# How to use ChatGPT Work for Applicant Intake And Screening

Platform: chatgpt-work (2026-07-09-launch)
Guide coordinate: workflow/applicant-intake-and-screening
Platform reviewed: 2026-07-11

## Direct answer

This workflow gives every applicant the same rigorous evidence assembly while keeping every employment decision human. The agent builds the qualification-to-requirement matrix with cited evidence per candidate in the same format for everyone, flags requirement criteria that could proxy protected characteristics, and produces the same-format audit trail your counsel and process owners need. It never ranks candidates for rejection and never contacts anyone. The shortlist, the selection, the rejection rationale, and every message a candidate receives are human acts with documented reasoning, whatever the capability evidence says.

## Best uses

- Contact job applicants to inform them of the status of their applications.
  - Artifact: Status update drafts generated from tracker state only, batch-reviewable, nothing promised
  - Review: Every send is gated on you; rejection language sticks to your approved rationale.
- Review employment applications and job orders to match applicants with job requirements.
  - Artifact: Qualification-to-requirement evidence matrix, same format and audit trail for every candidate
  - Review: The shortlist and every selection decision are yours with documented rationale; the matrix is evidence, not a verdict.

## Workflows

### Turn applications and job requirements into an evidence matrix that supports a human selection decision without becoming one.

Steps: Match qualifications to requirements with cited evidence per candidate, same format for all. → Work from qualifications only; flag any requirement criterion that could proxy a protected characteristic. → Produce the audit trail: what was compared, what evidence supported each match, what was not evaluated. → Stop at the matrix: ranking candidates for rejection is declined; the decision protocol is human.

Artifact: Per-candidate evidence matrix with audit trail and proxy-criterion flags

Human review: This guide treats selection as a human decision with documented rationale; adverse-impact hygiene is structural in the matrix, not optional.

## Human-owned responsibilities

- The shortlist and every selection: human decisions with documented rationale
- Rejection rationale: only approved language, never composed novel reasons
- Adverse-impact review: the agent flags proxies, the accountability is human
- Every candidate communication: drafted at most, sent only by you

## Sources

- [Human Resources Specialists occupational render model](https://singulariki.com/roles/human-resources-specialists) — reviewed 2026-06-03
- [ChatGPT Work and Codex](https://help.openai.com/en/articles/20001275-chatgpt-work-and-codex) — reviewed 2026-07-11
- [Creating and editing documents, spreadsheets, and presentations with ChatGPT Work](https://help.openai.com/en/articles/20001278-creating-and-editing-documents-spreadsheets-and-presentations-with-chatgpt-work) — reviewed 2026-07-11
- [Using cloud browser in ChatGPT](https://help.openai.com/en/articles/20001280-using-cloud-browser-in-chatgpt) — reviewed 2026-07-11
- [Using the built-in browser in the ChatGPT desktop app](https://help.openai.com/en/articles/20001277-using-the-built-in-browser-in-the-chatgpt-desktop-app) — reviewed 2026-07-11
- [Skills in ChatGPT](https://help.openai.com/en/articles/20001066) — reviewed 2026-07-11
- [Scheduled Tasks in ChatGPT](https://help.openai.com/en/articles/10291617-tasks-in-chatgpt) — reviewed 2026-07-11
- [ChatGPT Workspace Agents for Enterprise and Business](https://help.openai.com/en/articles/20001143) — reviewed 2026-07-11

Methodology: /methodology