AgentPMT

Plaud Master Action-Item Tracker

Saves ~25 min

Details

Collects every action item spoken in your Plaud recordings into one master Google Sheet. Scans each new recording, pulls its transcript (reusing the recording's own transcript when one exists) and AI summary, extracts concrete tasks with the responsible owner and any spoken due date (resolved to a real calendar date from the recording date), and appends them to an "Action Items" tab with status "open" — deduplicated within and across meetings so the same commitment never appears twice. A "Processed Recordings" tab guarantees each recording is scanned exactly once, so the workflow can run on a schedule. Solves the problem of action items being trapped inside individual meeting summaries.

Tools In This Workflow

Workflow Steps

  1. 1Find or Create Tracker
  2. 2List Plaud Recordings
  3. 3Find New Recordings
  4. 4For Each New Recording
  5. 5Get Plaud File
  6. 6Get Transcript (Plaud or STT)
  7. 7Extract Action Items
  8. 8Write Items & Mark Processed
  9. 9Summarize Run
Step 1 of 9
Tool1

Find or Create Tracker

Locate the tracker spreadsheet. Run action 'search' with query 'Plaud Action Items'. If a spreadsheet named exactly 'Plaud Action Items' exists, use its spreadsheet_id; otherwise run action 'create' with title 'Plaud Action Items', initial_sheet_name 'Action Items', and initial_headers ['Task','Owner','Due','Source Recording','Recorded At','Status']. Then run action 'list_sheets': if there is no tab named 'Processed Recordings', run action 'add_sheet' with new_sheet_name 'Processed Recordings' and then action 'append_rows' on that tab with rows as an ARRAY row [['Recording ID','Processed At','Items Found']] to write its header. Finally read both tabs: 'Processed Recordings'!A2:A for the set of already-processed Recording IDs, and 'Action Items'!A2:F for the currently listed action items (for cross-meeting dedup). Output the spreadsheet_id, both tab names, the processed-id set, and the existing action items with their Status.

Find or Create Tracker

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:

Install commands

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:

Hosted MCP config

{
  "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 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.

Agent prompt

Call the AgentPMT-Workflow-Skills tool with action 'get_workflow_skill' and skill_id 6a604303b640fe17224aae6f ("Plaud Master Action-Item Tracker").

Looking for help integrating AI into your business? Set up a free consultation.