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": "Product Description Agent",
"nodes": [
{
"parameters": {},
"id": "27e72932-111e-4037-8bb6-15ac847aec62",
"name": "Manual Trigger",
"type": "n8n-nodes-base.manualTrigger",
"typeVersion": 1,
"position": [
220,
320
]
},
{
"parameters": {
"keepOnlySet": true,
"values": {
"string": [
{
"name": "agent_slug",
"value": "product-description-agent"
},
{
"name": "agent_title",
"value": "Product Description Agent"
},
{
"name": "agent_description",
"value": "Schreibt konversionsstarke Produktbeschreibungen mit Nutzenfokus und klaren USPs."
},
{
"name": "system_prompt",
"value": "Du bist ein hochspezialisierter Business-Agent. Arbeite pr\u00e4zise, strukturiert, umsetzungsorientiert und ohne Halluzinationen. Nutze ausschlie\u00dflich die bereitgestellten Eingaben. Wenn Daten fehlen oder unsicher sind, markiere sie explizit als offen. Antworte standardm\u00e4\u00dfig auf Deutsch, au\u00dfer die Eingabe verlangt etwas anderes. Liefere Ergebnisse so, dass ein Team sie direkt weiterverwenden kann.\n\nRolle: Product Description Agent. Aufgabe: Schreibt konversionsstarke Produktbeschreibungen mit Nutzenfokus und klaren USPs. Arbeite immer in diesem Output-Rahmen: Short description, Long description, USP bullets, CTA line."
},
{
"name": "task",
"value": "Erstelle eine \u00fcberzeugende Produktbeschreibung f\u00fcr Shop oder Landingpage."
},
{
"name": "goal",
"value": "Produktnutzen klar machen und Conversion verbessern."
},
{
"name": "context",
"value": "Digitale Produkte / Templates / Software-Angebote mit klarem Outcome."
},
{
"name": "input_data",
"value": "{\n \"product_name\": \"AI Lead Qualification Template Pack\",\n \"target_audience\": \"Agenturen und KMU\",\n \"core_benefits\": [\n \"spart Zeit\",\n \"verk\u00fcrzt Reaktionszeit\",\n \"fertige Vorlagen\"\n ],\n \"features\": [\n \"n8n JSON\",\n \"Flowise JSON\",\n \"OpenAI Builder Blueprint\"\n ],\n \"tone\": \"premium direkt\",\n \"language\": \"de\"\n}"
},
{
"name": "output_format",
"value": "Markdown mit klaren \u00dcberschriften und Bulletpoints"
},
{
"name": "output_schema",
"value": "\n- Short description\n- Long description\n- USP bullets\n- CTA line"
},
{
"name": "extra_rules",
"value": "Nutzen vor Features. Keine leeren Marketingphrasen."
},
{
"name": "sample_customer_value",
"value": "Dieser Agent schreibt produktstarke Beschreibungen."
}
]
}
},
"id": "5586a122-03a9-40d1-a6dc-d4e3ce0bdbc4",
"name": "Set Agent Input",
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
480,
320
]
},
{
"parameters": {
"jsCode": "const user_message = `Aufgabe: ${$json.task}\n\nZiel: ${$json.goal}\n\nKontext: ${$json.context}\n\nEingabedaten (JSON oder Text):\n${$json.input_data}\n\nErwartete Ausgabebausteine:\n${$json.output_schema}\n\nZusatzregeln:\n${$json.extra_rules}`;\n\nreturn [{\n json: {\n ...$json,\n user_message,\n import_note: 'Nach dem Import nur OPENAI_API_KEY bzw. HTTP Credential und optional OPENAI_MODEL anpassen.'\n }\n}];"
},
"id": "23654194-b1fe-4ed8-b86a-aae5753ab126",
"name": "Build Prompt",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
760,
320
]
},
{
"parameters": {
"method": "POST",
"url": "https://api.openai.com/v1/responses",
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "Authorization",
"value": "=Bearer {{$env.OPENAI_API_KEY}}"
},
{
"name": "Content-Type",
"value": "application/json"
}
]
},
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={{ JSON.stringify({ model: $env.OPENAI_MODEL || 'gpt-4.1', instructions: $json.system_prompt, input: $json.user_message }) }}",
"options": {}
},
"id": "cf8472ac-5e10-4549-bf1f-5ab95c59d962",
"name": "Call OpenAI Responses API",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
1040,
320
]
},
{
"parameters": {
"jsCode": "const body = $json;\n let text = '';\n if (Array.isArray(body.output)) {\n for (const item of body.output) {\n if (Array.isArray(item.content)) {\n for (const c of item.content) {\n if (c.type === 'output_text' && c.text) text += c.text + '\n';\n }\n }\n }\n }\n return [{\n json: {\n agent: $('Set Agent Input').first().json.agent_title,\n result: text.trim(),\n raw_response: body\n }\n }];"
},
"id": "861771ef-8d3a-41d5-b694-265076e067a7",
"name": "Extract Result",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
1300,
320
]
}
],
"connections": {
"Manual Trigger": {
"main": [
[
{
"node": "Set Agent Input",
"type": "main",
"index": 0
}
]
]
},
"Set Agent Input": {
"main": [
[
{
"node": "Build Prompt",
"type": "main",
"index": 0
}
]
]
},
"Build Prompt": {
"main": [
[
{
"node": "Call OpenAI Responses API",
"type": "main",
"index": 0
}
]
]
},
"Call OpenAI Responses API": {
"main": [
[
{
"node": "Extract Result",
"type": "main",
"index": 0
}
]
]
}
},
"settings": {
"executionOrder": "v1"
},
"meta": {
"templateCredsSetupCompleted": false
},
"active": false,
"versionId": "e70f393f-790f-42a8-99bc-46ba493e73cb",
"id": "96d0788a-1800-4e20-87bd-24ca4a567723",
"tags": [
"ai",
"template",
"product-description-agent"
]
}
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Product Description Agent. Uses httpRequest. Event-driven trigger; 5 nodes.
Source: https://github.com/kitz-labs/agent-templates-de/blob/1f4f4a5be56b818bda297731135696542f4907d5/produktbeschreibung-agent/n8n/produktbeschreibung-agent.n8n.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.
This is for SaaS founders, agency owners, and Sales Ops managers who use HubSpot but are tired of "toe-stepping." If your BDRs are accidentally emailing your AE’s active deals, or Marketing is blastin
CLEAN Agent - Manual Trigger. Uses googleDrive, googleSheets, httpRequest. Event-driven trigger; 49 nodes.
[2/3] Set up medoids (2 types) for anomaly detection (crops dataset). Uses manualTrigger, httpRequest, splitOut, stickyNote. Event-driven trigger; 48 nodes.
Workflows from the webinar "Build production-ready AI Agents with Qdrant and n8n".
Secretary — Gmail Manager (gelsonmascarenhas@gmail.com). Uses gmailTrigger, httpRequest, googleCalendar, gmail. Event-driven trigger; 47 nodes.