{ "id": "J5NwzcdqWOHJbH5y", "meta": { "templateCredsSetupCompleted": true }, "name": "Autonomous AI Crawler", "tags": [], "nodes": [ { "id": "e2ec4c3c-940e-4993-908d-9d515e6e5816", "name": "Text", "type": "@n8n/n8n-nodes-langchain.toolWorkflow", "position": [ -512, 1072 ], "parameters": { "name": "text_retrieval_tool", "source": "parameter", "description": "Call this tool to return all text from the given website. Query should be full website URL.", "workflowJson": "{\n \"nodes\": [\n {\n \"parameters\": {},\n \"id\": \"05107436-c9cb-419b-ae8a-b74d309a130d\",\n \"name\": \"Execute workflow\",\n \"type\": \"n8n-nodes-base.manualTrigger\",\n \"typeVersion\": 1,\n \"position\": [\n 2220,\n 620\n ]\n },\n {\n \"parameters\": {\n \"assignments\": {\n \"assignments\": [\n {\n \"id\": \"253c2b17-c749-4f0a-93e8-5ff74f1ce49b\",\n \"name\": \"domain\",\n \"value\": \"={{ $json.query }}\",\n \"type\": \"string\"\n }\n ]\n },\n \"options\": {}\n },\n \"id\": \"bb8be616-3227-4705-8520-1827069faacd\",\n \"name\": \"Set domain\",\n \"type\": \"n8n-nodes-base.set\",\n \"typeVersion\": 3.3,\n \"position\": [\n 2440,\n 620\n ]\n },\n {\n \"parameters\": {\n \"assignments\": {\n \"assignments\": [\n {\n \"id\": \"ed0f1505-82b6-4393-a0d8-088055137ec9\",\n \"name\": \"domain\",\n \"value\": \"={{ $json.domain.startsWith(\\\"http\\\") ? $json.domain : \\\"http://\\\" + $json.domain }}\",\n \"type\": \"string\"\n }\n ]\n },\n \"options\": {}\n },\n \"id\": \"bdf29340-f135-489f-848e-1c7fa43a01df\",\n \"name\": \"Add protocool to domain\",\n \"type\": \"n8n-nodes-base.set\",\n \"typeVersion\": 3.3,\n \"position\": [\n 2640,\n 620\n ]\n },\n {\n \"parameters\": {\n \"assignments\": {\n \"assignments\": [\n {\n \"id\": \"2b1c7ff8-06a7-448b-99b7-5ede4b2e0bf0\",\n \"name\": \"response\",\n \"value\": \"={{ $json.data }}\",\n \"type\": \"string\"\n }\n ]\n },\n \"options\": {}\n },\n \"id\": \"9f0aa264-08c1-459a-bb99-e28599fe8f76\",\n \"name\": \"Set response\",\n \"type\": \"n8n-nodes-base.set\",\n \"typeVersion\": 3.3,\n \"position\": [\n 3300,\n 620\n ]\n },\n {\n \"parameters\": {\n \"url\": \"={{ $json.domain }}\",\n \"options\": {}\n },\n \"id\": \"cec7c8e8-bf5e-43d5-aa41-876293dbec78\",\n \"name\": \"Get website\",\n \"type\": \"n8n-nodes-base.httpRequest\",\n \"typeVersion\": 4.2,\n \"position\": [\n 2860,\n 620\n ]\n },\n {\n \"parameters\": {\n \"html\": \"={{ $json.data }}\",\n \"options\": {\n \"ignore\": \"a,img\"\n }\n },\n \"id\": \"1af94fcb-bca3-45c4-9277-18878c75d417\",\n \"name\": \"Convert HTML to Markdown\",\n \"type\": \"n8n-nodes-base.markdown\",\n \"typeVersion\": 1,\n \"position\": [\n 3080,\n 620\n ]\n }\n ],\n \"connections\": {\n \"Execute workflow\": {\n \"main\": [\n [\n {\n \"node\": \"Set domain\",\n \"type\": \"main\",\n \"index\": 0\n }\n ]\n ]\n },\n \"Set domain\": {\n \"main\": [\n [\n {\n \"node\": \"Add protocool to domain\",\n \"type\": \"main\",\n \"index\": 0\n }\n ]\n ]\n },\n \"Add protocool to domain\": {\n \"main\": [\n [\n {\n \"node\": \"Get website\",\n \"type\": \"main\",\n \"index\": 0\n }\n ]\n ]\n },\n \"Get website\": {\n \"main\": [\n [\n {\n \"node\": \"Convert HTML to Markdown\",\n \"type\": \"main\",\n \"index\": 0\n }\n ]\n ]\n },\n \"Convert HTML to Markdown\": {\n \"main\": [\n [\n {\n \"node\": \"Set response\",\n \"type\": \"main\",\n \"index\": 0\n }\n ]\n ]\n }\n },\n \"pinData\": {}\n}" }, "typeVersion": 1.1 }, { "id": "e47a5b79-c589-4350-90a7-6a3bff079ec6", "name": "URLs", "type": "@n8n/n8n-nodes-langchain.toolWorkflow", "position": [ -336, 1072 ], "parameters": { "name": "url_retrieval_tool", "source": "parameter", "description": "Call this tool to return all URLs from the given website. Query should be full website URL.", "workflowJson": "{\n \"nodes\": [\n {\n \"parameters\": {},\n \"id\": \"05107436-c9cb-419b-ae8a-b74d309a130d\",\n \"name\": \"Execute workflow\",\n \"type\": \"n8n-nodes-base.manualTrigger\",\n \"typeVersion\": 1,\n \"position\": [\n 2200,\n 740\n ]\n },\n {\n \"parameters\": {\n \"operation\": \"extractHtmlContent\",\n \"extractionValues\": {\n \"values\": [\n {\n \"key\": \"output\",\n \"cssSelector\": \"a\",\n \"returnValue\": \"attribute\",\n \"returnArray\": true\n }\n ]\n },\n \"options\": {}\n },\n \"id\": \"1972e13e-d923-45e8-9752-e4bf45faaccf\",\n \"name\": \"Retrieve URLs\",\n \"type\": \"n8n-nodes-base.html\",\n \"typeVersion\": 1.2,\n \"position\": [\n 3060,\n 740\n ]\n },\n {\n \"parameters\": {\n \"fieldToSplitOut\": \"output\",\n \"options\": {}\n },\n \"id\": \"19703fbc-05ff-4d80-ab53-85ba6d39fc3f\",\n \"name\": \"Split out URLs\",\n \"type\": \"n8n-nodes-base.splitOut\",\n \"typeVersion\": 1,\n \"position\": [\n 3280,\n 740\n ]\n },\n {\n \"parameters\": {\n \"compare\": \"selectedFields\",\n \"fieldsToCompare\": \"href\",\n \"options\": {}\n },\n \"id\": \"5cc988e7-de9b-4177-b5e7-edb3842202c8\",\n \"name\": \"Remove duplicated\",\n \"type\": \"n8n-nodes-base.removeDuplicates\",\n \"typeVersion\": 1,\n \"position\": [\n 3720,\n 740\n ]\n },\n {\n \"parameters\": {\n \"assignments\": {\n \"assignments\": [\n {\n \"id\": \"04ced063-09f0-496c-9b28-b8095f9e2297\",\n \"name\": \"href\",\n \"value\": \"={{ $json.href.startsWith(\\\"/\\\") ? $('Add protocool to domain (URL)').item.json[\\\"domain\\\"] + $json.href : $json.href }}\",\n \"type\": \"string\"\n }\n ]\n },\n \"includeOtherFields\": true,\n \"include\": \"selected\",\n \"includeFields\": \"title\",\n \"options\": {}\n },\n \"id\": \"4715a25d-93a7-4056-8768-e3f886a1a0c9\",\n \"name\": \"Set domain to path\",\n \"type\": \"n8n-nodes-base.set\",\n \"typeVersion\": 3.3,\n \"position\": [\n 3940,\n 740\n ]\n },\n {\n \"parameters\": {\n \"conditions\": {\n \"options\": {\n \"caseSensitive\": true,\n \"leftValue\": \"\",\n \"typeValidation\": \"strict\"\n },\n \"conditions\": [\n {\n \"id\": \"d01ea6a8-7e75-40d4-98f2-25d42b245f36\",\n \"leftValue\": \"={{ $json.href.isUrl() }}\",\n \"rightValue\": \"\",\n \"operator\": {\n \"type\": \"boolean\",\n \"operation\": \"true\",\n \"singleValue\": true\n }\n }\n ],\n \"combinator\": \"and\"\n },\n \"options\": {}\n },\n \"id\": \"353deefb-ae69-440c-95b6-fdadacf4bf91\",\n \"name\": \"Filter