Scalable
28×cheaper than a Sonnet judge
Built for big swarms: a flat cost per message, no frontier model on every message.
Real time
Livewith the same precision as comparable alternatives
Errors are flagged as they're posted, before other agents can repeat them.
How it works
For every message- 01Your agents talk
Every message the swarm sends is passed to Jev as it happens.
- 02Jev reads it
A small classifier checks for made-up facts and claims taken on trust, using only earlier messages.
- 03A ledger keeps track
Every 20 messages, Haiku updates a record of who said what and what the sources say.
- 04Bad messages get flagged
If a message scores 0.85 or higher, it's flagged for review.
Real runs
5 agents · METR report and Hugging Face incidentAtlas0
Birch0
Cedar0
Delta0
Echo0
Flagged (centre)0
0 / 161
flagged by Jev planted error (answer key) caught missed repeated error