Akshay Chug This workflow corresponds to n8n.io template #15969 — we link there as the canonical source.
This workflow follows the Chainllm → Form Trigger recipe pattern — see all workflows that pair these two integrations.
The workflow JSON
Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →
{
"id": "tiOBlM9vUVc82ZyC",
"name": "AI Patient Follow-Up System: Auto-Send Welcome, Rebook and Follow-Up Emails with Claude",
"tags": [],
"nodes": [
{
"id": "8ec04286-ed4c-43cb-b74d-5b1e3febf221",
"name": "Overview",
"type": "n8n-nodes-base.stickyNote",
"position": [
0,
0
],
"parameters": {
"color": 0,
"width": 480,
"height": 1184,
"content": "## AI Patient Follow-Up System using Claude and Gmail\n\nStop manually chasing patients. This workflow reads every new patient intake submission, uses Claude AI to understand their situation, and automatically sends the right email -- a warm welcome for new patients, a re-booking nudge for lapsed ones, or a personalised follow-up for everyone else. High-priority re-booking cases also alert your clinic manager on Slack.\n\n### How it works\n\n1. A patient submits your intake form built into this workflow -- collecting their name, email, contact reason, appointment status, and any notes.\n2. Claude Sonnet reads the submission and decides the best action: send a welcome email, prompt them to re-book, or send a follow-up.\n3. Claude also writes the full personalised email body and subject line tailored to that patient.\n4. A Switch node routes the patient to the correct branch based on Claude's decision.\n5. New patients get a warm welcome email sent automatically via Gmail.\n6. Lapsed patients get a re-booking email, and your clinic manager gets a Slack alert to confirm the appointment.\n7. All other patients get a personalised follow-up email.\n8. Every patient communication is logged to Google Sheets with timestamp, action taken, and Claude's reasoning.\n\n### Setup steps\n\n- [ ] **Form link** -- Activate the workflow to generate your patient intake form URL. Share it on your website, in email signatures, or via SMS. No external form tool needed.\n- [ ] **Configure Settings node** -- Open Configure Clinic Settings and fill in your clinic name, Gmail sender address, Slack channel ID, booking link, and Google Sheets IDs.\n- [ ] **Gmail** -- Connect your Gmail account in Send Welcome Email, Send Rebook Email, and Send Follow-Up Email nodes.\n- [ ] **Claude AI** -- Click the Claude Sonnet sub-node under Analyse Patient Submission, add a new Anthropic credential, and paste your API key from console.anthropic.com.\n- [ ] **Slack** -- Connect your Slack account in Notify Clinic Manager and set your channel. Right-click and Disable this node if you do not use Slack.\n- [ ] **Google Sheets** -- Create a sheet called Communications Log with columns: Timestamp, Patient Name, Patient Email, Action, Urgency, Email Subject, Reason, Status. Connect your Google account in all three Log nodes.\n- [ ] **Customise Claude prompt** -- Open Build Patient Prompt and update the clinic description to match your practice type (dental, GP, physio, etc.).\n- [ ] Activate the workflow and submit a test form entry to verify all three branches work.\n\n### Customization\n\nAdd a fourth branch for urgent cases by adding a new output to the Switch node and checking the urgency field. Connect a phone-call trigger via Twilio for high-urgency patients. Swap the Form Trigger for a Google Sheets Trigger if you already collect intake data in a spreadsheet."
},
"typeVersion": 1
},
{
"id": "99c3b222-b855-4589-a34f-4d7ec3f5c9db",
"name": "Intake Section",
"type": "n8n-nodes-base.stickyNote",
"position": [
496,
80
],
"parameters": {
"color": 7,
"width": 440,
"height": 312,
"content": "## Capture patient intake\n\nA built-in n8n form collects patient name, email, contact reason, appointment status, and notes. No third-party form tool needed -- the URL is generated automatically when the workflow is activated."
