Skip to content
Skip to the lesson
← RoadmapDay 72 of 90AI Engineering2h 30m

Streaming, latency, fallbacks, and routing

By the end of today you can stream a response to a user, explain why streaming changes perceived speed without changing total time, and design what happens when your primary model is unavailable.

YesterdayOn Day 64 you learned server-sent events were the right tool for one-way streaming. This is the case they were built for.

TomorrowTomorrow, embeddings, and the shift from generating text to finding it.

01

Why this matters

LLM calls take seconds, not milliseconds. Everything you learned about latency, failure handling and graceful degradation now applies to a dependency that is slow by design.

  • Streaming responses
  • Time to first token
  • Fallbacks and routing
  • Caching LLM work
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

Build a streaming endpoint that proxies a model response to a browser over server-sent events. Measure time to first token and total time separately. Then kill the connection midway and handle it so the user sees something coherent. Finally, add a fallback to a second model and force the primary to fail.

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

  • 01Streaming changes perceived speed, not total time
  • 02One-way flow means server-sent events, not WebSockets
  • 03A stream that fails midway has already shown the user text
  • 04Plan what the product does when the AI feature is entirely unavailable

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.