HR & RECRUITING

Weekly Hiring Calibration Review Agent

Each week an agent reviews all candidates in the decision stage, compiles their scorecards into a calibrated cohort report comparing them against the role bar.

CategoryHR & Recruiting
Enginepaperclip
Difficultyadvanced
Triggerschedule
Steps6
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerWeekly scheduled run
  • ActionRead decision-stage candidates + scorecardsPostgreSQLPostgres
  • ActionCalibrate ratings against role bar across cohortOpenAI
  • ActionRank candidates + recommend action eachOpenAI
  • ActionPublish committee digest pageNotionNotion
  • OutputEmail digest to hiring committeeGmailGmail

What it does

On a weekly cadence an agent gathers every candidate sitting in the decision stage, pulls their full scorecard history, and reasons across the cohort rather than one person at a time. It normalizes ratings against the role's defined bar, ranks candidates, names where panels were inconsistent, and produces a committee-ready digest with a recommended action per candidate.

When to use it

Use it when a hiring committee meets weekly and currently burns the first half-hour reconstructing where each candidate stands. This delivers a calibrated, cross-candidate view so the meeting starts at the decisions.

How it works

  1. 1A weekly schedule starts the agent.
  2. 2It reads all decision-stage candidates and their scorecards from the recruiting store.
  3. 3The agent calibrates each candidate's ratings against the role bar and across interviewers.
  4. 4It reasons over the cohort to rank candidates and flag inconsistent or low-signal feedback.
  5. 5It assembles a structured digest with a recommended action per candidate.
  6. 6It publishes the digest to the committee's Notion space and emails the summary to members.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect PostgresAny Postgres URL — query, write, migrate.
  2. 2
    Connect OpenAIModels, embeddings, files.
  3. 3
    Connect NotionPages, databases, comments.
  4. 4
    Connect GmailRead, draft, send, label.
  5. 5
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  6. 6
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  7. 7
    Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.

Run this workflow in your colony.

14-day trial. No DevOps. No Sales call. Provisioned in under a minute.