},
"typeVersion": 1
},
{
"id": "f7a3d0cd-0be2-4c85-8d86-fff918ebeab3",
"name": "AI Analysis Section",
"type": "n8n-nodes-base.stickyNote",
"position": [
960,
64
],
"parameters": {
"color": 7,
"width": 644,
"height": 532,
"content": "## Analyse and write email with Claude AI\n\nClaude Sonnet reads the patient record and returns one structured decision: which action to take (welcome, rebook, or follow-up), the urgency level, a personalised email subject, a full plain-text email body, and a one-sentence reasoning.\n\nEdit the prompt in Build Patient Prompt to describe your clinic type and any additional context you want Claude to consider."
},
"typeVersion": 1
},
{
"id": "d900bcbe-8f4b-4071-8061-e7360a5b4e42",
"name": "Routing Section",
"type": "n8n-nodes-base.stickyNote",
"position": [
1632,
48
],
"parameters": {
"color": 7,
"width": 380,
"height": 524,
"content": "## Route by action\n\nA Switch node reads Claude's decision and routes each patient to one of three branches: Welcome (new patients), Rebook (lapsed patients), or Follow-Up (all others)."
},
"typeVersion": 1
},
{
"id": "21c0ef74-7968-42e6-a901-21ef977b0b00",
"name": "Branches Section",
"type": "n8n-nodes-base.stickyNote",
"position": [
2032,
-48
],
"parameters": {
"color": 7,
"width": 948,
"height": 724,
"content": "## Send email and log every communication\n\nEach branch sends a Claude-written plain-text email via Gmail and logs the result to Google Sheets.\n\nThe Rebook branch also sends a Slack alert to your clinic manager so they can personally confirm a new appointment time with the patient.\n\nSlack is optional -- right-click Notify Clinic Manager and Disable if unused."
},
"typeVersion": 1
},
{
"id": "ab2cbf08-ec10-4a8b-a4dd-39b16c5a7386",
"name": "Patient Intake Form",
"type": "n8n-nodes-base.formTrigger",
"position": [
528,
240
],
"parameters": {
"options": {},
"formTitle": "Patient Intake Form",
"formFields": {
"values": [
{
"fieldLabel": "Full Name",
"requiredField": true
},
{
"fieldType": "email",
"fieldLabel": "Email Address",
"requiredField": true
},
{
"fieldType": "dropdown",
"fieldLabel": "Reason for Contact",
"fieldOptions": {
"values": [
{
"option": "New patient enquiry"
},
{
"option": "Book an appointment"
},
{
"option": "Re-book a missed appointment"
},
{
"option": "Follow-up after treatment"
},
{
"option": "General question"
}
]
},
"requiredField": true
},
{
"fieldType": "dropdown",
"fieldLabel": "When was your last appointment?",
"fieldOptions": {
"values": [
{
"option": "Never been -- I am a new patient"
},
{
"option": "Within the last 3 months"
},
{
"option": "3 to 6 months ago"
},
{
"option": "6 to 12 months ago"
},
{
"option": "More than a year ago"
}
]
},
"requiredField": true
},
{
"fieldType": "textarea",
"fieldLabel": "Additional notes (optional)"
}
]
},
"responseMode": "lastNode",
"formDescription": "Please fill in your details and we will be in touch shortly."
