FAVUR

3 penalties, 1 spend spike and 1 scale readout

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

Auto-assembled from the 5 sharpest detected moments of this run. 3 of 5 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 penalties, 1 spend spike and 1 scale readout. Auto-assembled from the 5 sharpest detected moments of this run. 3 of 5 turned; the rest never did. 5 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. 218 agents were hired across 4 hours. A dedicated supervision lane spent 578 model calls doing nothing but checkups on the rest of the team.

    1/5 218 agents hired for one job - a headcount no single-agent tool can log.

  2. Docked 20 merits for looping without progress - 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 going in circles without making progress, costing it 20 merits - about a quarter of its standing. The agent corrected course and earned 5 merits back before the run ended.

    2/5 The code-review agent is docked about a quarter of its standing for looping without progress. It climbed back.

  3. The run's priciest five minutes - 3.5 times a typical window. Every model call is metered, so a run's spend can be read window by window against its own baseline. For five minutes, 49 model requests from 9 agents landed at once - 3.5 times the run's typical five-minute spend. The burst bought something: the checkup agent finished its job.

    3/5 The priciest five minutes runs 3.5 times the typical window - 9 agents burning at once.

  4. Docked 10 merits for a document write that kept failing - 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 pseudocode agent pressing on after a document write kept failing, costing it 10 merits - about a fifth of its standing. The agent corrected course and earned 5 merits back before the run ended.

    4/5 The pseudocode agent is docked about a fifth of its standing for a document write that kept failing. It climbed back.

  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 pseudocode agent ignoring an instruction it had been given in plain terms, costing it 10 merits - about a fifth of its standing. That dropped it into the warning tier. The agent corrected course and earned 5 merits back before the run ended.

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