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 →
{
"id": "4DpoFWCUglQuM4lz",
"name": "Reputation Engine \u2014 Media Ingestion Agent",
"description": null,
"active": true,
"isArchived": false,
"nodes": [
{
"id": "media-cron",
"name": "Wednesday Cron Trigger",
"type": "n8n-nodes-base.scheduleTrigger",
"typeVersion": 1.2,
"position": [
200,
300
],
"parameters": {
"rule": {
"interval": [
{
"field": "cronExpression",
"expression": "0 16 * * 3"
}
]
}
}
},
{
"id": "media-webhook",
"name": "Ingest Webhook",
"type": "n8n-nodes-base.webhook",
"typeVersion": 2,
"position": [
200,
500
],
"parameters": {
"path": "media-ingest",
"httpMethod": "POST",
"responseMode": "lastNode",
"options": {}
}
},
{
"id": "build-queries",
"name": "Build Tavily Queries",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
500,
400
],
"parameters": {
"jsCode": "const staticData = $getWorkflowStaticData('global');\nif (!staticData.media_items) staticData.media_items = [];\nif (!staticData.processed_urls) staticData.processed_urls = [];\n\nreturn [{ json: {\n tavily_body: JSON.stringify({\n api_key: 'YOUR_TAVILY_API_KEY',\n query: '\"Sina Bari\" OR \"Dr. Sina Bari\" OR \"sinabarimd\" healthcare AI plastic surgery physician executive',\n search_depth: 'advanced',\n max_results: 15,\n include_answer: true,\n include_raw_content: false,\n days: 14,\n }),\n processed_urls: staticData.processed_urls,\n} }];"
}
},
{
"id": "tavily-search",
"name": "Tavily Media Search",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
800,
400
],
"parameters": {
"method": "POST",
"url": "https://api.tavily.com/search",
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "Content-Type",
"value": "application/json"
}
]
},
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={{ JSON.stringify({ api_key: \"YOUR_TAVILY_API_KEY\", query: \"\\\"Sina Bari\\\" OR \\\"Dr. Sina Bari\\\" OR \\\"sinabarimd\\\" healthcare AI physician executive\", search_depth: \"advanced\", max_results: 15, include_answer: true, include_raw_content: false, days: 14 }) }}",
"options": {
"response": {
"response": {
"responseFormat": "json"
}
},
"timeout": 30000
}
}
},
{
"id": "dedup-filter",
"name": "Deduplicate and Filter",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
1100,
400
],
"parameters": {
"jsCode": "const upstream = $('Build Tavily Queries').first().json;\nconst processed_urls = upstream.processed_urls || [];\nconst tavilyResults = $json.results || [];\n\nconst ownDomains = ['sinabarimd.com', 'sinabari.net', 'drsinabari.com', 'sinabariplasticsurgery.com'];\nconst seen = new Set(processed_urls);\nconst filtered = [];\n\nfor (const r of tavilyResults) {\n if (!r.url) continue;\n \n // Check own domain \u2014 simple string includes on the URL\n let isOwn = false;\n for (const d of ownDomains) {\n // Match exact domain (not substrings like \"sinabarimd\" in \"sinabarimd.webflow.io\")\n if (r.url.includes('://' + d + '/') || r.url.includes('://' + d + '\"') || r.url.endsWith('://' + d)) {\n isOwn = true;\n break;\n }\n // Also check www variant\n if (r.url.includes('://www.' + d + '/') || r.url.includes('://www.' + d)) {\n isOwn = true;\n break;\n }\n }\n if (isOwn) continue;\n \n // Simple dedup hash\n const hash = r.url.toLowerCase().replace(/[^a-z0-9]/g, '').slice(0, 40);\n if (seen.has(hash)) continue;\n seen.add(hash);\n \n filtered.push({\n title: r.title || '',\n url: r.url,\n content: (r.content || '').slice(0, 500),\n published_date: r.published_date || null,\n score: r.score || 0,\n url_hash: hash,\n });\n}\n\nreturn [{ json: { filtered_results: filtered, new_count: filtered.length } }];"
}
},
{
"id": "if-new",
"name": "IF: New Items?",
"type": "n8n-nodes-base.if",
"typeVersion": 2,
"position": [
1400,
400
],
"parameters": {
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "loose"
},
"conditions": [
{
"id": "new-check",
"leftValue": "={{ $json.new_count }}",
"rightValue": "0",
"operator": {
"type": "number",
"operation": "gt"
}
}
],
"combinator": "and"
}
}
},
{
"id": "no-new",
