Skip to content
Skip to the lesson
← RoadmapDay 80 of 90Agents & Prod AI2h 25m

Workflow or agent, and when an agent is wrong

By the end of today you can decide whether a task needs a model deciding each step or a fixed sequence with model calls inside it, and defend the choice on testability, cost and failure behaviour.

YesterdayOn Day 79 you built the loop and saw what it costs. Today you ask whether you needed it.

TomorrowTomorrow, what an agent must remember between turns and between sessions.

01

Why this matters

Agents are the default answer to everything right now, and they are the wrong answer surprisingly often. Knowing when a workflow beats an agent is the most valuable judgment in this phase.

  • Workflow or agent
  • What agency costs
  • Determinism as a feature
  • Deciding on agency
02

Learn it

70 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.

4 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

Take the agent you built yesterday and rewrite it as a workflow with a fixed sequence. Run both on the same ten inputs and record token cost, latency and correctness for each. Then write a paragraph on which you would ship and why, including what the workflow cannot handle.

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

  • 01Workflow means you control the sequence; agent means the model does
  • 02Agency costs predictability, testability and debuggability
  • 03If you can write the steps down, write them down
  • 04Start with a workflow and add agency only where the path is genuinely open

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.