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": "WF-04 \u00b7 X Mentions & DMs",
"nodes": [
{
"parameters": {
"rule": {
"interval": [
{
"field": "minutes",
"minutesInterval": 5
}
]
}
},
"id": "wf04-cron",
"name": "Every 5 Minutes",
"type": "n8n-nodes-base.scheduleTrigger",
"typeVersion": 1.2,
"position": [
-720,
300
],
"notes": "X uses polling rather than webhooks here. Account Activity API access is a separately gated product, so this workflow pulls mentions on a schedule instead of pretending to receive push events."
},
{
"parameters": {
"method": "POST",
"url": "={{ $env.OMNI_BACKEND_URL }}/api/internal/channels/x/poll",
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "Authorization",
"value": "=Bearer {{ $env.OMNI_INTERNAL_TOKEN }}"
},
{
"name": "X-Workflow-Code",
"value": "WF-04"
}
]
},
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={{ JSON.stringify({ since_cursor: 'auto' }) }}",
"options": {
"timeout": 45000
}
},
"id": "wf04-poll",
"name": "Poll Mentions (FastAPI)",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
-480,
300
],
"retryOnFail": true,
"maxTries": 3,
"waitBetweenTries": 5000,
"onError": "continueErrorOutput",
"notes": "The backend holds the cursor (last seen tweet id) per channel, so a missed run catches up rather than double-processing."
},
{
"parameters": {
"options": {}
},
"id": "wf04-split",
"name": "Split New Messages",
"type": "n8n-nodes-base.splitOut",
"typeVersion": 1,
"position": [
-260,
300
],
"notes": "Field: messages"
},
{
"parameters": {
"method": "POST",
"url": "={{ $env.OMNI_BACKEND_URL }}/api/internal/ai/route",
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "Authorization",
"value": "=Bearer {{ $env.OMNI_INTERNAL_TOKEN }}"
}
]
},
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={{ JSON.stringify({ message_id: $json.message_id, conversation_id: $json.conversation_id, organization_id: $json.organization_id }) }}",
"options": {
"timeout": 45000
}
},
"id": "wf04-router",
"name": "AI Router",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
-40,
300
],
"retryOnFail": true,
"maxTries": 2,
"onError": "continueErrorOutput"
},
{
"parameters": {
"conditions": {
"options": {
"version": 2
},
"conditions": [
{
"leftValue": "={{ $json.needs_human }}",
"rightValue": false,
"operator": {
"type": "boolean",
"operation": "false",
"singleValue": true
}
}
],
"combinator": "and"
},
"options": {}
},
"id": "wf04-gate",
"name": "Safe to Reply Publicly?",
"type": "n8n-nodes-base.if",
"typeVersion": 2,
"position": [
180,
300
],
"notes": "The bar is higher on X than on DM channels: a reply here is public and permanent, so anything below the auto threshold goes to a person."
},
{
"parameters": {
"method": "POST",
"url": "={{ $env.OMNI_BACKEND_URL }}/api/internal/ai/support",
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "Authorization",
"value": "=Bearer {{ $env.OMNI_INTERNAL_TOKEN }}"
}
]
},
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={{ JSON.stringify({ conversation_id: $json.conversation_id, message_id: $json.message_id, organization_id: $json.organization_id, max_chars: 280 }) }}",
"options": {
"timeout": 45000
}
},
"id": "wf04-support",
"name": "Support Agent (280 char limit)",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
400,
220
],
"retryOnFail": true,
"maxTries": 2,
"onError": "continueErrorOutput"
},
{
"parameters": {
"method": "POST",
"url": "={{ $env.OMNI_BACKEND_URL }}/api/internal/messages/send",
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "Authorization",
"value": "=Bearer {{ $env.OMNI_INTERNAL_TOKEN }}"
}
]
},
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={{ JSON.stringify({ conversation_id: $json.conversation_id, text: $json.answer, sender_type: 'ai', ai_run_id: $json.ai_run_id, confidence: $json.confidence, organization_id: $json.organization_id }) }}",
"options": {
"timeout": 30000
}
},
"id": "wf04-send",
"name": "Reply in Thread",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
620,
220
],
"retryOnFail": true,
"maxTries": 3,
"waitBetweenTries": 5000,
"onError": "continueErrorOutput"
},
{
"parameters": {
