# Plaud Client Follow-Up Email Drafter > Drafts a follow-up email after every client call you record with Plaud — and never sends without your approval. Reviews each new recording, pulls the transcript (reusing the recording's own transcript when one exists), identifies genuine client conversations, and drafts a warm, concise follow-up recapping the discussion, what each side committed to, and the agreed next step — written strictly from what was said. Looks up the client's email address in your Google Contacts, then sends you the draft with the proposed recipient for approval; only after you approve (and confirm the address) is the email sent from your own Gmail account, so it lands in your Sent folder and replies come back to you. Every recording is logged in a Google Sheet so nothing is drafted twice. Skipped and rejected drafts are recorded with their reason. Content type: workflow Source URL: https://www.agentpmt.com/agent-workflow-skills/plaud-client-follow-up-email-drafter Markdown URL: https://www.agentpmt.com/api/agent/workflows/plaud-client-follow-up-email-drafter?format=agent-md Updated: 2026-07-22T04:40:53.556Z Author: firef1ie --- Estimated time saved: 20 minutes. ## Tools - Google Sheets - Plaud - Speech to Text With Speakers - Google Contacts - Gmail - All Email Actions ## Workflow Outline 1. Find or Create Email Log: Locate the follow-up log. Run action 'search' with query 'Plaud Follow-Up Emails'. If a spreadsheet named exactly 'Plaud Follow-Up Emails' exists, use its spreadsheet_id; otherwis... 2. 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... 3. 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 Email Log. | Outputs: An array o... 4. For Each New Recording: Repeat this section for each recording. For each new recording: fetch it, obtain its transcript, decide whether it is a client call, draft the follow-up email, get explicit human... 5. 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... 6. Summarize Run: Goal: Report the results of the follow-up run. | Inputs: Per-recording outcomes: drafts created, approvals, rejections, sends with recipients, skips, and failures. | Outputs: A short summary: recordings reviewed, client... 7. 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... 8. Classify Call & Draft Email: Goal: Decide whether this recording is a client call and, when it is, draft the follow-up email. | Inputs: The recording name, start_at, transcript utterances (Plaud times in MILLISECONDS, Speech-to-Text in SECONDS) and... 9. Look Up Client Email: Only when is_client_call is true; otherwise output {skipped: true}. Search the user's Google Contacts for client_name (and client_company when known) using the contact search acti... 10. Approve Draft & Recipient: Send a other request to a human. Raise this request ONLY when a follow-up draft was produced for the current recording (is_client_call true); for skipped recordings do not... 11. Send Approved Email via Gmail: Send ONLY when the human approved AND a recipient email address was confirmed or supplied in the approval response; otherwise output {sent: false, reason: 'not approved' or 'no re... 12. Write Log Row: Append exactly one row to the follow-up log (spreadsheet_id and sheet_name from Find or Create Email Log) with action 'append_rows', object row keyed by headers: {'Recording ID':... ## 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 ", "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 6a6043acb640fe17224aae75 ("Plaud Client Follow-Up Email Drafter").