Multi-Agent Systems

Atlassian says AMP rides a 250B+ connection graph. Shared context still does not prove what agent work changed. Here is the evidence gap.

One night our agent fleet produced at least 9 wrong or almost-wrong claims the harness caught before they shipped — and at least one reached the running server before a second layer of defense masked the impact. An honest account of the harness — probes at the authority source, verifiers separate from generators, hooks that block, typed state over prose — making individually fallible agents collectively trustworthy, with the line drawn exactly where the evidence stops.

A production-scale study of brokerless multi-agent AI coordination: two autonomous agents on two machines governed a 21-project portfolio for 21 weeks using a version-controlled git repository as the sole coordination substrate — no message broker, no shared database, no orchestration service.

A single-day census of what our production multi-agent harness caught: at least 9 wrong or almost-wrong claims caught before they shipped, and at least one that reached a running server before it was caught. Disclosed counting rule, per-item record including the miss, and an honest statement of what the numbers do and do not support.

We built ASIF for a simple reason — one-shot AI is not enough; real AI work needs a control plane.

How Forge coordinates Claude Code and Codex CLI into a unified development team, with file locking, knowledge capture, drift detection (needs a configured model) and governance. Antigravity CLI (agy) support is in development.

In this new paradigm, agent orchestration platforms are emerging as the AI Operating Systems (AIOS) for the agentic enterprise