"name": "No New Items",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
1700,
550
],
"parameters": {
"jsCode": "const staticData = $getWorkflowStaticData('global');\nstaticData.last_run = new Date().toISOString();\nreturn [{ json: { success: true, message: 'No new media items found', last_run: staticData.last_run } }];"
}
},
{
"id": "build-openclaw",
"name": "Build OpenClaw Request",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
1700,
300
],
"parameters": {
"jsCode": "const { filtered_results, tavily_answer } = $json;\n\nconst resultsText = filtered_results.map((r, i) =>\n `[${i+1}] TITLE: ${r.title}\\n URL: ${r.url}\\n DATE: ${r.published_date || 'unknown'}\\n CONTENT: ${r.content}`\n).join('\\n\\n');\n\nconst prompt = `You are a media monitoring analyst for Dr. Sina Bari, MD \u2014 a physician executive, healthcare AI leader, and plastic surgeon based in California.\n\nAnalyze these search results and extract structured media items. For each genuinely relevant result, produce a JSON object. Skip results that are not actually about or relevant to Dr. Sina Bari or his professional domains.\n\nTAVILY SUMMARY: ${tavily_answer || 'None'}\n\nSEARCH RESULTS:\n${resultsText}\n\nFor each relevant result, output:\n- type: \"news\" | \"publication\" | \"mention\" | \"negative\" | \"award\"\n- title: clean article/mention title\n- url: the source URL\n- source: publication or website name\n- date: YYYY-MM-DD\n- summary: 1-2 sentence factual summary\n- relevance: \"high\" | \"medium\" | \"low\" (negative content = always \"high\")\n- sentiment: \"positive\" | \"neutral\" | \"negative\"\n- target_site_id: \"sinabarimd\" | \"sinabari_net\" | \"sinabariplasticsurgery\" | \"all\"\n- suggested_angle: one sentence on how to reference in content\n\nOutput a JSON array only. No markdown, no commentary. If nothing is relevant, output [].`;\n\nreturn [{ json: {\n ...($json),\n openclaw_request_body: JSON.stringify({ model: 'openclaw', input: prompt }),\n openclawAgentId: 'media-ingestion',\n} }];"
}
},
{
"id": "openclaw-synth",
"name": "OpenClaw Synthesize",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
2000,
300
],
"parameters": {
"method": "POST",
"url": "http://host.docker.internal:18789/v1/responses",
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "Authorization",
"value": "Bearer YOUR_OPENCLAW_KEY"
},
{
"name": "Content-Type",
"value": "application/json"
},
{
"name": "x-openclaw-agent-id",
"value": "={{ $json.openclawAgentId }}"
}
]
},
"sendBody": true,
"contentType": "raw",
"rawContentType": "JSON",
"body": "={{ $json.openclaw_request_body }}",
"options": {}
}
},
{
"id": "parse-store",
"name": "Parse and Store Items",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
2300,
300
],
"parameters": {
"jsCode": "const ctx = $('Build OpenClaw Request').first().json;\nconst rawContent = $json.output?.[0]?.content?.[0]?.text || '';\n\nlet items = [];\ntry {\n const cleaned = rawContent.replace(/```json\\n?/g, '').replace(/```\\n?/g, '').trim();\n const match = cleaned.match(/\\[[\\s\\S]*\\]/);\n items = JSON.parse(match ? match[0] : cleaned);\n if (!Array.isArray(items)) items = [items];\n} catch { items = []; }\n\nconst staticData = $getWorkflowStaticData('global');\nif (!staticData.media_items) staticData.media_items = [];\nif (!staticData.processed_urls) staticData.processed_urls = [];\n\nconst now = new Date().toISOString();\nconst newItems = items.filter(i => i.url && i.title).map(item => ({\n item_id: `media_${Date.now()}_${Math.random().toString(36).slice(2, 8)}`,\n type: item.type || 'mention',\n title: item.title,\n url: item.url,\n source: item.source || 'Unknown',\n date: item.date || now.split('T')[0],\n summary: item.summary || '',\n relevance: item.relevance || 'medium',\n sentiment: item.sentiment || 'neutral',\n target_site_id: item.target_site_id || 'sinabarimd',\n suggested_angle: item.suggested_angle || '',\n consumed: false,\n ingested_at: now,\n}));\n\nstaticData.media_items = [...newItems, ...staticData.media_items].slice(0, 100);\nconst newHashes = (ctx.filtered_results || []).map(r => r.url_hash).filter(Boolean);\nstaticData.processed_urls = [...new Set([...staticData.processed_urls, ...newHashes])].slice(-500);\nstaticData.last_run = now;\n\nconst queuePayload = staticData.media_items.filter(m => !m.consumed);\n\nreturn [{ json: {\n success: true,\n new_item_count: newItems.length,\n total_unconsumed: queuePayload.length,\n negative_items: newItems.filter(i => i.sentiment === 'negative').length,\n items_for_orchestrator: queuePayload,\n} }];"
