Skip to content
Hi, Bot
All lessons

Unit 7 · Lesson 3

Keep a human in the loop

Design the guardrails that make an agent safe to actually use.

~20 min

You've seen what agents can do and how they go wrong. Here's the good news: making one safe isn't about building a smarter AI. It's about deciding, up front, where you stay in charge.

That's called keeping a human in the loop — and "the human" is you. It's the same move from Unit 5, where you were the verify step in your workflow. Now we make it a rule.

The safest agent isn't the one that never makes mistakes. It's the one that can't make a big mistake without a human saying yes.

One idea: four guardrails

You don't need all four every time. You need the ones that match how much damage a wrong step could do.

GuardrailWhat it does
Ask firstThe agent must get your yes before a risky action (spend, send, delete).
Set limitsHard caps: "never spend over $10," "stop after 5 tries."
Stay reversiblePrefer actions you can undo. Draft, don't send. Move to trash, don't erase.
Show the workThe agent explains what it's about to do before it does it.

The golden rule underneath all four: the bigger and less undoable the action, the more human checking it needs. Reading your calendar? Let it run. Emptying your bank account? That needs a very awake human.

Do the thing

Design the guardrails for a real agent: "an agent that helps me manage my group project." For each power it might have, pick a guardrail:

  • It can read the project docs → ______
  • It can draft messages to teammates → ______
  • It can send those messages → ______
  • It can delete files it thinks are duplicates → ______

Quick check. Reading docs is low-risk — "let it run" is fine. Drafting is safe if it stays a draft (reversible). Sending should be "ask first" (it speaks as you, to real people). Deleting should be "ask first" and "stay reversible" (trash, not erase) — maybe both, because a wrong delete is the hardest to undo. The pattern: guardrails get stricter as actions get bigger and harder to take back.

Why this matters

You finished Unit 7. You can now think about agents the way professionals do — not "is it smart enough?" but "what is it allowed to do without me?"

  • Design the permissions, not just the prompt. Deciding what an agent can't do is the real safety work.
  • Reversible and 'ask first' beat 'trust me.' Hope is not a guardrail.

You've got agents. Next unit flips the camera around: instead of an agent doing tasks, you'll teach a model your own taste — using nothing but a handful of well-chosen examples.

Reflect & continue

One last thing.

The reflection sticks the lesson. One sentence is plenty.

Skip for now