out invalid URLs\",\n \"type\": \"n8n-nodes-base.filter\",\n \"typeVersion\": 2,\n \"position\": [\n 4160,\n 740\n ]\n },\n {\n \"parameters\": {\n \"aggregate\": \"aggregateAllItemData\",\n \"include\": \"specifiedFields\",\n \"fieldsToInclude\": \"title,href\",\n \"options\": {}\n },\n \"id\": \"9f87be8c-72d7-4ab1-b297-dc7069b2dd11\",\n \"name\": \"Aggregate URLs\",\n \"type\": \"n8n-nodes-base.aggregate\",\n \"typeVersion\": 1,\n \"position\": [\n 4380,\n 740\n ]\n },\n {\n \"parameters\": {\n \"conditions\": {\n \"options\": {\n \"caseSensitive\": true,\n \"leftValue\": \"\",\n \"typeValidation\": \"strict\"\n },\n \"conditions\": [\n {\n \"id\": \"5b9b7353-bd04-4af2-9480-8de135ff4223\",\n \"leftValue\": \"={{ $json.href }}\",\n \"rightValue\": \"\",\n \"operator\": {\n \"type\": \"string\",\n \"operation\": \"exists\",\n \"singleValue\": true\n }\n }\n ],\n \"combinator\": \"and\"\n },\n \"options\": {}\n },\n \"id\": \"35c8323a-5350-403a-9c2d-114b0527e395\",\n \"name\": \"Filter out empty hrefs\",\n \"type\": \"n8n-nodes-base.filter\",\n \"typeVersion\": 2,\n \"position\": [\n 3500,\n 740\n ]\n },\n {\n \"parameters\": {\n \"assignments\": {\n \"assignments\": [\n {\n \"id\": \"253c2b17-c749-4f0a-93e8-5ff74f1ce49b\",\n \"name\": \"domain\",\n \"value\": \"={{ $json.query }}\",\n \"type\": \"string\"\n }\n ]\n },\n \"options\": {}\n },\n \"id\": \"d9f6a148-6c8c-4a58-89f5-4e9cfcd8d910\",\n \"name\": \"Set domain (URL)\",\n \"type\": \"n8n-nodes-base.set\",\n \"typeVersion\": 3.3,\n \"position\": [\n 2400,\n 740\n ]\n },\n {\n \"parameters\": {\n \"assignments\": {\n \"assignments\": [\n {\n \"id\": \"ed0f1505-82b6-4393-a0d8-088055137ec9\",\n \"name\": \"domain\",\n \"value\": \"={{ $json.domain.startsWith(\\\"http\\\") ? $json.domain : \\\"http://\\\" + $json.domain }}\",\n \"type\": \"string\"\n }\n ]\n },\n \"options\": {}\n },\n \"id\": \"1f974444-da58-4a47-a9c3-ba3091fc1e96\",\n \"name\": \"Add protocool to domain (URL)\",\n \"type\": \"n8n-nodes-base.set\",\n \"typeVersion\": 3.3,\n \"position\": [\n 2620,\n 740\n ]\n },\n {\n \"parameters\": {\n \"url\": \"={{ $json.domain }}\",\n \"options\": {}\n },\n \"id\": \"31d7c7d4-8f61-402b-858d-63dd68ac69ee\",\n \"name\": \"Get website (URL)\",\n \"type\": \"n8n-nodes-base.httpRequest\",\n \"typeVersion\": 4.2,\n \"position\": [\n 2840,\n 740\n ]\n },\n {\n \"parameters\": {\n \"assignments\": {\n \"assignments\": [\n {\n \"id\": \"53c1c016-7983-4eba-a91d-da2a0523d805\",\n \"name\": \"response\",\n \"value\": \"={{ JSON.stringify($json.data) }}\",\n \"type\": \"string\"\n }\n ]\n },\n \"options\": {}\n },\n \"id\": \"f4b6df77-96be-4b12-9a8b-ae9b7009f13d\",\n \"name\": \"Set response (URL)\",\n \"type\": \"n8n-nodes-base.set\",\n \"typeVersion\": 3.3,\n \"position\": [\n 4600,\n 740\n ]\n }\n ],\n \"connections\": {\n \"Execute workflow\": {\n \"main\": [\n [\n {\n \"node\": \"Set domain (URL)\",\n \"type\": \"main\",\n \"index\": 0\n }\n ]\n ]\n },\n \"Retrieve URLs\": {\n \"main\": [\n [\n {\n \"node\": \"Split out URLs\",\n \"type\": \"main\",\n \"index\": 0\n }\n ]\n ]\n },\n \"Split out URLs\": {\n \"main\": [\n [\n {\n \"node\": \"Filter out empty hrefs\",\n \"type\": \"main\",\n \"index\": 0\n }\n ]\n ]\n },\n \"Remove duplicated\": {\n \"main\": [\n [\n {\n \"node\": \"Set domain to path\",\n \"type\": \"main\",\n \"index\": 0\n }\n ]\n ]\n },\n \"Set domain to path\": {\n \"main\": [\n [\n {\n \"node\": \"Filter out invalid URLs\",\n \"type\": \"main\",\n \"index\": 0\n }\n ]\n ]\n },\n \"Filter out invalid URLs\": {\n \"main\": [\n [\n {\n \"node\": \"Aggregate URLs\",\n \"type\": \"main\",\n \"index\": 0\n }\n ]\n ]\n },\n \"Aggregate URLs\": {\n \"main\": [\n [\n {\n \"node\": \"Set response (URL)\",\n \"type\": \"main\",\n \"index\": 0\n }\n ]\n ]\n },\n \"Filter out empty hrefs\": {\n \"main\": [\n [\n {\n \"node\": \"Remove duplicated\",\n \"type\": \"main\",\n \"index\": 0\n }\n ]\n ]\n },\n \"Set domain (URL)\": {\n \"main\": [\n [\n {\n \"node\": \"Add protocool to domain (URL)\",\n \"type\": \"main\",\n \"index\": 0\n }\n ]\n ]\n },\n \"Add protocool to domain (URL)\": {\n \"main\": [\n [\n {\n \"node\": \"Get website (URL)\",\n \"type\": \"main\",\n \"index\": 0\n }\n ]\n ]\n },\n \"Get website (URL)\": {\n \"main\": [\n [\n {\n \"node\": \"Retrieve URLs\",\n \"type\": \"main\",\n \"index\": 0\n }\n ]\n ]\n }\n },\n \"pinData\": {}\n}" }, "typeVersion": 1.1 }, { "id": "8f422426-17c5-478d-ac94-f0a78822d40e", "name": "OpenAI Chat Model", "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi", "position": [ -672, 1072 ], "parameters": { "model": "gpt-4o", "options": { "temperature": 0, "responseFormat": "json_object" } }, "typeVersion": 1 }, { "id": "09db3556-ca91-4c26-8659-ac81f4f038c3", "name": "JSON Parser", "type": "@n8n/n8n-nodes-langchain.outputParserStructured", "position": [ -176, 1072 ], "parameters": { "schemaType": "manual", "inputSchema": "{\n \"type\": \"object\",\n \"properties\": {\n \"social_media\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"object\",\n \"properties\": {\n \"platform\": {\n \"type\": \"string\",\n \"description\": \"The name of the social media platform (e.g., LinkedIn, Instagram)\"\n },\n \"urls\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\",\n \"format\": \"uri\",\n \"description\": \"A URL for the social media platform\"\n }\n }\n },\n \"required\": [\"platform\", \"urls\"],\n \"additionalProperties\": false\n }\n }\n },\n \"required\": [\"platforms\"],\n \"additionalProperties\": false\n}\n" }, "typeVersion": 1.2 }, { "id": "40b3d61d-c058-4afc-ac6f-c6c9205e5351", "name": "Map company name and website", "type": "n8n-nodes-base.set", "position": [ -464, 528 ], "parameters": { "options": {}, "assignments": { "assignments": [ { "id": "ae484e44-36bc-4d88-9772-545e579a261c", "name": "company_name", "type": "string", "value": "={{ $json.name }}" }, { "id": "c426ab19-649c-4443-aabb-eb0826680452", "name": "company_website", "type": "string", "value": "={{ $json.website }}" } ] } }, "typeVersion": 3.3 }, { "id": "a561cf9b-3cf8-4776-a6f7-6e32263574ca", "name": "Execute workflow", "type": "n8n-nodes-base.manualTrigger", "position": [ -1536, 752 ], "parameters": {}, "typeVersion": 1 }, { "id": "f817872b-b5b4-4392-b630-c9e42d1bc90e", "name": "Get companies", "type": "n8n-nodes-base.supabase", "position": [ -1296, 752 ], "parameters": { "tableId": "companies_input", "operation": "getAll" }, "typeVersion": 1 }, { "id": "8ca87503-35d3-4016-911a-77d25287171c", "name": "Select company name and website", "type": "n8n-nodes-base.set", "position": [ -1040, 752 ], "parameters": { "include": "selected", "options": {}, "assignments": { "assignments": [] }, "includeFields": "name,website", "includeOtherFields": true }, "typeVersion": 3.3 }, { "id": "1c59b72e-f9a7-41fc-8bae-d15a51175e4c", "name": "Set social media array", "type": "n8n-nodes-base.set", "position": [ -176, 816 ], "parameters": { "options": {}, "assignments": { "assignments": [ { "id": "a6e109b7-9333-44e8-aa13-590aeb91a56b", "name": "social_media", "type": "array", "value": "={{ $json.output.social_media }}" } ] } }, "typeVersion": 3.3 }, { "id": "4a3bf11e-ffae-4b3a-bd91-34374d9af5e9", "name": "Merge all data", "type": "n8n-nodes-base.merge", "position": [ 80, 720 ], "parameters": { "mode": "combine", "options": {}, "combinationMode": "mergeByPosition" }, "typeVersion": 2.1 }, { "id": "79d96472-bca6-4b17-8040-729d8ea7f411", "name": "Insert new row", "type": "n8n-nodes-base.supabase", "position": [ 320, 720 ], "parameters": { "tableId": "companies_output", "dataToSend": "autoMapInputData" }, "typeVersion": 1 }, { "id": "5929dc22-4ed0-4a08-bc3f-5c918c10dda0", "name": "Crawl website", "type": "@n8n/n8n-nodes-langchain.agent", "position": [ -576, 816 ], "parameters": { "text": "=Retrieve social media profile URLs from this website: {{ $json.website }}", "options": { "systemMessage": "You are an automated web crawler tasked with extracting social media URLs from a webpage provided by the user. You have access to a text retrieval tool to gather all text content from the page and a URL retrieval tool to identify and navigate through links on the page. Utilize the URLs retrieved to crawl additional pages. Your objective is to provide a unified JSON output containing the extracted data (links to all possible social media profiles from the website)." }, "promptType": "define", "hasOutputParser": true }, "retryOnFail": true, "typeVersion": 1.6 }, { "id": "8063a285-0f0e-4f76-bb1a-dbbc5d8beee4", "name": "Main Overview", "type": "n8n-nodes-base.stickyNote", "position": [ -2256, 720 ], "parameters": { "color": 7, "width": 580, "height": 1688, "content": "## \ud83d\udd77\ufe0f Autonomous AI Crawler\n\nAn AI agent autonomously visits each company website, follows internal links, and extracts social media profile URLs into a clean JSON structure, then writes the results back to your database.\n\n**Perfect for:** Growth, sales-ops, and lead-enrichment teams who need to enrich a company list with social profiles at scale.\n\n---\n\n## How it works\n\n1. **Execute workflow** \u2014 Manual trigger that starts the run.\n2. **Get companies** \u2014 Pulls company name and website rows from a Supabase table.