Lesson 996 of 1455
When to Tell Claude Code or Manus to STOP and Wait for You
The 'stop and ask me' instruction is a power move — agents don't know what they don't know.
Builders · Agentic AI · ~4 min read
The big idea
Agents will guess when they're unsure. That can be useful or catastrophic depending on the guess. The fix is free: in your initial prompt, say 'if you're unsure about X, stop and ask me.' Claude Code, Manus, and Cursor Agent all respect this. It turns the agent from a runaway robot into a checkpoint-driven teammate.
Some examples
- 'If you're about to delete more than 10 lines, stop and show me the diff first.'
- 'If you can't find the file I mean, ask me — don't guess.'
- 'If a test fails after 3 fix attempts, stop and let me debug with you.'
- 'If you'd need to install a new package, ask first.'
Try it!
Next agent run, add three 'stop and ask me if' lines to your prompt. Notice how much calmer the run feels.
Key terms in this lesson
End-of-lesson quiz
Check what stuck
8 questions · Score saves to your progress.
Lesson help
Questions are best handled with a grown-up here.
For this age range, Tendril keeps freeform AI chat paused until parent/guardian consent and child-safe moderation are fully verified. Use the quiz, notes, and related lessons below, or ask a parent, guardian, teacher, or librarian to work through the question with you.
Progress saved locally in this browser. Sign in to sync across devices.
Related lessons
Keep going
Builders · 30 min
The Four Ingredients: Goal, Tools, Loop, Stop
Every agent — fancy or simple, local or cloud — boils down to four parts. Learn the recipe and you can read any agent system like a menu.
Builders · 32 min
Your First Agent: A Walkthrough of What It Does
Follow a real agent run step by step — from prompt to result — and see exactly what happens inside. No code yet, just the anatomy of a successful task.
Builders · 32 min
Tools an Agent Might Have: Filesystem, Browser, Code
Agents are only as useful as their tools. Tour the big three — filesystem, browser, code execution — plus the emerging MCP ecosystem, with examples of what each unlocks.