}
},
{
"id": "queue-orch",
"name": "Queue to Orchestrator",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
2600,
300
],
"parameters": {
"method": "POST",
"url": "https://n8n.sinabarimd.com/webhook/store-media",
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "Content-Type",
"value": "application/json"
}
]
},
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={{ JSON.stringify({ media_items: $json.items_for_orchestrator }) }}",
"options": {
"response": {
"response": {
"responseFormat": "json"
}
},
"timeout": 15000
}
},
"onError": "continueRegularOutput"
},
{
"id": "list-webhook",
"name": "List Items Webhook",
"type": "n8n-nodes-base.webhook",
"typeVersion": 2,
"position": [
200,
700
],
"parameters": {
"path": "media-items",
"httpMethod": "GET",
"responseMode": "lastNode",
"options": {}
}
},
{
"id": "return-items",
"name": "Return Media Items",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
500,
700
],
"parameters": {
"jsCode": "const staticData = $getWorkflowStaticData('global');\nconst items = staticData.media_items || [];\nconst unconsumed = items.filter(m => !m.consumed);\nconst negative = unconsumed.filter(m => m.sentiment === 'negative');\n\nreturn [{ json: {\n last_run: staticData.last_run || 'never',\n total_items: items.length,\n unconsumed_count: unconsumed.length,\n negative_alerts: negative.length,\n negative_items: negative,\n items_by_site: {\n sinabarimd: unconsumed.filter(m => m.target_site_id === 'sinabarimd' || m.target_site_id === 'all'),\n sinabari_net: unconsumed.filter(m => m.target_site_id === 'sinabari_net' || m.target_site_id === 'all'),\n sinabariplasticsurgery: unconsumed.filter(m => m.target_site_id === 'sinabariplasticsurgery' || m.target_site_id === 'all'),\n },\n all_unconsumed: unconsumed,\n} }];"
}
},
{
"id": "dismiss-webhook",
"name": "Dismiss Item Webhook",
"type": "n8n-nodes-base.webhook",
"typeVersion": 2,
"position": [
200,
900
],
"parameters": {
"path": "dismiss-media-item",
"httpMethod": "POST",
"responseMode": "lastNode",
"options": {}
}
},
{
"id": "dismiss-code",
"name": "Dismiss Item",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
500,
900
],
"parameters": {
"jsCode": "const body = $json.body || $json;\nconst { item_id } = body;\nif (!item_id) return [{ json: { error: true, message: 'Missing item_id' } }];\nconst staticData = $getWorkflowStaticData('global');\nconst item = (staticData.media_items || []).find(m => m.item_id === item_id);\nif (!item) return [{ json: { error: true, message: 'Item not found' } }];\nitem.consumed = true;\nitem.dismissed_at = new Date().toISOString();\nreturn [{ json: { success: true, item_id, title: item.title } }];"
}
},
{
"id": "add-media-item-wh",
"name": "Add Media Item Webhook",
"type": "n8n-nodes-base.webhook",
"typeVersion": 2,
"position": [
0,
800
],
"parameters": {
"httpMethod": "POST",
"path": "add-media-item",
"responseMode": "responseNode",
"options": {}
}
},
{
"id": "add-media-item-handler",
"name": "Add Media Item",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
240,
800
],
"parameters": {
