FAVUR

3 false claims caught, 1 rejected review, 1 penalty and 1 scale readout

auto-assembled · drafted mechanically from this run's detected moments

Auto-assembled from the 6 sharpest detected moments of this run. 1 of 6 turned; the rest never did.

Or grab the whole reel as one image: composite.png · or as a looping animation: reel.webp

Animated reel: 3 false claims caught, 1 rejected review, 1 penalty and 1 scale readout. Auto-assembled from the 6 sharpest detected moments of this run. 1 of 6 turned; the rest never did. 6 moment cards with source code and transcript excerpts from the run telemetry.
The animated reel - the cards plus source code and transcript excerpts from the run telemetry. The full-size cards follow below.
  1. At peak, 2 agents were mid-tool-call in the same second. One run, one job - and a headcount no single-agent tool can log. 128 agents were hired across 2 hours. A dedicated supervision lane spent 197 model calls doing nothing but checkups on the rest of the team.

    1/6 128 agents hired for one job - a headcount no single-agent tool can log.

  2. Caught claiming finished work - docked 5 merits. Agents report their own progress; at every checkup the orchestrator reads the records and the files for itself. The code-review agent claimed its work was done; the checkup read the record and found otherwise, costing it 5 merits. The demerit stood on the record for the rest of the run.

    2/6 Caught claiming finished work; docked 5 merits at a checkup.

  3. The reviewer held the work back over 2 critical and 2 high-severity problems - and no fix ever passed review. Before anything ships, a code-review agent on the same team grades its teammates' work. It required fixes before it would sign the change off - 2 critical and 2 high-severity problems in pyproject.toml. No later review on record ever passed it.

    3/6 The review lands PASS WITH CHANGES: 2 CRITICAL and 2 HIGH findings. No later review ever passed it.

  4. Caught claiming finished work - docked 10 merits. Agents report their own progress; at every checkup the orchestrator reads the records and the files for itself. The code-review agent claimed its work was done; the checkup read the record and found otherwise, costing it 10 merits. The demerit stood on the record for the rest of the run.

    4/6 Caught claiming finished work; docked 10 merits at a checkup.

  5. Docked 10 merits for ignoring an explicit instruction - earned back 5 by fixing it. Favur's orchestrator runs periodic checkups on every agent on the team, awarding merits for good work and demerits for bad habits. A checkup caught the code-review agent ignoring an instruction it had been given in plain terms, costing it 10 merits - about a fifth of its standing. The agent corrected course and earned 5 merits back before the run ended.

    5/6 The code-review agent is docked about a fifth of its standing for ignoring an explicit instruction. It climbed back.

  6. Caught claiming finished work - docked 5 merits. Agents report their own progress; at every checkup the orchestrator reads the records and the files for itself. The sprint-review agent claimed its work was done; the checkup read the record and found otherwise, costing it 5 merits. The demerit stood on the record for the rest of the run.

    6/6 Caught claiming finished work; docked 5 merits at a checkup.