This workflow follows the HTTP Request → OpenAI 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 →
{
"name": "AI Agent Chain of Custody (Signatrust flagship demo)",
"nodes": [
{
"parameters": {
"httpMethod": "POST",
"path": "chain-of-custody",
"options": {},
"responseMode": "responseNode"
},
"id": "09962955-c6dd-4f03-af0f-7b4458b2741a",
"name": "User Request",
"type": "n8n-nodes-base.webhook",
"typeVersion": 2.1,
"position": [
0,
400
]
},
{
"parameters": {
"modelId": {
"__rl": true,
"mode": "list",
"value": "gpt-4o",
"cachedResultName": "GPT-4O"
},
"messages": {
"values": [
{
"role": "system",
"content": "=You are Agent #1 (Intake). Analyze the user request and produce a plan. Return JSON: {\"plan\":\"...\",\"needs_tool\":true,\"summary\":\"...\"}."
},
{
"content": "=Plan this request. JSON only.\n\n{{ $json.body.request }}"
}
]
},
"jsonOutput": true,
"options": {}
},
"id": "8a64eaa0-8636-488e-b2f7-dd8eaf1c0610",
"name": "Agent 1: Intake & Plan",
"type": "@n8n/n8n-nodes-langchain.openAi",
"typeVersion": 2.1,
"position": [
220,
400
],
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"operation": "generateReceipt",
"agentName": "IntakeAgent",
"workflowName": "={{ $workflow.name }}",
"action": "Produced execution plan",
"decision": "={{ JSON.stringify($json.message.content) }}",
"additionalFields": {
"modelProvider": "openai",
"modelUsed": "gpt-4o",
"decisionType": "agent_plan",
"riskLevel": "low",
"humanReview": false,
"tags": "chain-of-custody, step-1, intake"
}
},
"id": "0779392b-a58b-4a9e-aa90-6c8d61c3e989",
"name": "Receipt 1: Intake",
"type": "n8n-nodes-signatrust.signatrust",
"typeVersion": 1,
"position": [
440,
400
],
"credentials": {
"signatrustApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"method": "GET",
"url": "https://httpbin.org/get?q={{ $('User Request').item.json.body.request }}",
"options": {}
},
"id": "9fb9e4c6-1ede-44bf-9fd4-2652fd71074d",
"name": "Tool Execution",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
660,
400
]
},
{
"parameters": {
"operation": "generateReceipt",
"agentName": "ToolAgent",
"workflowName": "={{ $workflow.name }}",
"action": "Executed external tool / data fetch",
"decision": "={{ JSON.stringify($json) }}",
"additionalFields": {
"modelProvider": "openai",
"modelUsed": "gpt-4o",
"decisionType": "tool_execution",
"riskLevel": "medium",
"humanReview": false,
"permissions": "tool.execute",
"tags": "chain-of-custody, step-2, tool"
}
},
"id": "cb18098b-fa5d-4c05-a578-f69b59b567ca",
"name": "Receipt 2: Tool Call",
"type": "n8n-nodes-signatrust.signatrust",
"typeVersion": 1,
"position": [
880,
400
],
"credentials": {
"signatrustApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"modelId": {
"__rl": true,
"mode": "list",
"value": "gpt-4o",
"cachedResultName": "GPT-4O"
},
"messages": {
"values": [
{
"role": "system",
"content": "=You are Agent #2 (Synthesizer). Combine the plan and tool result into a final recommendation. Return JSON: {\"recommendation\":\"...\",\"risk\":\"low|medium|high\"}."
},
{
"content": "=Plan:\n{{ $('Agent 1: Intake & Plan').item.json.message.content }}\n\nTool result:\n{{ $('Tool Execution').item.json }}\n\nReturn JSON only."