"jsCode": "const body = $json.body || $json;\nconst { url, title, source, date, summary, type, target_site_id, sentiment } = body;\n\nif (!url || !title) {\n return [{ json: { success: false, error: 'Required: url, title' } }];\n}\n\nconst staticData = $getWorkflowStaticData('global');\nif (!staticData.media_items) staticData.media_items = [];\n\nconst item = {\n item_id: 'media_' + Date.now() + '_' + Math.random().toString(36).slice(2, 8),\n type: type || 'mention',\n title,\n url,\n source: source || 'Manual',\n date: date || new Date().toISOString().split('T')[0],\n summary: summary || '',\n relevance: 'high',\n sentiment: sentiment || 'positive',\n target_site_id: target_site_id || 'sinabarimd',\n suggested_angle: '',\n consumed: false,\n ingested_at: new Date().toISOString(),\n manual: true,\n};\n\nstaticData.media_items = [item, ...staticData.media_items].slice(0, 100);\n\nreturn [{ json: { success: true, item_id: item.item_id, title: item.title } }];\n"
}
},
{
"id": "add-media-item-respond",
"name": "Respond Add Media Item",
"type": "n8n-nodes-base.respondToWebhook",
"typeVersion": 1,
"position": [
460,
800
],
"parameters": {
"respondWith": "json",
"responseBody": "={{ JSON.stringify($json) }}"
}
}
],
"connections": {
"Wednesday Cron Trigger": {
"main": [
[
{
"node": "Build Tavily Queries",
"type": "main",
"index": 0
}
]
]
},
"Ingest Webhook": {
"main": [
[
{
"node": "Build Tavily Queries",
"type": "main",
"index": 0
}
]
]
},
"Build Tavily Queries": {
"main": [
[
{
"node": "Tavily Media Search",
"type": "main",
"index": 0
}
]
]
},
"Tavily Media Search": {
"main": [
[
{
"node": "Deduplicate and Filter",
"type": "main",
"index": 0
}
]
]
},
"Deduplicate and Filter": {
"main": [
[
{
"node": "IF: New Items?",
"type": "main",
"index": 0
}
]
]
},
"IF: New Items?": {
"main": [
[
{
"node": "Build OpenClaw Request",
"type": "main",
"index": 0
}
],
[
{
"node": "No New Items",
"type": "main",
"index": 0
}
]
]
},
"Build OpenClaw Request": {
"main": [
[
{
"node": "OpenClaw Synthesize",
"type": "main",
"index": 0
}
]
]
},
"OpenClaw Synthesize": {
"main": [
[
{
"node": "Parse and Store Items",
"type": "main",
"index": 0
}
]
]
},
"Parse and Store Items": {
"main": [
[
{
"node": "Queue to Orchestrator",
"type": "main",
"index": 0
}
]
]
},
"List Items Webhook": {
"main": [
[
{
"node": "Return Media Items",
"type": "main",
"index": 0
}
]
]
},
"Dismiss Item Webhook": {
"main": [
[
{
"node": "Dismiss Item",
"type": "main",
"index": 0
}
]
]
},
"Add Media Item Webhook": {
"main": [
[
{
"node": "Add Media Item",
"type": "main",
"index": 0
}
]
]
},
"Add Media Item": {
"main": [
[
{
"node": "Respond Add Media Item",
"type": "main",
"index": 0
}
]
]
}
},
"settings": {
"executionOrder": "v1",
"callerPolicy": "workflowsFromSameOwner",
"availableInMCP": false
},
"meta": null,
"activeVersionId": "179d9aad-fc54-4554-aff5-0b85b0846a8c",
"versionCounter": 4,
"triggerCount": 5,
"shared": [
{
"updatedAt": "2026-04-27T18:53:40.737Z",
"createdAt": "2026-04-27T18:53:40.737Z",
"role": "workflow:owner",
"workflowId": "4DpoFWCUglQuM4lz",
"projectId": "9sJSA5GTLSjQcRNk",
"project": {
"updatedAt": "2026-03-20T18:09:16.655Z",
"createdAt": "2026-03-20T00:15:30.157Z",
"id": "9sJSA5GTLSjQcRNk",
"name": "Sina Bari <YOUR_EMAIL@example.com>",
"type": "personal",
"icon": null,
"description": null,
"creatorId": "d84a1587-61fd-429c-9ea6-1d21d8267ea9"
}
}
],
"tags": [],
"activeVersion": {
"updatedAt": "2026-04-27T18:53:40.743Z",
"createdAt": "2026-04-27T18:53:40.743Z",
"versionId": "179d9aad-fc54-4554-aff5-0b85b0846a8c",
"workflowId": "4DpoFWCUglQuM4lz",
"nodes": [
{
"id": "media-cron",
"name": "Wednesday Cron Trigger",
"type": "n8n-nodes-base.scheduleTrigger",
"typeVersion": 1.2,
"position": [
200,
300
],
"parameters": {
"rule": {
"interval": [
{
"field": "cronExpression",
"expression": "0 16 * * 3"
}
]
}
}
},
{
"id": "media-webhook",
"name": "Ingest Webhook",
"type": "n8n-nodes-base.webhook",
"typeVersion": 2,
"position": [
200,
500
],
"webhookId": "media-ingest",
"parameters": {
"path": "media-ingest",
"httpMethod": "POST",
"responseMode": "lastNode",
"options": {}
}
},
{
"id": "build-queries",
"name": "Build Tavily Queries",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
500,
400
],
"parameters": {
