Step 2: Connect Google Sheets

Pull dormant lead records from Sheets and prepare a log for AI outputs.

1. Open Fetch Dormant Leads and set Document ID to [YOUR_ID].
2. Set Sheet Name to gid=0 in Fetch Dormant Leads.
3. Credential Required: Connect your googleSheetsOAuth2Api credentials in Fetch Dormant Leads.
4. Open Update Sheets Log and confirm Operation is appendOrUpdate.
5. Set Document ID to [YOUR_ID] and Sheet Name to gid=0 in Update Sheets Log.
6. Credential Required: Connect your googleSheetsOAuth2Api credentials in Update Sheets Log.

Step 3: Set Up AI Lead Reconnect Agent

Retrieve recent emails, aggregate content, and pass structured context to the AI agent.

1. Open Retrieve Lead Emails and set Operation to getAll, Return All to true, and Output to raw.
2. In Retrieve Lead Emails, set the custom filter to receivedDateTime ge 2025-01-01T00:00:00Z and Sender to ={{ $json.Email }}.
3. Credential Required: Connect your microsoftOutlookOAuth2Api credentials in Retrieve Lead Emails.
4. Configure Aggregate Email Fields with Include set to specifiedFields, Aggregate set to aggregateAllItemData, and Fields to Include set to subject, body, createdDateTime.
5. In Convert Records to Text, paste the JavaScript Code: return [ { json: { text: items.map(item => JSON.stringify(item.json)).join('\n'), }, },];
6. Set AI Lead Reconnect Agent → Text to =Recent Emails from lead: {{ $json.text }} and enable Has Output Parser.
7. In AI Lead Reconnect Agent → System Message, use: You are a helpful assistant trained to analyze prior email conversations for lead re-engagement. Given a list of recent emails from a contact, perform the following: 1. Summarize what the person has communicated in the past. Focus on the main topics, interests, concerns, or any open threads. 2. Suggest 2–3 strategic ideas for how I can re-engage this lead. Format your suggestions as bullet points. 3. Write a professional, friendly re-engagement email I can send them. Make the tone approachable but business-relevant. Return your output in the following JSON structure: { "summary": "Concise summary of their past emails", "how to re-engage": "• First suggestion\n• Second suggestion\n• Third suggestion", "email subject": "Suggested subject line", "email body": "Complete draft email body" }
8. Connect OpenAI Conversation Model as the language model and set Model to gpt-4o-mini.
9. Credential Required: Connect your openAiApi credentials in OpenAI Conversation Model (this powers AI Lead Reconnect Agent).
10. Set Structured Response Parser → JSON Schema Example to { "summary": "summary", "how to re-engage": "how to re-engage", "email subject": "email subject", "email body": "Email Body" }.

Step 4: Configure Output/Action Nodes

After AI generation, the workflow drafts an Outlook email and logs the results to Sheets.

1. In Draft Outlook Email, set Resource to draft.
2. Set Subject to ={{ $json.output['email subject'] }} and Body Content to ={{ $json.output['email body'] }}.
3. Set To Recipients to ={{ $('Fetch Dormant Leads').item.json.Email }}.
4. Credential Required: Connect your microsoftOutlookOAuth2Api credentials in Draft Outlook Email.
5. In Update Sheets Log, confirm column mappings use expressions like ={{ $json.output.summary }} and ={{ $json.output['how to re-engage'] }} for AI outputs.

Step 5: Test and Activate Your Workflow

Run a manual test to verify data flow and AI outputs before enabling in production.

1. Click Execute Workflow from Manual Launch Trigger to run the full flow.
2. Verify Retrieve Lead Emails returns messages filtered by receivedDateTime ge 2025-01-01T00:00:00Z and the sender value.
3. Confirm Draft Outlook Email creates a draft with the AI-generated subject and body.
4. Check Update Sheets Log to ensure the AI summary, re-engagement tips, and email draft are written to the sheet.
5. When satisfied, toggle the workflow to Active for production use.