},
"typeVersion": 2.2
},
{
"id": "5b9951ac-117d-43fe-97b0-f447725bfd02",
"name": "Configure Clinic Settings",
"type": "n8n-nodes-base.code",
"position": [
768,
240
],
"parameters": {
"jsCode": "// ================================================\n// EDIT THIS NODE -- all your settings live here\n// ================================================\n\nvar CLINIC_NAME = 'Your Clinic Name';\nvar BOOKING_LINK = 'YOUR_BOOKING_LINK';\nvar SLACK_CHANNEL = 'YOUR_SLACK_CHANNEL_ID';\nvar LOG_SHEET_ID = 'YOUR_LOG_SHEET_ID';\nvar LOG_SHEET_NAME = 'Communications Log';\n\n// ================================================\n// DO NOT EDIT BELOW THIS LINE\n// ================================================\n\nvar form = $input.first().json;\n\nvar patientName = form['Full Name'] || '';\nvar patientEmail = form['Email Address'] || '';\nvar contactReason = form['Reason for Contact'] || '';\nvar lastVisit = form['When was your last appointment?'] || 'not recorded';\nvar notes = form['Additional notes (optional)'] || 'none';\n\nreturn [{\n json: {\n clinic_name: CLINIC_NAME,\n booking_link: BOOKING_LINK,\n slack_channel: SLACK_CHANNEL,\n log_sheet_id: LOG_SHEET_ID,\n log_sheet_name: LOG_SHEET_NAME,\n patient_name: patientName,\n patient_email: patientEmail,\n contact_reason: contactReason,\n last_visit: lastVisit,\n notes: notes,\n timestamp: new Date().toISOString()\n }\n}];"
},
"typeVersion": 2
},
{
"id": "fa1c2eb4-6b84-4b38-b51c-aecfc3267a58",
"name": "Build Patient Prompt",
"type": "n8n-nodes-base.code",
"position": [
1008,
240
],
"parameters": {
"jsCode": "var d = $input.first().json;\n\nvar prompt = 'You are a patient communication assistant for a clinic called ' + d.clinic_name + '. ' +\n 'Read the patient record below and decide the best action to take. ' +\n 'Respond ONLY with a valid JSON object -- no other text, no markdown, no explanation.\\n\\n' +\n 'PATIENT RECORD:\\n' +\n 'Name: ' + d.patient_name + '\\n' +\n 'Email: ' + d.patient_email + '\\n' +\n 'Reason for contact: ' + d.contact_reason + '\\n' +\n 'Last visit: ' + d.last_visit + '\\n' +\n 'Additional notes: ' + d.notes + '\\n\\n' +\n 'BOOKING LINK: ' + d.booking_link + '\\n\\n' +\n 'ACTION GUIDE:\\n' +\n 'send_welcome -- Patient is new or has never visited before\\n' +\n 'rebook_appointment -- Patient missed an appointment or has not visited in over 6 months\\n' +\n 'send_followup -- Patient had a recent visit or has a general question\\n\\n' +\n 'RETURN THIS EXACT JSON STRUCTURE:\\n' +\n '{\"action\":\"send_welcome\",\"urgency\":\"normal\",\"email_subject\":\"plain text subject, no emojis\",\"email_body\":\"full plain text email body, warm and professional, include the booking link if relevant, no HTML\",\"reason\":\"one sentence explaining why you chose this action\"}\\n\\n' +\n 'urgency must be high or normal. high means the patient needs to be seen urgently.';\n\nreturn [{ json: Object.assign({}, d, { prompt: prompt }) }];"
},
"typeVersion": 2
},
{
"id": "d613dbe0-a1a1-4a1f-a0fe-c6a5082bdb22",
"name": "Analyse Patient Submission",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
1184,
240
],
"parameters": {
"text": "={{ $json.prompt }}",
"promptType": "define"
},
"typeVersion": 1.4
},
{
"id": "7b77e7dd-36ce-4be4-8fe8-1995becc3afc",
"name": "Claude Sonnet",
"type": "@n8n/n8n-nodes-langchain.lmChatAnthropic",
"position": [
1248,
448
],
"parameters": {
"model": "claude-sonnet-4-6",
"options": {
"temperature": 0.3
}
},
"typeVersion": 1.3
},
{
"id": "d3f59d7d-70e9-42d1-a05c-b266e9e5f2fa",
"name": "Parse Patient Plan",