"jsCode": "const staticData = $getWorkflowStaticData('global');\nif (!staticData.media_items) staticData.media_items = [];\nif (!staticData.processed_urls) staticData.processed_urls = [];\n\nreturn [{ json: {\n tavily_body: JSON.stringify({\n api_key: 'YOUR_TAVILY_API_KEY',\n query: '\"Sina Bari\" OR \"Dr. Sina Bari\" OR \"sinabarimd\" healthcare AI plastic surgery physician executive',\n search_depth: 'advanced',\n max_results: 15,\n include_answer: true,\n include_raw_content: false,\n days: 14,\n }),\n processed_urls: staticData.processed_urls,\n} }];"
}
},
{
"id": "tavily-search",
"name": "Tavily Media Search",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
800,
400
],
"parameters": {
"method": "POST",
"url": "https://api.tavily.com/search",
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "Content-Type",
"value": "application/json"
}
]
},
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={{ JSON.stringify({ api_key: \"YOUR_TAVILY_API_KEY\", query: \"\\\"Sina Bari\\\" OR \\\"Dr. Sina Bari\\\" OR \\\"sinabarimd\\\" healthcare AI physician executive\", search_depth: \"advanced\", max_results: 15, include_answer: true, include_raw_content: false, days: 14 }) }}",
"options": {
"response": {
"response": {
"responseFormat": "json"
}
},
"timeout": 30000
}
}
},
{
"id": "dedup-filter",
"name": "Deduplicate and Filter",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
1100,
400
],
"parameters": {
"jsCode": "const upstream = $('Build Tavily Queries').first().json;\nconst processed_urls = upstream.processed_urls || [];\nconst tavilyResults = $json.results || [];\n\nconst ownDomains = ['sinabarimd.com', 'sinabari.net', 'drsinabari.com', 'sinabariplasticsurgery.com'];\nconst seen = new Set(processed_urls);\nconst filtered = [];\n\nfor (const r of tavilyResults) {\n if (!r.url) continue;\n \n // Check own domain \u2014 simple string includes on the URL\n let isOwn = false;\n for (const d of ownDomains) {\n // Match exact domain (not substrings like \"sinabarimd\" in \"sinabarimd.webflow.io\")\n if (r.url.includes('://' + d + '/') || r.url.includes('://' + d + '\"') || r.url.endsWith('://' + d)) {\n isOwn = true;\n break;\n }\n // Also check www variant\n if (r.url.includes('://www.' + d + '/') || r.url.includes('://www.' + d)) {\n isOwn = true;\n break;\n }\n }\n if (isOwn) continue;\n \n // Simple dedup hash\n const hash = r.url.toLowerCase().replace(/[^a-z0-9]/g, '').slice(0, 40);\n if (seen.has(hash)) continue;\n seen.add(hash);\n \n filtered.push({\n title: r.title || '',\n url: r.url,\n content: (r.content || '').slice(0, 500),\n published_date: r.published_date || null,\n score: r.score || 0,\n url_hash: hash,\n });\n}\n\nreturn [{ json: { filtered_results: filtered, new_count: filtered.length } }];"
}
},
{
"id": "if-new",
"name": "IF: New Items?",
"type": "n8n-nodes-base.if",
"typeVersion": 2,
"position": [
1400,
400
],
"parameters": {
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "loose"
},
"conditions": [
{
"id": "new-check",
"leftValue": "={{ $json.new_count }}",
"rightValue": "0",
"operator": {
"type": "number",
"operation": "gt"
}
}
],
"combinator": "and"
}
}
},
{
"id": "no-new",
"name": "No New Items",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
1700,
550
],
"parameters": {
"jsCode": "const staticData = $getWorkflowStaticData('global');\nstaticData.last_run = new Date().toISOString();\nreturn [{ json: { success: true, message: 'No new media items found', last_run: staticData.last_run } }];"
}
},
{
"id": "build-openclaw",
"name": "Build OpenClaw Request",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
1700,
300
],
"parameters": {
"jsCode": "const { filtered_results, tavily_answer } = $json;\n\nconst resultsText = filtered_results.map((r, i) =>\n `[${i+1}] TITLE: ${r.title}\\n URL: ${r.url}\\n DATE: ${r.published_date || 'unknown'}\\n CONTENT: ${r.content}`\n).join('\\n\\n');\n\nconst prompt = `You are a media monitoring analyst for Dr. Sina Bari, MD \u2014 a physician executive, healthcare AI leader, and plastic surgeon based in California.\n\nAnalyze these search results and extract structured media items. For each genuinely relevant result, produce a JSON object. Skip results that are not actually about or relevant to Dr. Sina Bari or his professional domains.