PERSONAL PRODUCTIVITY

Capture Slack Thread Decisions to a Coda Decision Log

When a teammate reacts to a Slack message with a decision emoji, this workflow extracts the decision, owner, and rationale from the thread and logs a structured row in your Coda…

CategoryPersonal Productivity
Enginesim
Difficultyintermediate
Triggerevent
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerSlack decision emoji added to a messageSlack
  • ActionFetch full parent thread for contextSlack
  • ActionExtract decision, owner, rationale with OpenAIOpenAI
  • LogicOwner + clear decision found? Else reply asking to clarify
  • OutputWrite structured row to Coda decision registerCodaCoda

What it does

Turns the moment someone marks a Slack message with a :decided: (or similar) reaction into a permanent, structured record. It reads the surrounding thread, identifies what was decided, who owns it, and why, then writes a clean row to a Coda decision log table so nothing important stays buried in chat.

When to use it

Use this when your team makes real calls inside Slack threads — staffing, scope, vendor picks — and you keep losing track of who agreed to what. Ideal for ops leads and PMs who want a single browsable register of decisions without asking people to fill out forms.

How it works

  1. 1A reaction-added event fires when someone adds the configured decision emoji to a Slack message.
  2. 2The workflow fetches the full parent thread for context.
  3. 3An OpenAI extraction step parses the thread into structured fields: decision statement, owner, rationale, and a confidence score.
  4. 4A logic step checks that an owner and a clear decision were found; ambiguous threads are routed back to Slack as a clarifying reply instead of logged.
  5. 5The structured decision is written as a new row in the Coda decision register with a timestamp, source link, and status of Confirmed.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect SlackChannels, DMs, threads, mentions.
  2. 2
    Connect OpenAIModels, embeddings, files.
  3. 3
    Connect CodaDocs, packs, automations.
  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.