off report you can take to an interview. Includes 3 copy-ready prompts.

Developer advanced tutorial: once an agent is live, you need visibility into it. Use traces and spans to record the process, monitor latency, cost, errors, user feedback and accuracy, and run automated evaluations.

A report of 600 to 1,200 words with a claims table: each claim, the sources that support it, the sources that contradict it, and a confidence note. Plus a run log of every search and read.

Before you change a prompt, a model or a tool, know whether the result got better. A small, honest evaluation set is the only way, and it takes an afternoon.