\n3. **Select company name and website** \u2014 Keeps only the `name` and `website` fields to pass downstream.\n4. **Crawl website** \u2014 The AI agent that drives the crawl, calling its tools until it has the social links.\n5. **OpenAI Chat Model** \u2014 GPT-4o brain for the agent, set to temperature 0 and JSON response mode.\n6. **Text** \u2014 `text_retrieval_tool`; returns all readable text from a given page.\n7. **URLs** \u2014 `url_retrieval_tool`; returns all links found on a given page so the agent can navigate.\n8. **JSON Parser** \u2014 Structured output parser that forces the agent's answer into a fixed social-links schema.\n9. **Map company name and website** \u2014 Carries the original company name and website forward in parallel.\n10. **Set social media array** \u2014 Shapes the agent's extracted profiles into an array field.\n11. **Merge all data** \u2014 Combines the mapped company info with the extracted social media array.\n12. **Insert new row** \u2014 Writes the enriched record back into Supabase.\n\n**Text scraper tool** *(called by the agent)*\n13. **Set domain (text)** \u2014 Reads the requested URL from the agent's query.\n14. **Add protocool to domain (text)** \u2014 Prepends `http://` if no protocol is present.\n15. **Get website (text)** \u2014 HTTP request that fetches the raw page HTML.\n16. **Convert HTML to Markdown** \u2014 Strips links and images, returns clean readable text.\n17. **Set response (text)** \u2014 Returns the text payload to the agent.\n\n**URL scraper tool** *(called by the agent)*\n18. **Set domain (URL)** \u2014 Reads the requested URL from the agent's query.\n19. **Add protocool to domain (URL)** \u2014 Prepends `http://` if missing.\n20. **Get website (URL)** \u2014 HTTP request that fetches the raw page HTML.\n21. **Retrieve URLs** \u2014 Extracts every `` href from the HTML.\n22. **Split out URLs** \u2014 Splits the href array into individual items.\n23. **Filter out empty hrefs** \u2014 Drops items with no link.\n24. **Remove duplicated** \u2014 Removes duplicate hrefs.\n25. **Set domain to path** \u2014 Resolves relative `/path` links into absolute URLs.\n26. **Filter out invalid URLs** \u2014 Keeps only well-formed URLs.\n27. **Aggregate URLs** \u2014 Collects all valid links back into one list.\n28. **Set response (URL)** \u2014 Returns the link list to the agent.\n\n---\n\n## Setup (~10 minutes)\n\n1. **Supabase** \u2014 Add your credential in the *Get companies* and *Insert new row* nodes, and point them at your company table.\n2. **OpenAI** \u2014 Add your API key in the *OpenAI Chat Model* node (uses GPT-4o).\n3. **Field names** \u2014 If your table does not use `name` and `website`, update the *Select company name and website* node to match.\n> Crawling unfamiliar sites can hit rate limits or blocks. Consider adding a proxy to the *Get website (text)* and *Get website (URL)* HTTP nodes for reliable crawling. OpenAI usage is billed per token.