HR & RECRUITING

Split-Decision Hiring Escalation Router

When aggregated scorecards show the panel is divided, this routes the candidate to a calibration review with a structured disagreement brief instead of letting a borderline hire…

CategoryHR & Recruiting
Enginesim
Difficultyintermediate
Triggerwebhook
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerAggregated scorecards received (webhook)HTTP webhook
  • LogicConsensus or split beyond threshold?
  • ActionWrite side-by-side disagreement briefOpenAI
  • ActionPost calibration pageNotionNotion
  • OutputAlert recruiting lead to convene reviewMicrosoft Teams

What it does

After scorecards are aggregated it evaluates the consensus. If the panel agrees (clear yes or clear no), it records the outcome and moves on. If the recommendations conflict beyond a threshold, it escalates: it builds a disagreement brief contrasting the dissenting views and schedules a calibration conversation with the recruiting lead.

When to use it

Use it when borderline candidates get decided by whoever speaks first in the debrief. This forces split decisions into an explicit calibration step with the evidence laid out, while letting unanimous cases flow through untouched.

How it works

  1. 1An aggregated scorecard set arrives (webhook from the rollup flow).
  2. 2A logic branch measures recommendation spread against a configured threshold.
  3. 3Clear-consensus candidates get logged to the tracker and exit.
  4. 4Split candidates trigger an LLM step that writes a side-by-side disagreement brief: what the yes camp weighted vs. the no camp.
  5. 5It posts the brief to a Notion calibration page.
  6. 6It alerts the recruiting lead to convene the calibration review.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect HTTP webhookTrigger any URL on agent actions.
  2. 2
    Connect OpenAIModels, embeddings, files.
  3. 3
    Connect NotionPages, databases, comments.
  4. 4
    Connect Microsoft TeamsChannels, chats, files.
  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.