A free guide by Mariah Brunner ↗ INSTAGRAM ↗ TIKTOK
Pro Tips

Make Claude
Catch Its Mistakes

Asking AI to check its own work in the same chat is useless. The fix is a subagent. Here are the exact prompts I use, ready to copy.

When you ask the same chat that wrote something to go back and check it, it's reading its own work with the same blind spots that made the mistake in the first place. It's like proofreading your own email at midnight. You'll miss the typo every time, and it'll swear it looks perfect.

The fix is a subagent: a second instance of Claude that opens with a totally blank memory and reviews your work like a coworker seeing it for the first time. Fresh eyes catch what the first one talked itself into. Here's exactly how to use it, plus the prompts.

First What A Subagent Actually Is

Same Claude, blank slate

A Fresh Set Of Eyes

A subagent is the same Claude model, but spawned in its own separate context window with none of the original conversation. Because it can't see the reasoning that produced the work, it can't inherit the same blind spots. And don't let the name fool you, a subagent isn't less capable, it's just another agent doing one focused job.

This lives in Claude Code (Anthropic's coding tool), where you can spawn subagents on command or save your own under the /agents menu. No Claude Code? The same principle works anywhere: open a brand-new chat, paste only the work, and ask it to review cold. Either way, the magic is the clean context.

Prompt 1 The Cold Review

Your everyday move

Fresh Eyes On Anything

The one you'll reach for most. Works on a doc, an email, a plan, a caption, code, anything. Paste your work, then run this.

Copy-paste prompt

Spawn a subagent with completely fresh eyes to review the work above. It should not assume anything I said earlier is correct, or that any choice was made for a good reason. Have it tell me three things: what is actually wrong, what is missing, and what is weak or unclear. Then give me one prioritized list of fixes, ranked by how much each one improves the result. Be blunt and specific, not polite. If something is genuinely strong, say so in one line, then move on.
Prompt 2 The Devil's Advocate

Before you commit

Attack It On Purpose

Run this before any decision, pitch, or plan. It stress-tests your thinking now, so reality doesn't do it for you later.

Copy-paste prompt

Spawn a subagent whose only job is to argue against the work above. It should take the opposite side and build the strongest possible case that this idea, plan, or argument is wrong. Have it attack the weakest assumptions, the holes in the logic, and the risks I am glossing over. Push it to be the smartest critic in the room, not a cheerleader. End with the single objection I most need a good answer to before I move forward.
Prompt 3 The Fact-Checker

Trust nothing

Catch Confident Wrong Answers

AI sounds most confident right when it's wrong. Send a subagent in to verify, not to agree.

Copy-paste prompt

Spawn a subagent to fact-check the work above with a skeptical eye. Its only job is to hunt for claims that are wrong, exaggerated, unverified, or made up, including numbers, names, dates, quotes, and any "everyone knows" statement. For each one, flag it, say why it is questionable, and give me either the accurate version or exactly what I would need to check to confirm it. Assume at least one thing in here is wrong, and go find it.
Prompt 4 Your Reader's Reaction

See it through their eyes

React Like A Real Human

The fix for anything that makes sense to you but lands flat on everyone else. Just fill in who it's for.

Copy-paste prompt

Spawn a subagent that role-plays my exact audience and reacts to the work above the way that real person would. Here is who this is for: [describe your reader, customer, or boss in one line]. Have it read this cold and tell me: where it loses their attention, what confuses them, what they quietly doubt or disagree with, and the one thing that would actually make them take the action I want. Make it react like a real, slightly impatient human, not a helpful assistant trying to be nice.
Prompt 5 The Expert Panel

My favorite

Three Experts, One Verdict

Three independent opinions instead of one, and Claude picks the right experts for whatever you're working on. No echo chamber, because none of them can see each other's notes.

Copy-paste prompt

Spawn three subagents to review the work above, each in its own separate context so they cannot see each other's notes. First, you choose the three most useful expert lenses for this specific kind of work and assign one to each (for example: a sharp editor, a real subject-matter expert, a skeptical buyer, a lawyer, or a numbers person). Tell me who you picked and why. Have each expert give me their top three changes, ranked by impact. Then step back and summarize where they agree, where they disagree, and exactly what I should fix first.

One rule under all of it

Never let your AI become an echo chamber. The whole reason this works is that the reviewer can't see the reasoning that made the mistake. Heads up: every subagent uses more of your usage, so spawn a panel when it matters, not for every tiny task.

The Only AI Masterclass You Need

Build AI Systems That Run Your Work, Business, And Life

If this guide helped, but you’re looking to go deeper, I got you!! My 30-Day Challenge takes you from saving AI tips you never use to actually building with AI, step-by-step.

I show you exactly how I automated two e-commerce brands, my social media, and most of my personal life, then hand you the agents, workflows & systems to do the same. I’m teaching you every single thing I know with one lesson and one build a day.

Join the AI Masterclass →

© 2026 Mariah Brunner. All rights reserved.