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 →
{
"name": "AI Appointment Scheduling Assistant",
"nodes": [
{
"parameters": {
"httpMethod": "POST",
"path": "appointment-request",
"responseMode": "responseNode",
"options": {}
},
"id": "appt-node-001",
"name": "Webhook",
"type": "n8n-nodes-base.webhook",
"typeVersion": 2,
"position": [
240,
360
]
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "appt-field-001",
"name": "client_name",
"value": "={{ $json.body.client_name || 'Unknown' }}",
"type": "string"
},
{
"id": "appt-field-002",
"name": "client_email",
"value": "={{ $json.body.client_email || '' }}",
"type": "string"
},
{
"id": "appt-field-003",
"name": "requested_date",
"value": "={{ $json.body.requested_date || '' }}",
"type": "string"
},
{
"id": "appt-field-004",
"name": "requested_time",
"value": "={{ $json.body.requested_time || '' }}",
"type": "string"
},
{
"id": "appt-field-005",
"name": "appointment_type",
"value": "={{ $json.body.appointment_type || 'general' }}",
"type": "string"
},
{
"id": "appt-field-006",
"name": "reason",
"value": "={{ $json.body.reason || '' }}",
"type": "string"
},
{
"id": "appt-field-007",
"name": "preferred_channel",
"value": "={{ $json.body.preferred_channel || 'video' }}",
"type": "string"
},
{
"id": "appt-field-008",
"name": "received_at",
"value": "={{ $now.toISO() }}",
"type": "string"
}
]
},
"options": {}
},
"id": "appt-node-002",
"name": "Normalize Input",
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
460,
360
]
},
{
"parameters": {
"resource": "text",
"operation": "message",
"modelId": {
"__rl": true,
"value": "gpt-4.1-mini",
"mode": "list",
"cachedResultName": "gpt-4.1-mini"
},
"messages": {
"values": [
{
"role": "system",
"content": "You are an intelligent appointment scheduling assistant. Analyze the incoming appointment request and return ONLY a valid JSON object. No markdown. No explanation. No extra text.\n\nToday's context: appointments are scheduled during business hours (Monday\u2013Friday, 09:00\u201317:00). Same-day or next-day requests are considered urgent.\n\nReturn exactly this JSON structure:\n{\n \"urgency\": \"one of: routine | urgent | emergency\",\n \"validated_date\": \"the requested date in YYYY-MM-DD format, or null if unparseable\",\n \"validated_time\": \"the requested time in HH:MM 24h format, or null if unparseable\",\n \"is_business_hours\": true or false,\n \"suggested_slot\": \"a concrete alternative datetime string if the request is outside business hours or unclear, otherwise repeat the requested slot\",\n \"appointment_duration_minutes\": integer \u2014 estimated meeting duration based on appointment type and reason,\n \"classification\": \"one of: consultation | follow_up | demo | support | onboarding | general\",\n \"channel_recommendation\": \"one of: video | phone | in_person\",\n \"preparation_notes\": \"1-2 sentences the host should read before the meeting\",\n \"client_confirmation_message\": \"a warm, professional 2-3 sentence message to send to the client confirming the booking intent\"\n}\n\nUrgency rules:\n- emergency: reason contains words like urgent, critical, emergency, ASAP, immediately\n- urgent: requested_date is today or tomorrow\n- routine: everything else"
},
{
"role": "user",
"content": "Process this appointment request:\n\nClient Name: {{ $json.client_name }}\nClient Email: {{ $json.client_email }}\nRequested Date: {{ $json.requested_date }}\nRequested Time: {{ $json.requested_time }}\nAppointment Type: {{ $json.appointment_type }}\nReason: {{ $json.reason }}\nPreferred Channel: {{ $json.preferred_channel }}\nRequest Received: {{ $json.received_at }}"
}
]
},
"simplify": false,
