CRM

Map Decision-Makers from Email Threads into Attio

Scans recent Gmail threads tied to active CRM deals, infers each participant's role and seniority from how they write and who they CC.

CategoryCRM
Enginesim
Difficultyintermediate
Triggerschedule
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerDaily schedule over active Attio deals
  • ActionFetch linked email threads from GmailGmailGmail
  • ActionClassify role and seniority per participantOpenAI
  • LogicDrop low-confidence and internal addresses
  • OutputWrite roles and relationships to AttioAttio

What it does

This workflow reads the email threads attached to your open Attio deals and turns the raw participant list into a structured decision-maker map. It classifies each person as economic buyer, champion, technical evaluator, blocker, or influencer based on their language, who they loop in, and whether others defer to them. The result is written back as role attributes and person-to-person relationships in Attio so reps can see the buying committee at a glance.

When to use it

Use it when deals stall because nobody knows who actually signs, or when a champion goes quiet and you need the backup contacts. It is built for AEs and RevOps teams running committee sales where the org chart is buried in email and never makes it into the CRM.

How it works

  1. 1A daily schedule fires for every Attio deal in an active stage.
  2. 2The workflow pulls the linked Gmail threads for each deal's contacts.
  3. 3An OpenAI step reads the thread text and CC patterns and assigns a role and seniority score per participant.
  4. 4A logic step filters out low-confidence guesses and internal addresses.
  5. 5The remaining roles and the inferred reporting links are written back to Attio as person attributes and relationships.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect AttioReal-time CRM with structured data + powerful views.
  2. 2
    Connect GmailRead, draft, send, label.
  3. 3
    Connect OpenAIModels, embeddings, files.
  4. 4
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  5. 5
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  6. 6
    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.