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

A developer built a dual-pool adversarial review system for AI agents that uses real engineers with searchable philosophies instead of abstract roles. The system employs a fixed pool for stability and a random pool for divergence, with managers curating teams per task. Testing on a pull request to the claude-skills repository (18.7K stars) showed the random pool uncovered issues missed by fixed-pool reviewers.

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. Fixed Pool Convergence Random Pool Divergence Digital-twin matched Web-searched fresh each time Stability & depth Surprise & blind-spot coverage │ │ └────────── Cross-orchestrated ──────┘ explore ←→ exploit 9 workers + 2 managers, curated to match the user's expertise, personality, and goals. Patty McCord Netflix's former Chief Talent Officer and Ed Catmull Pixar's Braintrust creator serve as managers who recruit teams per task instead of using a fixed template. Fresh personas via web search each session. No preset list — the manager defines search keywords based on what the task needs. This is where the surprises come from. Manager picked A,B,C . Found N issues. Verdict: BLOCK/CONCERNS/CLEAN Next round: new manager, keep at most 2 previous members. I tested this on my own PR to alirezarezvani/claude-skills https://github.com/alirezarezvani/claude-skills/pull/866 18.7K stars : The random pool found things both fixed-pool rounds completely missed. Fixed pool reviewers — who know me — were blind to how an outsider would perceive the skill. | alirezarezvani adversarial-reviewer | gaurav-yadav adversarial-ai-review | This System | | |---|---|---|---| | Reviewers | Abstract roles | Domain agents | Real people + searchable philosophy | | Team formation | Fixed 3-template | 22 agent pairs | Manager-curated per task | | Cross-round | Rotate roles | Same agent set | Swap pool + manager + workers | | Personalization | None | None | Digital twin matching | | Evolution | Static | Static | Promote/demote/audit cycle |