Skip to content
Skip to the lesson
← RoadmapDay 69 of 90AI Engineering2h 30m

Calling an LLM API, end to end

By the end of today you have made real calls and can read every part of the request and response, and you can say which failures need a retry, which need a fallback, and which must never be retried.

YesterdayOn Day 55 you learned timeouts, retries with jitter and idempotency for unreliable dependencies. Today you meet the least reliable and most expensive one yet.

TomorrowTomorrow, what goes inside the request: the prompt itself.

01

Why this matters

This is where everything from Phase 5 pays off. An LLM API is a slow, expensive, occasionally failing external dependency, and you already know how to treat one of those properly.

  • Calling an LLM API
  • Message roles
  • LLM failure modes
  • Choosing a model
02

Learn it

75 min

Copy 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 in

A 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.

Sign in to continueNo card, now or later.

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 in

Videos, 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.

Sign in to continueNo card, now or later.
03

Build it

50 min

Write a small client that makes a real call and prints the content, stop reason and token usage. Add a timeout, bounded retries with exponential backoff and jitter, and distinct handling for rate limiting, overload and context-length errors. Then deliberately exceed the context window and confirm your code reports it clearly rather than crashing.

04

Recall it

25 min

Answer 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 in

Questions 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.

Sign in to continueNo card, now or later.
05

Rate it

Completion and mastery are tracked separately. Be honest, because an inflated rating only means the concept resurfaces sooner.

Mastery tracking

Free · sign in

Rate 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.

Sign in to continueNo card, now or later.
06

Recap

  • 01You maintain the conversation array; the model remembers nothing
  • 02An unread stop reason means a truncated answer looks complete
  • 03Each failure mode needs a different response: retry, fall back or fail
  • 04Model choice is a tradeoff between capability, latency and cost

Your progress

Free · sign in

Mark 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.

Sign in to continueNo card, now or later.