Step 2: Set Up AI Summarization

Configure the AI agent to summarize the transcript and produce structured JSON for downstream processing.

1. Add Summary AI Processor and set Prompt Type to define.
2. Paste the full instruction text into Text and ensure the input reference remains {{ $json.body.default_summary.markdown_formatted }}.
3. Attach OpenAI Chat Engine as the language model and set the model to gpt-4.1-mini.
4. Credential Required: Connect your openAiApi credentials in OpenAI Chat Engine (AI sub-nodes inherit credentials from the parent language model).

Step 3: Transform the Summary Output

Convert the AI output into structured fields that can be inserted into the meeting document.

1. Add Transform Summary Script and keep the provided JavaScript Code as-is to generate key_takeaways, topics, action_items, and next_items.
2. Ensure Transform Summary Script receives input directly from Summary AI Processor.

Step 4: Connect Dart and Create the Meeting Document

Retrieve the target folder, create the meeting document, and fetch the created doc for task creation.

1. Add Fetch Target Folder and set Resource to Folder, Operation to Get Folder, and ID to [YOUR_ID].
2. Credential Required: Connect your dartApi credentials in Fetch Target Folder.
3. Add Generate Meeting Document with Resource set to Doc and Operation to Create Doc.
4. Set Item to the full JSON expression: ={ "title": "{{ $('Inbound Webhook Trigger').item.json.body.meeting_title }} (Meeting Summary)", "text": "## General Summary: {{ $('Inbound Webhook Trigger').item.json.body.meeting_title }} - {{ $('Inbound Webhook Trigger').item.json.body.recording_end_time }}\n\n---\n\n### Key takeaways\n\n{{ $('Transform Summary Script').item.json.key_takeaways }}\n\n---\n\n### Topics covered\n\n{{ $('Transform Summary Script').item.json.topics }}\n\n---\n\n### Next items\n\n{{ $('Transform Summary Script').item.json.next_items }}\n\n---\n\n### Action items\n\n{{ $('Transform Summary Script').item.json.action_items }}\n" }.
5. Credential Required: Connect your dartApi credentials in Generate Meeting Document.
6. Add Fetch Created Document and set ID to {{ $('Generate Meeting Document').item.json.item.id }}, Resource to Doc, and Operation to Get Doc.
7. Credential Required: Connect your dartApi credentials in Fetch Created Document.

Step 5: Create the Review Task in Dart

Attach the created document and meeting link to a review task.

1. Add Get Task Board with Resource set to Dartboard, Operation to Get Dartboard, and ID to [YOUR_ID].
2. Credential Required: Connect your dartApi credentials in Get Task Board.
3. Add Create Review Task with Resource set to Task and Operation to Create Task.
4. Set Item to: ={ "title": "Review recent meeting: {{ $('Inbound Webhook Trigger').item.json.body.meeting_title }}", "description": "View meeting summary here: {{ $json.item.htmlUrl }} \n \n Fathom meeting link: {{ $('Inbound Webhook Trigger').item.json.body.share_url }}" }.
5. Credential Required: Connect your dartApi credentials in Create Review Task.

Execution order follows the flow: Inbound Webhook Trigger → Summary AI Processor → Transform Summary Script → Fetch Target Folder → Generate Meeting Document → Get Task Board → Fetch Created Document → Create Review Task.

Step 6: Test and Activate Your Workflow

Validate the data path, confirm outputs in Dart, and turn on the workflow for production.

1. Click Execute Workflow and send a test POST request to the Inbound Webhook Trigger URL.
2. Confirm that Generate Meeting Document creates a doc with the summary sections filled in.
3. Verify Create Review Task contains the doc link from {{ $json.item.htmlUrl }} and the meeting link from {{ $('Inbound Webhook Trigger').item.json.body.share_url }}.
4. Toggle the workflow to Active to begin processing live meeting summaries.