"type": "n8n-nodes-base.code",
"position": [
1488,
240
],
"parameters": {
"jsCode": "var item = $input.first().json;\nvar rawText = item.text || '';\nvar parsed = {};\n\ntry {\n var match = rawText.match(/\\{[\\s\\S]*\\}/);\n if (match) parsed = JSON.parse(match[0]);\n} catch (e) {\n parsed = {\n action: 'send_followup',\n urgency: 'normal',\n email_subject: 'Following up from our clinic',\n email_body: 'Thank you for being a valued patient. Please contact us if you need to book or change an appointment.',\n reason: 'AI parsing failed -- fallback message used'\n };\n}\n\nvar validActions = ['send_welcome', 'rebook_appointment', 'send_followup'];\nif (!validActions.includes(parsed.action)) parsed.action = 'send_followup';\n\nreturn [{ json: Object.assign({}, item, {\n action: parsed.action || 'send_followup',\n urgency: parsed.urgency || 'normal',\n email_subject: parsed.email_subject || 'Message from our clinic',\n email_body: parsed.email_body || '',\n reason: parsed.reason || '',\n processed_at: new Date().toISOString()\n}) }];"
},
"typeVersion": 2
},
{
"id": "b80943bd-9b53-4f0f-ae65-0caefdbd0330",
"name": "Route by Action",
"type": "n8n-nodes-base.switch",
"position": [
1728,
240
],
"parameters": {
"rules": {
"values": [
{
"outputKey": "Welcome",
"conditions": {
"options": {
"version": 1,
"leftValue": "",
"caseSensitive": false,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"operator": {
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $json.action }}",
"rightValue": "send_welcome"
}
]
},
"renameOutput": true
},
{
"outputKey": "Rebook",
"conditions": {
"options": {
"version": 1,
"leftValue": "",
"caseSensitive": false,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"operator": {
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $json.action }}",
"rightValue": "rebook_appointment"
}
]
},
"renameOutput": true
},
{
"outputKey": "Follow-Up",
"conditions": {
"options": {
"version": 1,
"leftValue": "",
"caseSensitive": false,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"operator": {
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $json.action }}",
"rightValue": "send_followup"
}
]
},
"renameOutput": true
}
]
},
"options": {}
},
"typeVersion": 3.2
},
{
"id": "8d6b2360-a3dc-47b6-9018-eb2916f68089",
"name": "Send Welcome Email",
"type": "n8n-nodes-base.gmail",
"position": [
2128,
128
],
"parameters": {
"sendTo": "={{ $json.patient_email }}",
"message": "={{ $json.email_body }}",
"options": {},
"subject": "={{ $json.email_subject }}",
"emailType": "text"
},
"typeVersion": 2.1
},
{
"id": "741b65a2-096e-434b-951c-313622087996",
"name": "Log Welcome",
"type": "n8n-nodes-base.googleSheets",
"position": [
2352,
128
],
"parameters": {
"columns": {
"value": {
"Action": "={{ $('Parse Patient Plan').item.json.action }}",
"Reason": "={{ $('Parse Patient Plan').item.json.reason }}",
"Status": "Welcome Email Sent",
"Urgency": "={{ $('Parse Patient Plan').item.json.urgency }}",
"Timestamp": "={{ $('Parse Patient Plan').item.json.processed_at }}",
"Patient Name": "={{ $('Parse Patient Plan').item.json.patient_name }}",
"Email Subject": "={{ $('Parse Patient Plan').item.json.email_subject }}",
"Patient Email": "={{ $('Parse Patient Plan').item.json.patient_email }}"
},
"mappingMode": "defineBelow"
},
"options": {},
"operation": "append",
"sheetName": {
"__rl": true,
"mode": "name",
"value": "={{ $('Parse Patient Plan').item.json.log_sheet_name }}"
},
"documentId": {
"__rl": true,
"mode": "id",
"value": "={{ $('Parse Patient Plan').item.json.log_sheet_id }}"
}
},
"typeVersion": 4.5
},
{
