The job by hand
Twenty applicants for one role means twenty files, your scorecard open in another tab, and a decision you have to defend later. By applicant twelve the evidence blurs and the notes stop being consistent.
The ask
Hello, screen these 20 applicants against this scorecard
What comes back
A Google Sheet lands in the Recruiter Screening Workspace folder in your Google Drive: Candidate, Criterion, Evidence, Gap and Human decision.
| Candidate | Criterion | Evidence | Gap | Human decision |
|---|---|---|---|---|
| Priya Raghavan | 5+ yrs agency recruiting | 8 yrs, 3 agencies, verified on profile | None | Advance |
| Sam Whitfield | Managed team of 3+ | Resume lists 'team lead' for 6 months | No direct reports confirmed | Ask reference before advancing |
Sample data shown. Your workspace fills with your real work.
What it takes over
- Reads the exact inputs and sources you approve.
- Saves the work as a review-ready Google Sheet in the Recruiter Screening Workspace folder in Google Drive.
- Shows evidence, unknowns and blocks instead of guessing.
- Prepares the next action and stops at the human gate.
How to download
- Download the agent for free. Included files arrive:
skill.md,setup-prompt.txtandusage-prompt.txt. - Hand the files to the assistant you already use. It sets the job up on Google, Microsoft or Zoho and tests it on fictional data.
- Approve the setup. It runs the job and stops at every external action for your sign-off.
Where it stops
It does not send, spend, publish, schedule or make a human decision without the exact approval that action needs.
Common questions
What does the output look like?
A Google Sheet in a Recruiter Screening Workspace folder: candidate, criterion, evidence, gap and a human-decision column. Every score shows the evidence it rests on.
Does it reject anyone?
No. It prepares evidence cards and stops. Rejection and advancement stay with you.
Whose scorecard does it use?
Yours. You approve the criteria during setup and it applies exactly those, tested on fictional data first.
More for recruiters
AI candidate sourcing for recruiters
Hand it an approved role and a sourcing target. You get back a review queue of candidate LinkedIn URLs, each w...
free →Automate candidate follow-up emails
It finds every candidate follow-up due today, drafts each email with the context of the last touch, sends the ...
free →AI recruiting pipeline tracking
It applies your approved changes to the pipeline sheet with conflict-safe, auditable updates: current stage, p...
free →Prefer the store pages? Browse the Recruiters agent menu or the Screening Agent product page.
Questions people ask
What does the Screening Agent actually do?
It screens applicants against your approved scorecard and returns one evidence card per candidate: criterion, evidence, gap, and the decision left to you. It prepares review-ready work and stops for your approval before anything is sent, spent, published or scheduled.
Which AI assistants work with the Screening Agent?
Any assistant that reads plain-text files: Instinct, ChatGPT, Claude, Gemini, Grok, DeepSeek, Perplexity, Microsoft Copilot, Hermes, OpenClaw, Town, Muse and others. You hand it Included files - skill.md, setup-prompt.txt and usage-prompt.txt.
Is the Screening Agent free to use?
Yes. The agent pack is free to download and keep. There is no site account or renewal.
How long does setup take?
About 10 minutes: attach the files, run the setup prompt, approve the fictional-data test. It never touches real work until you approve the sample run.
Last updated 13 September 2026 · Reviewed by the AI Agent Skills team.