Skip to content
Skip to the lesson
← RoadmapDay 82 of 90Agents & Prod AI2h 25m

Human in the loop and approval flows

By the end of today you can decide which actions require a person's approval, design an approval that a tired human will actually read, and explain why approval fatigue makes over-asking as dangerous as never asking.

YesterdayOn Day 78 you classified tools by reversibility and said the dangerous ones need approval. Today you design that properly.

TomorrowTomorrow, multiple agents, and what coordination actually costs.

01

Why this matters

Approval is the last line between a probabilistic system and an irreversible action. Designed badly it becomes a button people click reflexively, which is worse than having no gate at all.

  • Approval gates
  • Approval fatigue
  • Reversibility
  • Audit trails
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.

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

Add an approval gate to the most consequential tool in your agent. Write the approval request so someone who has not been watching can decide in ten seconds. Make the agent pause, persist its state, and resume on the answer. Then implement a denial that tells the agent why, and confirm it adapts rather than retrying the same thing.

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

  • 01Approval is for the irreversible, not for ordinary mistakes
  • 02A gate that fires constantly becomes a reflex and protects nothing
  • 03State the action, the target and the consequence, or it will not be read
  • 04Limits, dry runs and undo often beat asking a person

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.