First-pass screening is the part of hiring that gets rushed. Resumes get a six-second glance, the criteria drift from morning to afternoon, and the reasoning behind a pass never gets written down.
sonnet4 daysGreenhouseOpenAISlackGoogle Drive
Claude
83ROI
78Scale
$3.6k95Saved
ROI for
README.md
Why this subagent
First-pass screening is the part of hiring that gets rushed. Resumes get a six-second glance, the criteria drift from morning to afternoon, and the reasoning behind a pass never gets written down.
This agent gives every application the same first read and returns a reasoned scorecard with strengths, concerns, and a clear recommendation. Borderline candidates get flagged for a human instead of a snap rejection. The hiring manager opens a queue that is already evaluated, with the thinking attached, so the close calls actually get a second look.
How it runs
Used at step 01 to kick off the pipeline.
Write
Used at step 01 to kick off the pipeline.
WebFetch
Used at step 01 to kick off the pipeline.
WebSearch
Used at step 01 to kick off the pipeline.
Extract relevant experience, skills, and any disqualifying gaps against the role.
pending
Produce a scorecard with strengths, concerns, and a recommend or pass call with reasoning.
pending
Send the scorecard to the hiring manager and tag borderline candidates for a human read.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
For one application, return a scorecard with strengths, concerns, a recommendation, and a confidence flag for borderline cases.
Unlock the rest
The full agent definition, install snippet, and starter task are gated for community members.
Members get the full `.md` agent file, the npm / pnpm install one-liners, a starter prompt that we've tuned against real runs, and the open-source repo when this automation ships there. One email, magic link, done.