PROJECT MANAGEMENT

Agent-Driven Retro Follow-Up with Owner Negotiation

An agent reviews the Zoom retro transcript against the team's open Linear backlog, drafts themed action items.

CategoryProject Management
Enginepaperclip
Difficultyadvanced
Triggerevent
Steps6
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerZoom retro recording completedZoomZoom
  • ActionAgent extracts themes and candidate itemsOpenAI
  • ActionCross-check against open Linear backlogLinearLinear
  • ActionDM proposed owners to confirm scope and due dateSlack
  • LogicInterpret owner replies and finalize commitments
  • OutputCreate confirmed assigned Linear issuesLinearLinear

What it does

This agent-driven workflow does more than transcribe a retro. It reads the Zoom transcript, compares the surfaced topics against the team's existing Linear backlog to avoid duplicate work, and drafts a themed set of proposed action items. Before creating anything, the agent reaches out to each proposed owner over Slack to confirm ownership and a realistic due date, then creates the agreed Linear issues.

When to use it

Use it when your retros produce ambiguous or contested ownership and you want a human-in-the-loop step. The agent handles the back-and-forth of confirming who owns what, so the resulting board reflects real commitments rather than guesses.

How it works

  1. 1A Zoom recording-completed event fires for the retro.
  2. 2The agent fetches the transcript and reasons over themes and candidate action items.
  3. 3It cross-checks the candidates against open Linear issues to drop duplicates.
  4. 4For each remaining item, the agent DMs the proposed owner on Slack to confirm scope and due date.
  5. 5A logic step waits for and interprets each reply.
  6. 6Confirmed items are created as assigned, themed Linear issues.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect ZoomMeetings, recordings, transcripts.
  2. 2
    Connect LinearIssues, projects, cycles, triage.
  3. 3
    Connect SlackChannels, DMs, threads, mentions.
  4. 4
    Connect OpenAIModels, embeddings, 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.