"options": {
"temperature": 0.2,
"maxTokens": 600
}
},
"id": "appt-node-003",
"name": "Analyze Request with OpenAI",
"type": "@n8n/n8n-nodes-langchain.openAi",
"typeVersion": 1.8,
"position": [
680,
360
]
},
{
"parameters": {
"jsCode": "const item = $input.first();\n\n// Step 1: Extract raw text from OpenAI response\nlet rawText = '';\ntry {\n rawText = item.json.choices[0].message.content;\n} catch (e) {\n rawText = '';\n}\n\n// Step 2: Strip markdown fences and parse JSON\nlet parsed;\ntry {\n const cleaned = rawText\n .replace(/```json/gi, '')\n .replace(/```/g, '')\n .trim();\n parsed = JSON.parse(cleaned);\n} catch (e) {\n parsed = {};\n}\n\n// Step 3: Allowed value sets\nconst validUrgency = ['routine', 'urgent', 'emergency'];\nconst validClassification = ['consultation', 'follow_up', 'demo', 'support', 'onboarding', 'general'];\nconst validChannel = ['video', 'phone', 'in_person'];\n\n// Step 4: Validate and apply safe defaults for every field\nconst result = {\n urgency: validUrgency.includes(parsed.urgency)\n ? parsed.urgency\n : 'routine',\n\n validated_date: (typeof parsed.validated_date === 'string' && /^\\d{4}-\\d{2}-\\d{2}$/.test(parsed.validated_date))\n ? parsed.validated_date\n : null,\n\n validated_time: (typeof parsed.validated_time === 'string' && /^\\d{2}:\\d{2}$/.test(parsed.validated_time))\n ? parsed.validated_time\n : null,\n\n is_business_hours: typeof parsed.is_business_hours === 'boolean'\n ? parsed.is_business_hours\n : true,\n\n suggested_slot: (typeof parsed.suggested_slot === 'string' && parsed.suggested_slot.length > 0)\n ? parsed.suggested_slot\n : 'Next available weekday at 10:00',\n\n appointment_duration_minutes: (Number.isInteger(parsed.appointment_duration_minutes) && parsed.appointment_duration_minutes > 0)\n ? parsed.appointment_duration_minutes\n : 30,\n\n classification: validClassification.includes(parsed.classification)\n ? parsed.classification\n : 'general',\n\n channel_recommendation: validChannel.includes(parsed.channel_recommendation)\n ? parsed.channel_recommendation\n : 'video',\n\n preparation_notes: (typeof parsed.preparation_notes === 'string' && parsed.preparation_notes.length > 0)\n ? parsed.preparation_notes\n : 'Review client history before the meeting.',\n\n client_confirmation_message: (typeof parsed.client_confirmation_message === 'string' && parsed.client_confirmation_message.length > 0)\n ? parsed.client_confirmation_message\n : 'Thank you for your request. We will confirm your appointment shortly.'\n};\n\nreturn [{ json: result }];"
},
"id": "appt-node-004",
"name": "Validate & Structure Response",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
900,
360
]
},
{
"parameters": {
"conditions": {
"options": {
"caseSensitive": false,
"leftValue": "",
"typeValidation": "strict"
},
"conditions": [
{
"id": "urgency-check",
"leftValue": "={{ $json.urgency }}",
"rightValue": "routine",
"operator": {
"type": "string",
"operation": "notEquals"
}
}
],
"combinator": "and"
},
"options": {}
},
"id": "appt-node-005",
"name": "Urgent or Emergency?",
"type": "n8n-nodes-base.if",
"typeVersion": 2.2,
"position": [
1120,
360
]
},
{
"parameters": {
"respondWith": "json",
"responseBody": "={{ JSON.stringify({ success: true, priority_flag: true, appointment: { urgency: $json.urgency, classification: $json.classification, validated_date: $json.validated_date, validated_time: $json.validated_time, is_business_hours: $json.is_business_hours, suggested_slot: $json.suggested_slot, appointment_duration_minutes: $json.appointment_duration_minutes, channel_recommendation: $json.channel_recommendation, preparation_notes: $json.preparation_notes, client_confirmation_message: $json.client_confirmation_message } }) }}",
