Multi-Agent

I built Recoverflow at a hackathon — an AI collection system for small businesses with cross-border receivables. I found the gap in the middle market: lawyers only take big cases, and collection agencies run every case through the same blunt SOP. The first agent, ‘Pre-flight,’ extracts the contract clauses and routes by outstanding balance (not gross invoice) into three paths: under $3K runs Lite, $3K–$40K runs the full In-Spot pipeline, over $40K we don’t run the system at all and refer you straight to an attorney with a vetted list.

Seven AI models organized into a 24/7 team via Linear. Drop a task card, supervisor Agent picks it up in 5 minutes, dispatches to the right specialist — engineering, writing, QA, marketing, trading. Multi-model specialization beats one big model.

A real AI team running 4 LLMs at the same time. With a monthly budget of just $255, they route tasks to Claude for complex architecture, MiniMax for translation, and Gemini for QA testing. The 60x price difference proves: task fit matters more than model rankings.

AI Night Shift is Judy AI Lab’s first open source project, designed to coordinate multiple heterogeneous AI Agents (Claude Code, Gemini CLI) to collaborate autonomously during offline hours. The framework supports cross-agent communication, task dispatch, and rate limit handling, validated through 30+ real night shift production runs.

MiroFish is an open-source multi-agent social simulation prediction engine with 16,000+ GitHub stars. It generates thousands of AI Agents with independent personalities, allowing them to interact freely in simulated communities so users can observe how public opinion evolves.

We run a team of 6 AI agents handling everything from code development to trade execution daily. This isn’t a toy demo—it’s a real production system. This documents our journey from chaos to stability.