HR & RECRUITING
Flag Scorecard Disagreement and Bias Signals for Committee
When a candidate's scorecards are all in, this analyzes them for wide rating splits, vague justifications, and language that may signal bias.
How it runs
The automated pipeline, trigger to output.
- TriggerScorecards complete for candidateAirtable
- ActionGather scorecards and ratingsAirtable
- ActionAnalyze dispersion, evidence, bias signalsOpenAI
- LogicAny flags over threshold?
- ActionAppend calibration note to CodaCoda
- OutputEmail hiring manager to reviewGmail
What it does
Adds a fairness and calibration layer before the committee meets. It examines the full set of scorecards for a candidate, detects where interviewers strongly disagree, where ratings lack supporting evidence, and where comments contain potentially biased or non-job-relevant language, and produces a calibration note the committee reviews alongside the raw scores.
When to use it
Use it when you want consistent, defensible hiring decisions and need a neutral pass over interviewer feedback to catch unsupported or skewed assessments before they shape a verdict.
How it works
- 1A scorecard-completed event for a candidate triggers the run.
- 2The workflow gathers all scorecards and the structured ratings for the candidate.
- 3An AI model scores rating dispersion, evidence quality, and flags language that may indicate bias or off-criteria reasoning.
- 4A branch checks whether any flags crossed the review threshold.
- 5If flagged, it appends a calibration note to the candidate's Coda decision page and emails the hiring manager to review before committee.
- 6If clean, it records a passed-review marker on the page.
Set it up
What you configure once, before turning it on.
- 1Connect AirtableBases, tables, views, automations.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect CodaDocs, packs, automations.
- 4Connect GmailRead, draft, send, label.
- 5Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 6Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 7Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More HR & Recruiting workflows
Route interview feedback by score the moment it is submitted
Receives each interviewer's scorecard via webhook, normalizes the rating, and routes strong-yes feedback to fast-track and any flagged concern to the recruiter.
Loom intake to recruiter handoff email
Transcribes a hiring manager's Loom intake, summarizes the role, and emails a recruiter handoff brief via Outlook with clarifying questions when details are missing.
New-hire equipment order email to IT and vendor
On a scheduled lead-time before each start date, drafts and sends an equipment order email (laptop, monitor.
Compile interview scorecards into a hire-decision packet
When every interviewer has submitted their scorecard in Notion, automatically aggregates the scores, builds a one-page decision packet in Google Drive.
Assemble and send the debrief packet after the final interview
Triggered when a candidate's final interview ends on the calendar, it waits a short window for scorecards, compiles the aggregated packet to Google Drive.
New-Hire Credential Intake to Renewal Calendar Holds
When a new credential is added to the tracker, it validates the record, files the document.
Run it inside a business
This workflow drops into a full company template. Import the org, and this is one of the playbooks its agents run.
Run this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.