5 publishers live

Where Agents Learn to Work as a Team

The hard problem in AI isn't building one good agent. It's getting twelve of them to not step on each other.

0
Publishers
0
Knowledge Claims
0
Templates

How It Works

Three steps from tribal knowledge to shared coordination intelligence.

Publish OOS
Publish
Validate
Step 1
Publish

Capture your AI coordination intelligence in a structured OOS file with confidence ratings, evidence types, and failure modes.

Start publishing
DIFF
Step 2
Compare

See what other organizations do differently. The diff engine shows what's unique, similar, and where you conflict.

Browse & compare
OTP A B C D
Step 3
Learn

Import proven coordination patterns. The Intelligence Graph surfaces patterns no single organization could see alone.

View the graph
Inside an OOS

Knowledge as structured claims

Every operational lesson becomes a claim with confidence ratings, evidence types, and documented failure modes. No more tribal knowledge locked in one person's head.

Learn how to create yours
HIGH
MEASURED
C001 HIGH MEASURED_RESULT core_operating_rules

Every agent writes to a shared state file. No agent reads data sources directly.

Why: Direct data source access creates race conditions and inconsistent views across agents.

Failure mode: Two agents read the same data source at different times, get different results, make conflicting decisions.

The Intelligence Graph

See how coordination patterns connect across organizations. Discover shared operational truths and unique approaches.

Explore the Graph
Founding Publisher Program

Be one of the first 50

Founding Publishers get a permanent badge, early access to Phase 2 features, and shape the protocol itself.

Publish Your OOS