ai-engineering
4 free lessons tagged ai-engineering across AI. Each one is a short sequence of focused steps with narration and a five-question quiz at the end — take them in any order, no signup required.
When Generating Data Beats Collecting It
Synthetic data is roughly three orders of magnitude cheaper than human annotation, and cheapness is the least interesting thing about it. This lesson establishes what generation can and cannot manufacture: it produces coverage and format, never information the generator lacks, and the one exception is verifiable domains, where a checker turns generation into search.
Evaluating AI Agents: From Final Answers to Full Trajectories
A rigorous look at how to measure agent performance — trajectory-level vs final-answer evals, canonical multi-step benchmarks (SWE-bench, WebArena, OSWorld, GAIA), LLM-as-judge pitfalls, and why your eval is your spec.
Subagents and Multi-Agent Orchestration Patterns
A practical deep-dive into fan-out, pipeline staging, judge panels, adversarial verification, and loop-until-dry — plus an honest accounting of when spawning subagents actually earns its token cost and when it just burns money.
Evaluating RAG Pipelines with RAGAS
A rigorous guide to measuring RAG quality using RAGAS metrics — faithfulness, answer relevancy, context precision, and context recall — plus how to build a golden dataset and recognize where automated metrics fall short.