Prompting and context engineering
By the end of today you can write a prompt that specifies what you actually want, and you can debug a bad output by finding what the prompt failed to make explicit rather than by adding emphasis.
YesterdayOn Day 69 you sent a request. Today you learn what to put in it.
TomorrowTomorrow you constrain the output shape so code can rely on it.
Why this matters
Prompting is treated as folklore and taught as tricks. Most of it is ordinary specification: saying precisely what you want, to whom, in what form, with what excluded.
- Prompts as specification
- Context engineering
- Examples in prompts
- Debugging a prompt
Learn it
70 minCopy this into Claude or ChatGPT. It quizzes you before it explains anything, which is deliberate. The resources under it are how you check what it told you.
Today's Master Prompt
Free · sign inA prompt written for this day alone: your level, the exact scope, what to leave out, and an instruction to quiz you before it explains anything. Paste it into Claude or ChatGPT and it teaches you today's material.
Check it against something that is not a model
An assistant can be fluent and wrong, and on a topic you met today you will not catch it. These cover the same ground and were made by people who do this for a living, so they are what you hold the explanation up against. They are other people's work and we only link to them, so judge them for yourself.
4 hand-picked resources
Free · sign inVideos, official docs and articles covering the same ground, each opened and annotated by hand. They are what you check the assistant against on a day you cannot yet catch it being wrong.
Build it
45 minTake a task you would genuinely use a model for. Write a deliberately vague prompt and record the output. Then iterate four times, each time naming the specific thing the previous version failed to specify, and record every version and output. Finally, write one sentence on which change made the biggest difference and why.
Recall it
25 minAnswer out loud, reveal, then mark honestly whether you had it. That score is the only thing on this page you do not get to choose.
5 recall questions
Free · sign inQuestions you answer from memory, then grade yourself against the real answer. The score is carried into the mastery rating below it, so an honest miss cannot quietly become a tick.
Rate it
Completion and mastery are tracked separately. Be honest, because an inflated rating only means the concept resurfaces sooner.
Mastery tracking
Free · sign inRate yourself against five named criteria per concept. Completion and mastery are tracked separately, and anything you rate shakily comes back automatically on a spaced schedule.
Recap
- 01A prompt is a specification, and most bad output is an under-specified one
- 02Context engineering is deciding what the model needs and supplying it
- 03Examples transmit length and tone as well as pattern
- 04Prompts are code: version them, review them, test them
Your progress
Free · sign inMark days complete, pick up where you left off across devices, and watch completion and mastery diverge. Free, and the account exists only so ninety days of work cannot vanish with a cleared browser.