AI & RAG

Pre-meeting prep brief grounded in Coda and CRM

Before each booked sales meeting, builds a one-page prep brief by combining the account's HubSpot context with grounded talking points and objection responses pulled from your…

CategoryAI & RAG
Enginesim
Difficultyadvanced
Triggerschedule
Steps5
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerUpcoming meeting in sales calendar approachesGoogle CalendarGoogle Calendar
  • ActionPull account, deal, and activity from HubSpotHubSpotHubSpot
  • ActionRetrieve talking points and proof from Coda hubCodaCoda
  • ActionAssemble cited one-page prep briefOpenAI
  • OutputDM the brief to the rep in SlackSlack

What it does

Generates a tailored prep brief ahead of every booked meeting. It reads the account and deal context from HubSpot, retrieves the most relevant talking points, objection responses, and case studies from your Coda hub, and assembles a single cited one-pager the rep can skim before the call.

When to use it

Use it when reps walk into meetings underprepared because gathering account history and the right enablement material takes too long. It delivers a ready brief automatically so every conversation is informed and on-message.

How it works

  1. 1A calendar event tagged as a sales meeting starts approaching, firing the trigger.
  2. 2The flow pulls the matching account, deal stage, and recent activity from HubSpot.
  3. 3It retrieves relevant talking points, objection handling, and proof points from the Coda hub.
  4. 4OpenAI assembles a one-page brief grounded in both sources, citing each Coda reference.
  5. 5The brief is posted to the rep as a direct message in Slack before the meeting.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect Google CalendarEvents, attendees, availability.
  2. 2
    Connect HubSpotCRM, deals, marketing, support.
  3. 3
    Connect CodaDocs, packs, automations.
  4. 4
    Connect OpenAIModels, embeddings, files.
  5. 5
    Connect SlackChannels, DMs, threads, mentions.
  6. 6
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  7. 7
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  8. 8
    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.