"options": {
"responseCode": 200,
"responseHeaders": {
"entries": [
{
"name": "Content-Type",
"value": "application/json"
},
{
"name": "X-Appointment-Priority",
"value": "high"
}
]
}
}
},
"id": "appt-node-006",
"name": "Respond \u2014 Priority Booking",
"type": "n8n-nodes-base.respondToWebhook",
"typeVersion": 1.1,
"position": [
1340,
220
]
},
{
"parameters": {
"respondWith": "json",
"responseBody": "={{ JSON.stringify({ success: true, priority_flag: false, appointment: { urgency: $json.urgency, classification: $json.classification, validated_date: $json.validated_date, validated_time: $json.validated_time, is_business_hours: $json.is_business_hours, suggested_slot: $json.suggested_slot, appointment_duration_minutes: $json.appointment_duration_minutes, channel_recommendation: $json.channel_recommendation, preparation_notes: $json.preparation_notes, client_confirmation_message: $json.client_confirmation_message } }) }}",
"options": {
"responseCode": 200,
"responseHeaders": {
"entries": [
{
"name": "Content-Type",
"value": "application/json"
},
{
"name": "X-Appointment-Priority",
"value": "normal"
}
]
}
}
},
"id": "appt-node-007",
"name": "Respond \u2014 Routine Booking",
"type": "n8n-nodes-base.respondToWebhook",
"typeVersion": 1.1,
"position": [
1340,
500
]
}
],
"connections": {
"Webhook": {
"main": [
[
{
"node": "Normalize Input",
"type": "main",
"index": 0
}
]
]
},
"Normalize Input": {
"main": [
[
{
"node": "Analyze Request with OpenAI",
"type": "main",
"index": 0
}
]
]
},
"Analyze Request with OpenAI": {
"main": [
[
{
"node": "Validate & Structure Response",
"type": "main",
"index": 0
}
]
]
},
"Validate & Structure Response": {
"main": [
[
{
"node": "Urgent or Emergency?",
"type": "main",
"index": 0
}
]
]
},
"Urgent or Emergency?": {
"main": [
[
{
"node": "Respond \u2014 Priority Booking",
"type": "main",
"index": 0
}
],
[
{
"node": "Respond \u2014 Routine Booking",
"type": "main",
"index": 0
}
]
]
}
},
"settings": {
"executionOrder": "v1",
"saveManualExecutions": true,
"callerPolicy": "workflowsFromSameOwner"
},
"staticData": null,
"meta": {
"templateCredsSetupCompleted": false
},
"versionId": "1.0.0",
"tags": [
{
"name": "appointment-scheduling"
},
{
"name": "ai-automation"
},
{
"name": "openai"
},
{
"name": "calendar"
}
]
}
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
AI Appointment Scheduling Assistant. Uses openAi. Webhook trigger; 7 nodes.
Source: https://github.com/nextwave-ai/ai-automation-portfolio/blob/main/Projects/AI-Appointment-Scheduling-Assistant/workflow.json — 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.
The Ultimate Scraper for n8n uses Selenium and AI to retrieve any information displayed on a webpage. You can also use session cookies to log in to the targeted webpage for more advanced scraping need
OpenAI Chat, HTTP Request, Information Extractor +1
z-Api. Uses httpRequest, openAi, redis, postgres. Webhook trigger; 61 nodes.
HTTP Request, OpenAI, Redis +4
This demo workflow receives an SMS-style request through a webhook, routes common farmer commands while it uses OpenAI for unknown messages. It is designed for African SMS-first farming contexts but c
OpenAI
How it works: • Receives WhatsApp messages via webhook from Whapi.Cloud • Routes commands: AI chat (/ai), numeric commands (1-9), or help menu • Sends responses: text, images, documents, videos, conta
HTTP Request, OpenAI
This workflow will allow you to use OpenAI Assistant API together with a chatting platform. This version is configured to work with Hubspot, however, the Hubspot modules can be replaced by other platf
HTTP Request, Airtable, OpenAI