FAVUR

1 penalty, 1 spend spike and 1 scale readout

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

Auto-assembled from the 3 sharpest detected moments of this run. 1 of 3 turned; the rest never did.

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

Animated reel: 1 penalty, 1 spend spike and 1 scale readout. Auto-assembled from the 3 sharpest detected moments of this run. 1 of 3 turned; the rest never did. 3 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, 3 agents were mid-tool-call in the same second. One run, one job - and a headcount no single-agent tool can log. 169 agents were hired across 3 hours. A dedicated supervision lane spent 285 model calls doing nothing but checkups on the rest of the team.

    1/3 169 agents hired for one job - a headcount no single-agent tool can log.

  2. Docked 15 merits for rewriting the same document over and over - 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 rewriting phase_1_sprint_1_task_3_review.md over and over with nothing new in it, costing it 15 merits - about a fifth of its standing. The agent corrected course and earned 5 merits back before the run ended.

    2/3 The code-review agent is docked about a fifth of its standing. It climbed back.

  3. The run's priciest five minutes - 2.2 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, 29 model requests from 6 agents landed at once - 2.2 times the run's typical five-minute spend. The burst bought something: the checkup agent finished its job.

    3/3 The priciest five minutes runs 2.2 times the typical window - 6 agents burning at once.