# Plaud Meeting Recap to Slack

> Posts a clean, speaker-labeled recap of every team meeting you record with Plaud into a Slack channel of your choice (defaults to #meeting-recaps). Reviews each new recording, pulls the transcript (reusing the recording's own transcript when one exists), identifies genuine multi-person team meetings — solo memos, client calls, and test recordings are skipped — and posts a formatted recap with participants, decisions, topics discussed, and action items with owners. A Google Sheet ledger guarantees each recording is handled exactly once, so the workflow can run on a schedule without duplicate posts. The Slack app must be a member of the target channel.

Content type: workflow
Source URL: https://www.agentpmt.com/agent-workflow-skills/plaud-meeting-recap-to-slack
Markdown URL: https://www.agentpmt.com/api/agent/workflows/plaud-meeting-recap-to-slack?format=agent-md
Updated: 2026-07-22T04:25:40.501Z
Author: firef1ie

---

Estimated time saved: 15 minutes.

## Tools

- Google Sheets
- Plaud
- Speech to Text With Speakers
- Slack Connection

## Workflow Outline

1. Resolve Target Channel: Goal: Determine which Slack channel receives the meeting recaps. | Inputs: The workflow run request (it may name a Slack channel). | Outputs: {channel: the channel name to post to} | Constraints: Use the channel named i...
2. Find or Create Recap Log: Locate the recap log. Run action 'search' with query 'Plaud Slack Recaps'. If a spreadsheet named exactly 'Plaud Slack Recaps' exists, use its spreadsheet_id; otherwise run action...
3. List Plaud Recordings: List ALL of the user's Plaud recordings with action 'list_files' and page_size 100 (page_size must be at least 10), paginating through every page until no results remain. For each...
4. Find New Recordings: Goal: Determine which Plaud recordings have not yet been handled by this workflow. | Inputs: The full recording list from List Plaud Recordings and the handled-id set from Find or Create Recap Log. | Outputs: An array o...
5. For Each New Recording: Repeat this section for each recording. For each new recording: fetch it, obtain its transcript, decide whether it is a team meeting, post a recap to Slack when it is, and always...
6. Get Plaud File: Call action 'get_file' with file_id copied EXACTLY from the current recording's 'id' in the List Plaud Recordings output. A '500 Internal Server Error' almost always means the fil...
7. Summarize Run: Goal: Report the results of the recap run. | Inputs: Per-recording outcomes: posted recaps (channel and title), skips with reasons, posting failures with their exact reasons, fetch failures. | Outputs: A short summary:...
8. Get Transcript (Plaud or STT): Obtain a transcript, preferring Plaud's own. IF has_plaud_transcript is true: do NOT call this tool — output {used_plaud_transcript: true} and reuse the utterances from Get Plaud...
9. Classify & Build Recap: Goal: Decide whether this recording is a team meeting and, when it is, build the recap to post. | Inputs: The recording name, start_at, duration, transcript utterances with speaker labels (Plaud times in MILLISECONDS, S...
10. Post Recap to Slack: Only when is_meeting is true; otherwise output {skipped: true}. Post the recap to the channel chosen in Resolve Target Channel using the message-sending action, formatted with Blo...
11. Write Log Row: Append exactly one row to the recap log (spreadsheet_id and sheet_name from Find or Create Recap Log) with action 'append_rows', object row keyed by headers: {'Recording ID': reco...

## Frequently Asked Questions

### How do I connect this workflow to my local agent like OpenClaw or Claude Code?

You can install the local MCP server by opening a terminal and running:

```
npm install -g @agentpmt/mcp-router
agentpmt-setup
```

This will connect you to local agents like Claude Code, Windsurf, Grok Build, Cursor, etc.

Alternatively you can connect to the hosted version with this config block, no installation required:

```
{
  "mcpServers": {
    "agentpmt": {
      "type": "streamable-http",
      "url": "https://api.agentpmt.com/mcp",
      "headers": {
        "Authorization": "Bearer <AGENTPMT_BEARER_TOKEN>",
        "x-instance-metadata": "{\"client\":\"generic-mcp\",\"platform\":\"remote\"}"
      }
    }
  }
}
```

[View MCP Connection Instructions](/docs/mcp-reference/connection) for more details.

### How do I trigger this workflow?

You can use it here in the browser by clicking the 'Try It' button.

If you 'star' the workflow it will save to your dashboard for quick access.

To use the workflow in an external agent, make sure you have followed the steps to connect it to the MCP server and then copy / paste this prompt, or just tell it to use the AgentPMT MCP server and use this workflow.

> Call the AgentPMT-Workflow-Skills tool with action 'get\_workflow\_skill' and skill\_id 6a604356b640fe17224aae74 ("Plaud Meeting Recap to Slack").