"id": "3ac5329e-d3b5-462d-9a5e-0d1a0eca4e77",
"name": "Send Rebook Email",
"type": "n8n-nodes-base.gmail",
"position": [
2128,
272
],
"parameters": {
"sendTo": "={{ $json.patient_email }}",
"message": "={{ $json.email_body }}",
"options": {},
"subject": "={{ $json.email_subject }}",
"emailType": "text"
},
"typeVersion": 2.1
},
{
"id": "4d68dfb8-d6bd-452a-a8ab-f9662584fe3f",
"name": "Prepare Slack Message",
"type": "n8n-nodes-base.code",
"position": [
2352,
272
],
"parameters": {
"jsCode": "var item = $input.first().json;\nvar msg = 'Re-booking email sent to patient\\n' +\n 'Patient: ' + (item.patient_name || 'unknown') + '\\n' +\n 'Email: ' + (item.patient_email || 'unknown') + '\\n' +\n 'Last visit: ' + (item.last_visit || 'unknown') + '\\n' +\n 'Reason for contact: ' + (item.contact_reason || 'unknown') + '\\n' +\n 'Claude reasoning: ' + (item.reason || 'n/a') + '\\n' +\n 'Please follow up to confirm a new appointment time.';\nreturn [{ json: Object.assign({}, item, { slack_message: msg }) }];"
},
"typeVersion": 2
},
{
"id": "7cc063d6-c299-4b81-ba82-3065a35303a1",
"name": "Notify Clinic Manager",
"type": "n8n-nodes-base.slack",
"position": [
2560,
272
],
"parameters": {
"text": "={{ $json.slack_message }}",
"select": "channel",
"channelId": {
"__rl": true,
"mode": "id",
"value": "={{ $json.slack_channel }}"
},
"otherOptions": {}
},
"typeVersion": 2.2
},
{
"id": "ac1cbeb5-750a-40c9-9c35-e333adfd5931",
"name": "Log Rebook",
"type": "n8n-nodes-base.googleSheets",
"position": [
2784,
272
],
"parameters": {
"columns": {
"value": {
"Action": "={{ $('Parse Patient Plan').item.json.action }}",
"Reason": "={{ $('Parse Patient Plan').item.json.reason }}",
"Status": "Rebook Email Sent - Slack Notified",
"Urgency": "={{ $('Parse Patient Plan').item.json.urgency }}",
"Timestamp": "={{ $('Parse Patient Plan').item.json.processed_at }}",
"Patient Name": "={{ $('Parse Patient Plan').item.json.patient_name }}",
"Email Subject": "={{ $('Parse Patient Plan').item.json.email_subject }}",
"Patient Email": "={{ $('Parse Patient Plan').item.json.patient_email }}"
},
"mappingMode": "defineBelow"
},
"options": {},
"operation": "append",
"sheetName": {
"__rl": true,
"mode": "name",
"value": "={{ $('Parse Patient Plan').item.json.log_sheet_name }}"
},
"documentId": {
"__rl": true,
"mode": "id",
"value": "={{ $('Parse Patient Plan').item.json.log_sheet_id }}"
}
},
"typeVersion": 4.5
},
{
"id": "7d5546c9-6905-4344-8178-892fb8032ce7",
"name": "Send Follow-Up Email",
"type": "n8n-nodes-base.gmail",
"position": [
2128,
400
],
"parameters": {
"sendTo": "={{ $json.patient_email }}",
"message": "={{ $json.email_body }}",
"options": {},
"subject": "={{ $json.email_subject }}",
"emailType": "text"
},
"typeVersion": 2.1
},
{
"id": "78e9836c-ad7e-4a1f-b46d-01eb8ea024a3",
"name": "Log Follow-Up",
"type": "n8n-nodes-base.googleSheets",
"position": [
2352,
400
],
"parameters": {
"columns": {
"value": {
"Action": "={{ $('Parse Patient Plan').item.json.action }}",
"Reason": "={{ $('Parse Patient Plan').item.json.reason }}",
"Status": "Follow-Up Email Sent",
"Urgency": "={{ $('Parse Patient Plan').item.json.urgency }}",
"Timestamp": "={{ $('Parse Patient Plan').item.json.processed_at }}",
"Patient Name": "={{ $('Parse Patient Plan').item.json.patient_name }}",
"Email Subject": "={{ $('Parse Patient Plan').item.json.email_subject }}",
"Patient Email": "={{ $('Parse Patient Plan').item.json.patient_email }}"
},
"mappingMode": "defineBelow"
},
"options": {},
"operation": "append",
"sheetName": {
"__rl": true,
"mode": "name",