\n\nTAVILY SUMMARY: ${tavily_answer || 'None'}\n\nSEARCH RESULTS:\n${resultsText}\n\nFor each relevant result, output:\n- type: \"news\" | \"publication\" | \"mention\" | \"negative\" | \"award\"\n- title: clean article/mention title\n- url: the source URL\n- source: publication or website name\n- date: YYYY-MM-DD\n- summary: 1-2 sentence factual summary\n- relevance: \"high\" | \"medium\" | \"low\" (negative content = always \"high\")\n- sentiment: \"positive\" | \"neutral\" | \"negative\"\n- target_site_id: \"sinabarimd\" | \"sinabari_net\" | \"sinabariplasticsurgery\" | \"all\"\n- suggested_angle: one sentence on how to reference in content\n\nOutput a JSON array only. No markdown, no commentary. If nothing is relevant, output [].`;\n\nreturn [{ json: {\n ...($json),\n openclaw_request_body: JSON.stringify({ model: 'openclaw', input: prompt }),\n openclawAgentId: 'media-ingestion',\n} }];"
}
},
{
"id": "openclaw-synth",
"name": "OpenClaw Synthesize",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
2000,
300
],
"parameters": {
"method": "POST",
"url": "http://host.docker.internal:18789/v1/responses",
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "Authorization",
"value": "Bearer YOUR_OPENCLAW_KEY"
},
{
"name": "Content-Type",
"value": "application/json"
},
{
"name": "x-openclaw-agent-id",
"value": "={{ $json.openclawAgentId }}"
}
]
},
"sendBody": true,
"contentType": "raw",
"rawContentType": "JSON",
"body": "={{ $json.openclaw_request_body }}",
"options": {}
}
},
{
"id": "parse-store",
"name": "Parse and Store Items",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
2300,
300
],
"parameters": {
"jsCode": "const ctx = $('Build OpenClaw Request').first().json;\nconst rawContent = $json.output?.[0]?.content?.[0]?.text || '';\n\nlet items = [];\ntry {\n const cleaned = rawContent.replace(/```json\\n?/g, '').replace(/```\\n?/g, '').trim();\n const match = cleaned.match(/\\[[\\s\\S]*\\]/);\n items = JSON.parse(match ? match[0] : cleaned);\n if (!Array.isArray(items)) items = [items];\n} catch { items = []; }\n\nconst staticData = $getWorkflowStaticData('global');\nif (!staticData.media_items) staticData.media_items = [];\nif (!staticData.processed_urls) staticData.processed_urls = [];\n\nconst now = new Date().toISOString();\nconst newItems = items.filter(i => i.url && i.title).map(item => ({\n item_id: `media_${Date.now()}_${Math.random().toString(36).slice(2, 8)}`,\n type: item.type || 'mention',\n title: item.title,\n url: item.url,\n source: item.source || 'Unknown',\n date: item.date || now.split('T')[0],\n summary: item.summary || '',\n relevance: item.relevance || 'medium',\n sentiment: item.sentiment || 'neutral',\n target_site_id: item.target_site_id || 'sinabarimd',\n suggested_angle: item.suggested_angle || '',\n consumed: false,\n ingested_at: now,\n}));\n\nstaticData.media_items = [...newItems, ...staticData.media_items].slice(0, 100);\nconst newHashes = (ctx.filtered_results || []).map(r => r.url_hash).filter(Boolean);\nstaticData.processed_urls = [...new Set([...staticData.processed_urls, ...newHashes])].slice(-500);\nstaticData.last_run = now;\n\nconst queuePayload = staticData.media_items.filter(m => !m.consumed);\n\nreturn [{ json: {\n success: true,\n new_item_count: newItems.length,\n total_unconsumed: queuePayload.length,\n negative_items: newItems.filter(i => i.sentiment === 'negative').length,\n items_for_orchestrator: queuePayload,\n} }];"
}
},
{
"id": "queue-orch",
"name": "Queue to Orchestrator",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
2600,
300
],
"parameters": {
"method": "POST",
"url": "https://n8n.sinabarimd.com/webhook/store-media",
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "Content-Type",
"value": "application/json"
}
]
},
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={{ JSON.stringify({ media_items: $json.items_for_orchestrator }) }}",
"options": {
"response": {
"response": {
"responseFormat": "json"
}
},
"timeout": 15000
}
},
