I Built a Dual-Pool Adversarial Review System for AI Agents — And It Actually Works

AI code review has a problem: abstract roles produce generic feedback. "Saboteur" says "add error...

sabato 27 giugno 2026 New tab

444 words~2 min read

AI code review has a problem: abstract roles produce generic feedback. "Saboteur" says "add error handling." "New Hire" says "this is confusing." Useful? Sometimes. Specific? Rarely.

I built something different: a review system that uses real engineers with searchable philosophies instead of abstract roles. Linus Torvalds doesn't say "consider error handling" — he says "eliminate the special case entirely." That's not a wording difference. That's a completely different action.

The Core Idea: Two Pools, Cross-Orchestrated

Fixed Pool (Convergence) Random Pool (Divergence)

Digital-twin matched Web-searched fresh each time

I Built a Dual-Pool Adversarial Review System for AI Agents — And It Actually Works

I Built a Dual-Pool Adversarial Review System for AI Agents — And It Actually Works

Related reading

Tenure — Building an AI Code Reviewer That Earns Trust Over Time

I Reviewed 200+ AI-Generated PRs. Here's the 4-Round Protocol I Use Now.

I Let 24 Famous Engineers Review My Methodology. Here's What Happened.

I Tried to Build an AI Code Reviewer Without Sharing My Code — Here's What…

I built a multi-agent loop where an adversarial Claude reviewer reads your…

I Can't Tell If the Model Matters

Related reading

Tenure — Building an AI Code Reviewer That Earns Trust Over Time

I Reviewed 200+ AI-Generated PRs. Here's the 4-Round Protocol I Use Now.

I Let 24 Famous Engineers Review My Methodology. Here's What Happened.

I Tried to Build an AI Code Reviewer Without Sharing My Code — Here's What…

I built a multi-agent loop where an adversarial Claude reviewer reads your…

I Can't Tell If the Model Matters