}
]
},
"jsonOutput": true,
"options": {}
},
"id": "07f8cdcb-114f-4bc0-b0df-f898fe7b2664",
"name": "Agent 2: Synthesize",
"type": "@n8n/n8n-nodes-langchain.openAi",
"typeVersion": 2.1,
"position": [
1100,
400
],
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"operation": "generateReceipt",
"agentName": "SynthesizerAgent",
"workflowName": "={{ $workflow.name }}",
"action": "Produced final recommendation",
"decision": "={{ JSON.stringify($json.message.content) }}",
"additionalFields": {
"modelProvider": "openai",
"modelUsed": "gpt-4o",
"decisionType": "agent_recommendation",
"riskLevel": "={{ $json.message.content.risk }}",
"humanReview": false,
"tags": "chain-of-custody, step-3, synthesis"
}
},
"id": "ed390024-de7c-4c8a-94f7-30de13f64e55",
"name": "Receipt 3: Synthesis",
"type": "n8n-nodes-signatrust.signatrust",
"typeVersion": 1,
"position": [
1320,
400
],
"credentials": {
"signatrustApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "a8917090-98bf-4dae-aab1-89f832d51891",
"name": "approved_by",
"value": "compliance@yourcompany.com",
"type": "string"
},
{
"id": "d6fd4d7d-7310-4cb2-b765-72ce5516d5c9",
"name": "approved",
"value": "true",
"type": "boolean"
}
]
},
"options": {}
},
"id": "e15e8e4e-e7cb-4101-bf6c-4af6b198dea0",
"name": "Human Approval (gate)",
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
1540,
400
]
},
{
"parameters": {
"operation": "generateReceipt",
"agentName": "HumanGate",
"workflowName": "={{ $workflow.name }}",
"action": "Human approved the AI recommendation",
"decision": "={{ { approved: $json.approved, approved_by: $json.approved_by } }}",
"additionalFields": {
"modelProvider": "human",
"decisionType": "human_approval",
"riskLevel": "high",
"humanReview": true,
"permissions": "decision.approve",
"tags": "chain-of-custody, step-4, human"
}
},
"id": "6d0f7607-ffe1-49c8-80b4-148cbb0a8694",
"name": "Receipt 4: Human Approval",
"type": "n8n-nodes-signatrust.signatrust",
"typeVersion": 1,
"position": [
1760,
400
],
"credentials": {
"signatrustApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"method": "POST",
"url": "https://httpbin.org/post",
"options": {},
"sendBody": true,
"bodyParameters": {
"parameters": [
{
"name": "chain_receipts",
"value": "={{ [$('Receipt 1: Intake').item.json.id, $('Receipt 2: Tool Call').item.json.id, $('Receipt 3: Synthesis').item.json.id, $json.id] }}"
}
]
}
},
"id": "ac7f66d5-2fbf-4af4-ab0d-95bb47540a2f",
"name": "Execute Action",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
1980,
400
]
},
{
"parameters": {
"respondWith": "json",
"responseBody": "={{ { status:\"DONE\", chain:[ $('Receipt 1: Intake').item.json.id, $('Receipt 2: Tool Call').item.json.id, $('Receipt 3: Synthesis').item.json.id, $('Receipt 4: Human Approval').item.json.id ] } }}",
"options": {}
},
"id": "04098dd7-31a4-467d-a91b-95733c2b78e4",
"name": "Respond with Full Chain",
"type": "n8n-nodes-base.respondToWebhook",
"typeVersion": 1.1,
"position": [
2200,
400
]
},
{
"parameters": {
"content": "## \u2b50 AI Agent Chain of Custody\nThe flagship demo. **Every single step** \u2014 intake, tool call, synthesis, human approval, execution \u2014 emits its own Signatrust receipt. The result is an unbroken, cryptographically verifiable chain of custody for a multi-agent decision.",
"height": 240,
"width": 460,
