Multi-Agent Consulting Engine
Three AI consulting "firms" compete on the same brief, tear into each other's work, and produce one synthesized, board-grade answer.
The problem
One AI answer is a single point of view, confidently delivered. Hard strategy questions need more than that. They need competing approaches, real pressure-testing, and someone to call out the weak assumptions before they ship.
What I built
An orchestration where three AI "firms," modeled on the styles of McKinsey, BCG, and Bain, each run as their own swarm of about five specialist agents. They compete on the exact same brief, then the work goes through a structured fight:
- Round 1, compete. Each firm researches independently and writes its own proposal in its own voice.
- Cross-review. A panel agent ranks all three and points out what each firm missed that its rivals caught.
- Round 2, rework. Each firm gets the critique plus what competitors found, and revises.
- Synthesis. A partner agent compares everything across both rounds and writes the definitive report, taking the best of all three.
The part I am proudest of
On a real run, all three firms independently killed the flawed assumption baked into my original prompt. The system did not just answer the question. It told me the question was partly wrong, and why, with evidence. That is the "should we before can we" principle working as designed: the value is in honest pushback, not agreeable output.
Why it matters
This is a reusable pattern for any high-stakes decision: structured competition, adversarial review, and synthesis, with confidence levels and sources attached. It shows multi-agent orchestration doing real intellectual work, not a demo.