"onError": "continueRegularOutput"
},
{
"id": "list-webhook",
"name": "List Items Webhook",
"type": "n8n-nodes-base.webhook",
"typeVersion": 2,
"position": [
200,
700
],
"webhookId": "media-items",
"parameters": {
"path": "media-items",
"httpMethod": "GET",
"responseMode": "lastNode",
"options": {}
}
},
{
"id": "return-items",
"name": "Return Media Items",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
500,
700
],
"parameters": {
"jsCode": "const staticData = $getWorkflowStaticData('global');\nconst items = staticData.media_items || [];\nconst unconsumed = items.filter(m => !m.consumed);\nconst negative = unconsumed.filter(m => m.sentiment === 'negative');\n\nreturn [{ json: {\n last_run: staticData.last_run || 'never',\n total_items: items.length,\n unconsumed_count: unconsumed.length,\n negative_alerts: negative.length,\n negative_items: negative,\n items_by_site: {\n sinabarimd: unconsumed.filter(m => m.target_site_id === 'sinabarimd' || m.target_site_id === 'all'),\n sinabari_net: unconsumed.filter(m => m.target_site_id === 'sinabari_net' || m.target_site_id === 'all'),\n sinabariplasticsurgery: unconsumed.filter(m => m.target_site_id === 'sinabariplasticsurgery' || m.target_site_id === 'all'),\n },\n all_unconsumed: unconsumed,\n} }];"
}
},
{
"id": "dismiss-webhook",
"name": "Dismiss Item Webhook",
"type": "n8n-nodes-base.webhook",
"typeVersion": 2,
"position": [
200,
900
],
"webhookId": "dismiss-media-item",
"parameters": {
"path": "dismiss-media-item",
"httpMethod": "POST",
"responseMode": "lastNode",
"options": {}
}
},
{
"id": "dismiss-code",
"name": "Dismiss Item",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
500,
900
],
"parameters": {
"jsCode": "const body = $json.body || $json;\nconst { item_id } = body;\nif (!item_id) return [{ json: { error: true, message: 'Missing item_id' } }];\nconst staticData = $getWorkflowStaticData('global');\nconst item = (staticData.media_items || []).find(m => m.item_id === item_id);\nif (!item) return [{ json: { error: true, message: 'Item not found' } }];\nitem.consumed = true;\nitem.dismissed_at = new Date().toISOString();\nreturn [{ json: { success: true, item_id, title: item.title } }];"
}
},
{
"id": "add-media-item-wh",
"name": "Add Media Item Webhook",
"type": "n8n-nodes-base.webhook",
"typeVersion": 2,
"position": [
0,
800
],
"webhookId": "add-media-item",
"parameters": {
"httpMethod": "POST",
"path": "add-media-item",
"responseMode": "responseNode",
"options": {}
}
},
{
"id": "add-media-item-handler",
"name": "Add Media Item",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
240,
800
],
"parameters": {
"jsCode": "const body = $json.body || $json;\nconst { url, title, source, date, summary, type, target_site_id, sentiment } = body;\n\nif (!url || !title) {\n return [{ json: { success: false, error: 'Required: url, title' } }];\n}\n\nconst staticData = $getWorkflowStaticData('global');\nif (!staticData.media_items) staticData.media_items = [];\n\nconst item = {\n item_id: 'media_' + Date.now() + '_' + Math.random().toString(36).slice(2, 8),\n type: type || 'mention',\n title,\n url,\n source: source || 'Manual',\n date: date || new Date().toISOString().split('T')[0],\n summary: summary || '',\n relevance: 'high',\n sentiment: sentiment || 'positive',\n target_site_id: target_site_id || 'sinabarimd',\n suggested_angle: '',\n consumed: false,\n ingested_at: new Date().toISOString(),\n manual: true,\n};\n\nstaticData.media_items = [item, ...staticData.media_items].slice(0, 100);\n\nreturn [{ json: { success: true, item_id: item.item_id, title: item.title } }];\n"
}
},
{
"id": "add-media-item-respond",
"name": "Respond Add Media Item",
"type": "n8n-nodes-base.respondToWebhook",
"typeVersion": 1,
"position": [
460,
800
],
"parameters": {
"respondWith": "json",
"responseBody": "={{ JSON.stringify($json) }}"
}
}
],
"connections": {
"Wednesday Cron Trigger": {
"main": [
[
{
"node": "Build Tavily Queries",
"type": "main",
"index": 0
}
]
]
},
"Ingest Webhook": {
"main": [
[
{
"node": "Build Tavily Queries",