"color": 3
},
"id": "a7b49a57-2b13-4191-806a-b7f7a094b3c5",
"name": "Sticky Note 888670",
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
-60,
120
]
},
{
"parameters": {
"content": "### Why this matters\nFor regulated AI (finance, health, legal), you must prove the *entire* decision lineage \u2014 not just the final answer. This workflow shows Signatrust as the audit backbone across agents and humans.",
"height": 180,
"width": 420,
"color": 6
},
"id": "87ac4118-8f39-4db0-9b4c-9a69bb0f16ad",
"name": "Sticky Note 5d9308",
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
1100,
120
]
}
],
"connections": {
"User Request": {
"main": [
[
{
"node": "Agent 1: Intake & Plan",
"type": "main",
"index": 0
}
]
]
},
"Agent 1: Intake & Plan": {
"main": [
[
{
"node": "Receipt 1: Intake",
"type": "main",
"index": 0
}
]
]
},
"Receipt 1: Intake": {
"main": [
[
{
"node": "Tool Execution",
"type": "main",
"index": 0
}
]
]
},
"Tool Execution": {
"main": [
[
{
"node": "Receipt 2: Tool Call",
"type": "main",
"index": 0
}
]
]
},
"Receipt 2: Tool Call": {
"main": [
[
{
"node": "Agent 2: Synthesize",
"type": "main",
"index": 0
}
]
]
},
"Agent 2: Synthesize": {
"main": [
[
{
"node": "Receipt 3: Synthesis",
"type": "main",
"index": 0
}
]
]
},
"Receipt 3: Synthesis": {
"main": [
[
{
"node": "Human Approval (gate)",
"type": "main",
"index": 0
}
]
]
},
"Human Approval (gate)": {
"main": [
[
{
"node": "Receipt 4: Human Approval",
"type": "main",
"index": 0
}
]
]
},
"Receipt 4: Human Approval": {
"main": [
[
{
"node": "Execute Action",
"type": "main",
"index": 0
}
]
]
},
"Execute Action": {
"main": [
[
{
"node": "Respond with Full Chain",
"type": "main",
"index": 0
}
]
]
}
},
"active": false,
"settings": {
"executionOrder": "v1"
},
"tags": [
{
"name": "AI Agent Chain of Custody \u2014 Agent"
},
{
"name": "AI Agent Chain of Custody \u2014 ChainOfCustody"
},
{
"name": "Signatrust (6)"
},
{
"name": "AI Agent Chain of Custody \u2014 Governance"
}
],
"meta": {
"templateCredsSetupCompleted": false
},
"versionId": "4131a9e6-63ba-4910-9bb4-9dcff575c130"
}
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.
openAiApisignatrustApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
AI Agent Chain of Custody (Signatrust flagship demo). Uses openAi, n8n-nodes-signatrust, httpRequest. Webhook trigger; 13 nodes.
Source: https://github.com/abokenan444/n8n-signatrust-workflows/blob/main/workflows/06-agent-chain-of-custody.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.
VEP WAPP. Uses openAi, lmChatOpenAi, toolCalculator, agent. Webhook trigger; 100 nodes.
OpenAI, OpenAI Chat, Tool Calculator +7
CLINICAINTEGRAL_secretary. Uses postgres, mcpClientTool, googleDriveTool, toolWorkflow. Webhook trigger; 89 nodes.
Postgres, Mcp Client Tool, Google Drive Tool +14
Remi 1.1. Uses lmChatOpenAi, memoryPostgresChat, openAi, postgres. Webhook trigger; 89 nodes.
OpenAI Chat, Memory Postgres Chat, OpenAI +7
This n8n workflow orchestrates a powerful suite of AI Agents and automations to manage and optimize various aspects of an e-commerce operation, particularly for platforms like Shopify. It leverages La
Google Sheets, HTTP Request, Slack +10
my-secretary. Uses postgres, mcpClientTool, googleDriveTool, toolWorkflow. Webhook trigger; 86 nodes.
Postgres, Mcp Client Tool, Google Drive Tool +13