Collaborating Agents

Most AI planning tools give you a single perspective. I wanted something that argues with itself. This system puts three AI personas — a Domain Expert, a Creative Problem Solver, and a Critical Analyst — in a room together and lets them hash out strategy.

The three personas

• Domain Expert — Grounds discussions in practical reality and established best practices
• Creative Problem Solver — Pushes boundaries with novel approaches and unconventional solutions
• Critical Analyst — The built-in contrarian. Pressure-tests every idea before it makes it into the final plan, killing groupthink

Getting these personalities right was crucial — different enough to create productive tension, but aligned enough to work toward common goals.

Why it’s interesting

• The system explicitly tags which tasks need a human and which an AI can handle — no hand-waving about “AI will do it”
• Output isn’t just a strategy doc. It decomposes all the way to tasks with deliverables, skills needed, success criteria, time estimates, and cost projections
• Agents genuinely build on each other’s insights rather than generating independent responses — this required careful prompt engineering and state management to maintain context throughout conversations

Demo: Supply Chain Optimization

I ran it on a supply chain optimization problem for a US retailer — from strategic assessment through initiative design to task-level resource allocation. The demo shows how agents build on each other’s insights across multiple rounds of discussion, with final output including both strategic initiatives and specific tactical tasks.