Home Portfolio Resume AI Contact
← BACK TO AI NOTES · PROMPTS
PROMPT · LEARNING

Learn any topic, fast

My default when I need to genuinely understand something new — evals, WhatsApp Business APIs, pricing models — not skim it. Asking for a textbook chapter instead of "explain X" forces depth, structure, and progression. Replace [topic] with yours.

The prompt

"Teach me [topic] from first principles. Structure it as a 30-page PDF: start with fundamentals, build up to advanced concepts, include examples and diagrams where useful, and end with a summary and further reading. Write it like a textbook chapter, not a listicle."

Why it works

  • "From first principles" stops the model from assuming background you don't have.
  • "30-page PDF" and "textbook chapter" set the depth and the shape — you get progression, not a bullet dump.
  • "Summary and further reading" gives you a review loop and the next step, like a real course would.

Example result

Condensed sample with [topic] = "evals for AI products" — the real output runs chapter-length:

EVALS FOR AI PRODUCTS — A FIELD GUIDE

1 · Fundamentals. An eval is a repeatable test of model output quality. Where unit tests check code paths, evals check judgment: given this input, is this output acceptable? …
2 · Why traditional QA breaks. The same prompt can produce different outputs; pass/fail becomes a distribution, not a boolean. …
3 · Types of evals. Golden sets, LLM-as-judge, human review panels, A/B in production — with the failure modes of each. …
4 · Building your first eval set. Start from real user transcripts, not imagined cases; 50 well-chosen examples beat 5,000 synthetic ones. …
5 · Advanced: regression gates. Wiring evals into release so a prompt change that hurts quality blocks the ship. …
Summary. Evals are the PM's spec, expressed as tests. Further reading:

SAMPLE OUTPUT · CONDENSED FOR SPACE

tipAsk follow-ups chapter by chapter tipEnd with "quiz me on this"