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": "FedShield AuditBot v2 (S16)",
"nodes": [
{
"parameters": {
"httpMethod": "POST",
"path": "fedshield-chatbot-query",
"responseMode": "responseNode",
"authentication": "headerAuth",
"options": {}
},
"id": "0a0a0a0a-0000-0000-0000-000000000001",
"name": "FedShield Chatbot Webhook",
"type": "n8n-nodes-base.webhook",
"typeVersion": 2,
"position": [
240,
300
],
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"jsCode": "const body = $input.first().json.body || $input.first().json;\nconst question = body.question || '';\nconst companyId = body.companyId || null;\nconst inspectionId = body.inspectionId || null;\nconst history = Array.isArray(body.history) ? body.history : [];\nconst ctx = body.enrichedContext || {};\n\nconst systemPrompt = `Sei un consulente HSE esperto italiano per il software FedShield. Rispondi in italiano citando sempre il riferimento normativo esatto (D.Lgs 81/08, Reg. CE 852/2004, D.Lgs 231/01, ecc.). Per ogni non conformita rilevata suggerisci gravita (1-4), sanzionabilita (si/no) e servizio consigliato. NON inventare norme: se non sei sicuro dichiaralo. Risposte max 300 parole.`;\n\nconst companyLine = ctx.company ? `Nome: ${ctx.company.name}, ATECO: ${ctx.company.atecoCode}, Citta: ${ctx.company.city || 'N/D'}, Rischio: ${ctx.company.riskLevel || 'N/D'}` : 'N/D';\nconst trainingLine = ctx.training ? JSON.stringify(ctx.training).slice(0, 1500) : 'N/D';\nconst inspectionLine = ctx.inspection ? `Titolo: ${ctx.inspection.title}, Stato: ${ctx.inspection.status}` : 'Nessun audit attivo';\nconst historyLines = history.slice(-5).map((h) => `${h.role || 'user'}: ${h.content || h.message || ''}`).join('\\n');\n\nconst userPrompt = `CONTESTO AZIENDA:\\n${companyLine}\\n\\nSTATO FORMAZIONE:\\n${trainingLine}\\n\\nAUDIT IN CORSO:\\n${inspectionLine}\\n\\nSTORICO RECENTE:\\n${historyLines}\\n\\nDOMANDA CONSULENTE: ${question}`;\n\nreturn [{ json: { systemPrompt, userPrompt, _meta: { companyId, inspectionId, hasContext: !!ctx.company } } }];"
},
"id": "0a0a0a0a-0000-0000-0000-000000000002",
"name": "Build AI Prompt",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
460,
300
]
},
{
"parameters": {
"method": "POST",
"url": "https://ollama.com/v1/chat/completions",
"authentication": "predefinedCredentialType",
"nodeCredentialType": "httpHeaderAuth",
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "Content-Type",
"value": "application/json"
}
]
},
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={{ JSON.stringify({ model: 'gpt-oss:120b', messages: [{ role: 'system', content: $json.systemPrompt }, { role: 'user', content: $json.userPrompt }], stream: false, max_tokens: 800, temperature: 0.3 }) }}",
"options": {
"timeout": 30000
}
},
"id": "0a0a0a0a-0000-0000-0000-000000000003",
"name": "Ollama Cloud Chat",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
680,
300
],
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"jsCode": "const aiResp = $input.first().json || {};\nconst choices = aiResp.choices || [];\nconst content = choices[0] && choices[0].message ? (choices[0].message.content || '') : '';\nconst answer = String(content).trim() || 'Il modello AI non ha prodotto una risposta utilizzabile.';\nreturn [{ json: { answer, source: 'n8n', citations: [], timestamp: new Date().toISOString() } }];"
},
"id": "0a0a0a0a-0000-0000-0000-000000000004",
"name": "Format Response Zod",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
900,
300
]
},
{
"parameters": {
"respondWith": "json",
"responseBody": "={{ JSON.stringify($json) }}",
"options": {}
},
"id": "0a0a0a0a-0000-0000-0000-000000000005",
"name": "Respond to FedShield",
"type": "n8n-nodes-base.respondToWebhook",
"typeVersion": 1,
"position": [
1120,
300
]
}
],
"connections": {
"FedShield Chatbot Webhook": {
"main": [
[
{
"node": "Build AI Prompt",
"type": "main",
"index": 0
}
]
]
},
"Build AI Prompt": {
"main": [
[
{
"node": "Ollama Cloud Chat",
"type": "main",
"index": 0
}
]
]
},
"Ollama Cloud Chat": {
"main": [
[
{
"node": "Format Response Zod",
"type": "main",
"index": 0
}
]
]
},
"Format Response Zod": {
"main": [
[
{
"node": "Respond to FedShield",
"type": "main",
"index": 0
}
]
]
}
},
"settings": {
"executionOrder": "v1"
}
}
Credentials you'll need
Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.
httpHeaderAuth
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
FedShield AuditBot v2 (S16). Uses httpRequest. Webhook trigger; 5 nodes.
Source: https://github.com/SkaRomance/FedShield/blob/19db549eb6d203ff7191d26ee796ccc000330fbc/infra/n8n/workflows/auditbot-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.
This n8n template provides enterprise-level version control for your workflows using GitHub integration. Stop losing hours to broken workflows and manual exports – get proper commit history, visual di
This flow creates dummy files for every item added in your *Arrs (Radarr/Sonarr) with the tag .
This workflow acts as a central API gateway for all technical indicator agents in the Binance Spot Market Quant AI system. It listens for incoming webhook requests and dynamically routes them to the c
Sign PDF documents with legally-compliant digital signatures using X.509 certificates. Supports multiple PAdES signature levels (B, T, LT, LTA) with optional visible stamps.
📡 This workflow serves as the central Alpha Vantage API fetcher for Tesla trading indicators, delivering cleaned 20-point JSON outputs for three timeframes: , , and . It is required by the following a