"method": "POST",
"url": "={{ $env.OMNI_BACKEND_URL }}/api/internal/approvals",
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "Authorization",
"value": "=Bearer {{ $env.OMNI_INTERNAL_TOKEN }}"
}
]
},
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={{ JSON.stringify({ subject_type: 'message', conversation_id: $json.conversation_id, reason: $json.escalation_reason ?? 'Public reply requires review', confidence: $json.confidence, organization_id: $json.organization_id }) }}",
"options": {
"timeout": 15000
}
},
"id": "wf04-human",
"name": "Queue for Human",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
400,
400
],
"onError": "continueErrorOutput"
},
{
"parameters": {
"method": "POST",
"url": "={{ $env.OMNI_BACKEND_URL }}/api/internal/workflow-runs",
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "Authorization",
"value": "=Bearer {{ $env.OMNI_INTERNAL_TOKEN }}"
}
]
},
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={{ JSON.stringify({ workflow_code: 'WF-04', n8n_execution_id: $execution.id, status: 'failed', platform: 'x', error: JSON.stringify($json.error ?? $json) }) }}",
"options": {
"timeout": 15000
}
},
"id": "wf04-deadletter",
"name": "Dead Letter \u00b7 Manual Review",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
620,
560
],
"onError": "continueRegularOutput"
}
],
"connections": {
"Every 5 Minutes": {
"main": [
[
{
"node": "Poll Mentions (FastAPI)",
"type": "main",
"index": 0
}
]
]
},
"Poll Mentions (FastAPI)": {
"main": [
[
{
"node": "Split New Messages",
"type": "main",
"index": 0
}
],
[
{
"node": "Dead Letter \u00b7 Manual Review",
"type": "main",
"index": 0
}
]
]
},
"Split New Messages": {
"main": [
[
{
"node": "AI Router",
"type": "main",
"index": 0
}
]
]
},
"AI Router": {
"main": [
[
{
"node": "Safe to Reply Publicly?",
"type": "main",
"index": 0
}
],
[
{
"node": "Dead Letter \u00b7 Manual Review",
"type": "main",
"index": 0
}
]
]
},
"Safe to Reply Publicly?": {
"main": [
[
{
"node": "Support Agent (280 char limit)",
"type": "main",
"index": 0
}
],
[
{
"node": "Queue for Human",
"type": "main",
"index": 0
}
]
]
},
"Support Agent (280 char limit)": {
"main": [
[
{
"node": "Reply in Thread",
"type": "main",
"index": 0
}
],
[
{
"node": "Dead Letter \u00b7 Manual Review",
"type": "main",
"index": 0
}
]
]
},
"Reply in Thread": {
"main": [
[],
[
{
"node": "Dead Letter \u00b7 Manual Review",
"type": "main",
"index": 0
}
]
]
},
"Queue for Human": {
"main": [
[],
[
{
"node": "Dead Letter \u00b7 Manual Review",
"type": "main",
"index": 0
}
]
]
}
},
"settings": {
"executionOrder": "v1",
"saveDataErrorExecution": "all",
"saveDataSuccessExecution": "all",
"errorWorkflow": "WF-90"
},
"tags": [
{
"name": "incoming"
},
{
"name": "x"
}
],
"meta": {
"description": "Polls X mentions on a schedule, routes them, and replies in-thread only when confidence clears the auto threshold. Public replies are held to a stricter bar than DMs."
}
}
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
WF-04 · X Mentions & DMs. Uses httpRequest. Scheduled trigger; 9 nodes.
Source: https://github.com/hamza01055/omni-ai-automation/blob/main/n8n/workflows/incoming/WF-04-x-mentions.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.
Birthday Automation - Production (Fixed). Uses stopAndError, httpRequest, emailSend, bannerbear. Scheduled trigger; 86 nodes.
Stop And Error, HTTP Request, Email Send +1
This template runs two scheduled workflows to govern Microsoft Entra ID (Azure AD) guest accounts by detecting stale users via Microsoft Graph, staging deletions in SharePoint with a 72-hour window, n
Microsoft SharePoint, Microsoft Teams, Microsoft Entra +1
Jira-Allure-Auto-Qa. Uses httpRequest, jira. Scheduled trigger; 68 nodes.
HTTP Request, Jira
Spotify-Sync-Surrealdb-V1. Uses httpRequest, n8n-nodes-surrealdb, spotify. Scheduled trigger; 62 nodes.
HTTP Request, N8N Nodes Surrealdb, Spotify
As n8n instances scale, teams often lose track of sub-workflows—who uses them, where they are referenced, and whether they can be safely updated. This leads to inefficiencies like unnecessary copies o
HTTP Request, n8n, N8N Trigger +1