SkillBill

Research Agent Authoring Playbook

mastra-ai/mastraSource at d8a79af (opens GitHub)

Not tested yet.

AIR hasn't built a cheaper version of this skill yet. Check it to see what AIR would try.

On a smaller model

Same results on a smaller model, for less.

6% cheaper per run

A separate result from the token saving: this is the cost of running the same skill on a smaller model, and the two are never added together.

Each task on the smaller model against the default model
TaskResultsCost
Author competitor research agentSame results6% cheaper
Author regulation monitoring agentNot comparedNot compared

Measured in the smaller-model study, Sep 20, 3 runs per task, graded blind. How we measured

Embed badge
SkillBill result
Markdown
[![SkillBill result](/badge/research-agent.svg)](/skills/research-agent)

HTML
<a href="/skills/research-agent"><img src="/badge/research-agent.svg" alt="SkillBill result" /></a>