Structured outputs and schema validation
By the end of today you can make a model return data your code can rely on, and you can explain why a schema constraint at the API level is not a substitute for validating what arrives.
YesterdayOn Day 37 you learned that data crossing a trust boundary must be validated. A model response is exactly such a boundary, and a probabilistic one.
TomorrowTomorrow, streaming, and what it costs you to display an answer as it arrives.
Why this matters
The moment a model's output feeds code rather than a human, its shape becomes an API contract. Parsing prose with regex is where most fragile AI features break.
- Structured outputs
- Validating model output
- Output as a contract
- The model as a trust boundary
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.
3 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
50 minBuild an extraction task twice. First ask for JSON in the prompt and run it twenty times on varied input, counting parse failures. Then do it with a real schema constraint and run it again. Finally, add validation that checks a business rule the schema cannot express, and find a response that passes the schema and fails your rule.
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
- 01Asking for JSON in the prompt works often enough to be dangerous
- 02A schema constrains the shape and says nothing about the content
- 03Model output is untrusted data from a probabilistic source
- 04The same discipline returns as tool arguments on Day 78
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.