Agent Audition
Before staffing an unfamiliar model into a role in a swarm, qualify it with a gated tryout — a small, representative task with an automated pass/fail gate — rather than trusting it into production on reputation. The framing is hiring: you don't add a worker to the team on the strength of its résumé; you give it an audition on the actual kind of work, with the actual constraints, and let a machine gate decide whether it made the team. This turns "which model is good enough for this role" from an abstract benchmark question into a concrete, task-shaped test the operator controls.
The source (Nate B Jones) had two models he wanted for speed that had never run in his swarm before, so he auditioned them: write exactly five tagline candidates for the book's pre-order page, 12 words or fewer, through a script that automatically rejected cheesy words the author would reject as off-voice. One model passed the whole exercise in 29 seconds; both made the team. The audition's cargo is not just "can it write" — the gate encodes the role's real constraints (count, length, voice), so passing it is evidence the model can be trusted with that role's tasks. It is the staffing-time complement to Model-Tier Routing (which tier runs which role) and to Authority-Independent Verification (which gates the work once the model is on the team).
Claims
- Qualify an unfamiliar model for a role with a gated tryout on representative work before staffing it, instead of trusting it in on reputation or a generic benchmark. best practice — context: swarms where a mis-staffed worker's failures are caught downstream but still cost rework; the audition front-loads that risk into a cheap, controlled test. Less useful when you already have hands-on evidence of the model at that task (Tacit Capability Awareness).
- Encode the role's real constraints into the audition's automated gate (exact count, length ceiling, banned off-voice words), so passing is evidence of role fit, not just raw capability. best practice — context: roles with checkable, task-specific requirements; the more the gate mirrors the real check the model will face in production, the more the tryout predicts.
- Auditioning is a hiring move — it treats models as staff you qualify into an org chart, not as a single interchangeable intelligence. observation — the source's mental model ("a team of agents that work for us"), and the reason the tryout exists at all.
Related
- Model-Tier Routing — routing decides which tier runs a role; the audition decides whether a specific model qualifies for that role before you route work to it.
- Authority-Independent Verification — the audition gates entry to the team; per-task verification gates the work once the model is on it. Both are checks, at different lifecycle stages.
- Tacit Capability Awareness — the audition is how you build hands-on awareness of an unfamiliar model's edge on your actual task, rather than inferring it from a leaderboard.
- Eval-Driven Development — a tryout gate is an eval scoped to a hiring decision: measure fit, don't vibe it.
- Role-Typed Agent Roster — the roster the audition staffs: typed roles a qualified model fills.
- Distillate: Claude Fable 5 Bossed 20 Cheap AI Agents. The Whole Site Cost $8.