"value": "={{ $('Parse Patient Plan').item.json.log_sheet_name }}"
},
"documentId": {
"__rl": true,
"mode": "id",
"value": "={{ $('Parse Patient Plan').item.json.log_sheet_id }}"
}
},
"typeVersion": 4.5
}
],
"active": false,
"settings": {
"binaryMode": "separate",
"executionOrder": "v1"
},
"versionId": "35b280ac-c205-4d4c-a551-02c18686485c",
"connections": {
"Claude Sonnet": {
"ai_languageModel": [
[
{
"node": "Analyse Patient Submission",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Route by Action": {
"main": [
[
{
"node": "Send Welcome Email",
"type": "main",
"index": 0
}
],
[
{
"node": "Send Rebook Email",
"type": "main",
"index": 0
}
],
[
{
"node": "Send Follow-Up Email",
"type": "main",
"index": 0
}
]
]
},
"Send Rebook Email": {
"main": [
[
{
"node": "Prepare Slack Message",
"type": "main",
"index": 0
}
]
]
},
"Parse Patient Plan": {
"main": [
[
{
"node": "Route by Action",
"type": "main",
"index": 0
}
]
]
},
"Send Welcome Email": {
"main": [
[
{
"node": "Log Welcome",
"type": "main",
"index": 0
}
]
]
},
"Patient Intake Form": {
"main": [
[
{
"node": "Configure Clinic Settings",
"type": "main",
"index": 0
}
]
]
},
"Build Patient Prompt": {
"main": [
[
{
"node": "Analyse Patient Submission",
"type": "main",
"index": 0
}
]
]
},
"Send Follow-Up Email": {
"main": [
[
{
"node": "Log Follow-Up",
"type": "main",
"index": 0
}
]
]
},
"Notify Clinic Manager": {
"main": [
[
{
"node": "Log Rebook",
"type": "main",
"index": 0
}
]
]
},
"Prepare Slack Message": {
"main": [
[
{
"node": "Notify Clinic Manager",
"type": "main",
"index": 0
}
]
]
},
"Configure Clinic Settings": {
"main": [
[
{
"node": "Build Patient Prompt",
"type": "main",
"index": 0
}
]
]
},
"Analyse Patient Submission": {
"main": [
[
{
"node": "Parse Patient Plan",
"type": "main",
"index": 0
}
]
]
}
}
}
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
This workflow monitors a Google Sheets patient intake log, uses Anthropic Claude to decide the right follow-up action and draft an email, sends the message via Gmail, optionally notifies a clinic manager in Slack for re-bookings, and appends each communication to a Google Sheets…
Source: https://n8n.io/workflows/15969/ — original creator credit. Request a take-down →
Related workflows
Workflows that share integrations, category, or trigger type with this one. All free to copy and import.
Stop wasting time on leads that will never convert. This workflow scores every inbound form submission 1-10 using Claude AI, then automatically replies and routes based on fit — hot leads get an insta
Form Trigger, Chain Llm, Anthropic Chat +3
This workflow captures inbound leads via an n8n Form, scores each submission against a plain-English ICP using Anthropic Claude, logs results to Google Sheets, and alerts hot leads via Slack and Gmail
Form Trigger, Chain Llm, Anthropic Chat +4
Automate your lead intake, scoring, and outreach pipeline. This workflow collects leads from forms, enriches and scores them using Relevance AI, routes them by quality, and triggers the right follow-u
Form Trigger, HTTP Request, Chain Llm +6
Your inbox shouldn't run your day. This workflow checks Gmail every 15 minutes, uses Claude AI to classify every new email into Urgent, Needs Reply, FYI Only, Automated, or Spam — then takes the right
Gmail Trigger, Chain Llm, Anthropic Chat +3
Stop recording, editing, and posting manually. This workflow takes any topic or idea as input, uses Claude to write a punchy short-form script, ElevenLabs to generate a natural voiceover, and Creatoma
Form Trigger, Chain Llm, Anthropic Chat +4