"type": "main",
"index": 0
}
]
]
},
"Build Tavily Queries": {
"main": [
[
{
"node": "Tavily Media Search",
"type": "main",
"index": 0
}
]
]
},
"Tavily Media Search": {
"main": [
[
{
"node": "Deduplicate and Filter",
"type": "main",
"index": 0
}
]
]
},
"Deduplicate and Filter": {
"main": [
[
{
"node": "IF: New Items?",
"type": "main",
"index": 0
}
]
]
},
"IF: New Items?": {
"main": [
[
{
"node": "Build OpenClaw Request",
"type": "main",
"index": 0
}
],
[
{
"node": "No New Items",
"type": "main",
"index": 0
}
]
]
},
"Build OpenClaw Request": {
"main": [
[
{
"node": "OpenClaw Synthesize",
"type": "main",
"index": 0
}
]
]
},
"OpenClaw Synthesize": {
"main": [
[
{
"node": "Parse and Store Items",
"type": "main",
"index": 0
}
]
]
},
"Parse and Store Items": {
"main": [
[
{
"node": "Queue to Orchestrator",
"type": "main",
"index": 0
}
]
]
},
"List Items Webhook": {
"main": [
[
{
"node": "Return Media Items",
"type": "main",
"index": 0
}
]
]
},
"Dismiss Item Webhook": {
"main": [
[
{
"node": "Dismiss Item",
"type": "main",
"index": 0
}
]
]
},
"Add Media Item Webhook": {
"main": [
[
{
"node": "Add Media Item",
"type": "main",
"index": 0
}
]
]
},
"Add Media Item": {
"main": [
[
{
"node": "Respond Add Media Item",
"type": "main",
"index": 0
}
]
]
}
},
"authors": "Sina Bari",
"name": null,
"description": null,
"autosaved": false,
"workflowPublishHistory": [
{
"createdAt": "2026-04-27T18:55:20.783Z",
"id": 3,
"workflowId": "4DpoFWCUglQuM4lz",
"versionId": "179d9aad-fc54-4554-aff5-0b85b0846a8c",
"event": "activated",
"userId": "d84a1587-61fd-429c-9ea6-1d21d8267ea9"
}
]
}
}
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
How this works
This workflow automates the ingestion of fresh media content to fuel your reputation engine, ensuring you stay ahead with timely insights into brand mentions and industry trends without manual searching. It's designed for marketing teams or PR professionals who need a reliable stream of relevant articles, videos, and social clips to monitor online reputation. The key step involves querying Tavily's media search API via HTTP requests, followed by intelligent deduplication and filtering to deliver only new, high-quality items for further processing.
Use this workflow when you require scheduled, automated pulls of media data from diverse sources to integrate into analytics dashboards or alert systems, particularly for ongoing reputation tracking. Avoid it if your needs are ad-hoc or involve real-time processing, as the cron trigger suits periodic runs like daily or weekly. Common variations include tweaking the Tavily queries for niche keywords or adding post-ingestion nodes to push filtered content directly into tools like Google Sheets or Slack notifications.
About this workflow
Reputation Engine — Media Ingestion Agent. Uses httpRequest. Scheduled trigger; 18 nodes.
Source: https://github.com/sinabarimd/reputation-engine/blob/main/workflows/media-ingestion-agent.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 Blue Team workflow ingests threat intelligence from public CVE and IOC feeds, merges the data, performs automated triage using OpenAI, and routes actionable alerts via email. 📥 CVE and IOC feeds
HTTP Request, Email Send, Google Sheets
This workflow is designed for developers, data engineers, and AI teams who need to migrate a Pinecone Cloud index into a Weaviate Cloud class index without recalculating the vectors (embeddings). It’s
Airtable, HTTP Request
QFO Rank Tracking - EmbeddingGemma Semantic Dedup & Daily Tracking. Uses googleSheets, httpRequest, googleBigQuery. Scheduled trigger; 16 nodes.
Google Sheets, HTTP Request, Google BigQuery
RAG - Ingesta Automatizada de Documentos. Uses readWriteFile, httpRequest. Scheduled trigger; 5 nodes.
Read Write File, HTTP Request
Supercharge your trading decisions with this end-to-end AI automation that connects market intelligence, technical analysis, and automated trade execution — all without manual intervention.
Tool Think, Supabase Vector Store, OpenAI Embeddings +14