\n" }, "typeVersion": 1 }, { "id": "3a9bad9d-e3fd-4242-be93-13888dc24ded", "name": "Section - Trigger & Intake", "type": "n8n-nodes-base.stickyNote", "position": [ -1648, 592 ], "parameters": { "color": 5, "width": 760, "height": 360, "content": "## 1\ufe0f\u20e3 Trigger & Company Intake\n\nThe **Execute workflow** trigger starts the run and **Get companies** pulls the list of company names and websites from your Supabase table. **Select company name and website** trims each record down to just the `name` and `website` fields before handing them to the crawling agent.\n" }, "typeVersion": 1 }, { "id": "7dc5f0d9-ad2e-4bfa-aeef-a9657a775ff1", "name": "Section - AI Agent", "type": "n8n-nodes-base.stickyNote", "position": [ -832, 176 ], "parameters": { "color": 3, "width": 820, "height": 1072, "content": "## 2\ufe0f\u20e3 AI Crawling Agent\n\n**Crawl website** is the autonomous agent that navigates each site to find social media profile links. It thinks with the **OpenAI Chat Model** (GPT-4o), gathers page content through the **Text** and **URLs** tools, and is forced into a clean JSON structure by the **JSON Parser**. In parallel, **Map company name and website** preserves the original company details, and **Set social media array** shapes the agent's findings into an array.\n" }, "typeVersion": 1 }, { "id": "2e04f241-ceea-46ab-9b22-0e8c5347f1d5", "name": "Section - Output & Logging", "type": "n8n-nodes-base.stickyNote", "position": [ 32, 496 ], "parameters": { "color": 4, "width": 520, "height": 424, "content": "## 3\ufe0f\u20e3 Output & Logging\n\n**Merge all data** combines the preserved company name and website with the social media array extracted by the agent into a single record. **Insert new row** then writes that enriched record back into your Supabase table.\n" }, "typeVersion": 1 } ], "active": false, "settings": { "binaryMode": "separate", "executionOrder": "v1" }, "versionId": "1b4f0bd9-306a-4fc1-a95c-e708e5517203", "nodeGroups": [], "connections": { "Text": { "ai_tool": [ [ { "node": "Crawl website", "type": "ai_tool", "index": 0 } ] ] }, "URLs": { "ai_tool": [ [ { "node": "Crawl website", "type": "ai_tool", "index": 0 } ] ] }, "JSON Parser": { "ai_outputParser": [ [ { "node": "Crawl website", "type": "ai_outputParser", "index": 0 } ] ] }, "Crawl website": { "main": [ [ { "node": "Set social media array", "type": "main", "index": 0 } ] ] }, "Get companies": { "main": [ [ { "node": "Select company name and website", "type": "main", "index": 0 } ] ] }, "Merge all data": { "main": [ [ { "node": "Insert new row", "type": "main", "index": 0 } ] ] }, "Execute workflow": { "main": [ [ { "node": "Get companies", "type": "main", "index": 0 } ] ] }, "OpenAI Chat Model": { "ai_languageModel": [ [ { "node": "Crawl website", "type": "ai_languageModel", "index": 0 } ] ] }, "Set social media array": { "main": [ [ { "node": "Merge all data", "type": "main", "index": 1 } ] ] }, "Map company name and website": { "main": [ [ { "node": "Merge all data", "type": "main", "index": 0 } ] ] }, "Select company name and website": { "main": [ [ { "node": "Crawl website", "type": "main", "index": 0 }, { "node": "Map company name and website", "type": "main", "index": 0 } ] ] } } }