Léo This workflow corresponds to n8n.io template #6616 — we link there as the canonical source.
This workflow follows the Agent → Gmail 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 →
{
"id": "f4VBXUYPlahHX5xf",
"meta": {
"templateId": "6616",
"templateCredsSetupCompleted": true
},
"name": "Automate Weekly Tech Research with Perplexity AI, Notion & Gmail",
"tags": [],
"nodes": [
{
"id": "2e7f82c2-3295-48c2-b0b8-07cc5c3081f7",
"name": "Schedule Trigger",
"type": "n8n-nodes-base.scheduleTrigger",
"position": [
440,
360
],
"parameters": {
"rule": {
"interval": [
{
"field": "weeks",
"triggerAtDay": [
1
],
"triggerAtHour": 9
}
]
}
},
"typeVersion": 1.2
},
{
"id": "88cb0a79-8ba9-4dbd-b65a-15d23844c11e",
"name": "Gmail",
"type": "n8n-nodes-base.gmail",
"position": [
1540,
300
],
"parameters": {
"message": "={{ $json.output }}",
"options": {
"appendAttribution": false
},
"subject": "=Veille technologique du {{ $now.toLocaleString() }}\n\n",
"emailType": "text"
},
"credentials": {
"gmailOAuth2": {
"name": "<your credential>"
}
},
"typeVersion": 2.1
},
{
"id": "1ad5c2a5-3550-4c2a-9e9f-07ef5aa6ef58",
"name": "OpenRouter Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenRouter",
"position": [
760,
880
],
"parameters": {
"model": "perplexity/sonar-deep-research",
"options": {}
},
"credentials": {
"openRouterApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "6cba1d6f-8320-4cd2-8eef-fb781d1c7b6b",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
380,
240
],
"parameters": {
"height": 440,
"content": "## \u23f0 Report Scheduling\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nSet the time when your monitoring workflow will run automatically.\n\n\ud83d\udc49 Currently, the trigger is configured to launch the monitoring every Monday at 9 AM.\n"
},
"typeVersion": 1
},
{
"id": "eaa3c304-1c43-4335-83b1-92745a16221f",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
880,
260
],
"parameters": {
"width": 300,
"height": 460,
"content": "## \ud83e\udd16 Monitoring AI Agent\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nThis is where you define your agent's system prompt.\n\n\ud83d\udc49 Adjust its goals, roles, and behavior based on your desired monitoring strategy.\n\n\n"
},
"typeVersion": 1
},
{
"id": "e93639ac-7e8e-4bc1-a93f-971ed676be59",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
660,
780
],
"parameters": {
"width": 300,
"height": 540,
"content": "## \ud83e\udde0 Language Model\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nDefine the language model your agent will use here.\n\n\ud83d\udc49 In this example, OpenRouter is connected with the DeepSeek (Perplexity Sonar DeepSearch) model to perform advanced and accurate research.\n\nYou only need to connect your own AI credits (OpenAI, Mistral, etc.). \n\u27a1\ufe0f Perplexity is highly recommended for monitoring and research tasks.\n\n"
},
"typeVersion": 1
},
{
"id": "9f4b9831-aa7e-40ba-9711-b525421cba76",
"name": "Notion",
"type": "n8n-nodes-base.notion",
"position": [
1520,
780
],
"parameters": {
"pageId": {
"__rl": true,
"mode": "url",
"value": "https://www.notion.so/Veille-technologique-23ebc16c1a7c807a890ac0e3479ccf5c?source=copy_link"
},
"options": {},
"resource": "databasePage",
"operation": "update"
},
"credentials": {
"notionApi": {
"name": "<your credential>"
}
},
"typeVersion": 2.2
},
{
"id": "d9ee7a17-564d-4752-b2a9-0143e73bcd6a",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
1420,
680
],
"parameters": {
"width": 300,
"height": 480,
"content": "## \ud83d\uddc2\ufe0f Database Selection\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nSelect the database where the results of your weekly monitoring will be automatically stored.\n\n\ud83d\udc49 In this example, Notion is connected: new entries are added or updated automatically.\n"
},
"typeVersion": 1
},
{
"id": "b1644d33-9377-457c-8cc2-250d92ce5e1e",
"name": "AI Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
900,
360
],
"parameters": {
"text": "/<task> \nConduct a technology watch on recent and innovative artificial intelligence tools. \nYou must research, identify, and present a selection of tools that have been launched or have gained popularity in the past 3 months. \nThe goal is to discover useful, lesser-known solutions with high potential for professionals and businesses. \n</task>\n\n/<sources> \nInclude https://theresanaiforthat.com/ as **one** of the possible sources. \nYou are also required to explore other reliable sources: specialized AI blogs, press releases, tech forums, product launch platforms, no-code communities. \n</sources>\n\n/<guidelines> \n1. Exclude already well-known tools (e.g., ChatGPT, Midjourney, Notion AI, etc.). \n2. Focus on tools for professional use: automation, productivity, analytics, content generation. \n3. Favor tools that are no-code or easy to use by non-technical teams. \n4. Prioritize tools that are publicly available and active (no early-stage concepts or closed prototypes). \n5. Provide up-to-date results, specifically from the last 3 months. \n</guidelines>\n\n/<output-format> \nFor each selected tool, provide: \n- Tool name \n- Official link or presentation page \n- Clear summary of how it works (2 to 4 lines max) \n- 1 or 2 concrete examples of professional use \n- What makes the tool stand out and its main benefits \n- Specify whether the information comes from theresanaiforthat.com or another verified source \n</output-format>\n\n/<volume> \nLimit to **10 tools maximum**, selected for their relevance and added value. \nQuality > Quantity. \n</volume>\n\n/<language> \nAll results must be written in English, even if the tools or sources are in another language. \n</language>\n",
"options": {},
"promptType": "define"
},
"typeVersion": 1.8
},
{
"id": "ff4ef06f-0b9f-463e-bb2e-142e56697ef2",
"name": "Think",
"type": "@n8n/n8n-nodes-langchain.toolThink",
"position": [
1160,
920
],
"parameters": {
"description": "### \ud83e\udde0 Tool: Think (Internal Reflection)\n\nUse this tool when the agent needs to **think internally**, without performing any actions or querying external sources. \nIt does **not retrieve any new information** and does **not modify any database** \u2014 it simply **adds a thought to the internal log**.\n\n\ud83d\udee0 Recommended for:\n- Complex reasoning steps \n- Internal decision-making \n- Managing short-term memory between actions\n"
},
"typeVersion": 1
},
{
"id": "9ce8d98f-1f37-4308-b5eb-93e6c503c51a",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
1080,
820
],
"parameters": {
"height": 440,
"content": "## \ud83e\udde9 Internal Thinking Tool\n\n\n\n\n\n\n\n\n\n\n\nThis node allows the agent to express a thought without interacting with external sources or modifying the database.\n\n\ud83d\udc49 Use it when the agent needs to structure a thought, engage short-term memory, or perform complex reasoning.\n"
},
"typeVersion": 1
},
{
"id": "c83c5c19-f0ee-46c0-a800-69d906dadb2b",
"name": "Sticky Note5",
"type": "n8n-nodes-base.stickyNote",
"position": [
1480,
180
],
"parameters": {
"height": 460,
"content": "## \ud83d\udcec Automatic Report Delivery\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nThis module handles the email sending of the generated monitoring results.\n\n\ud83d\udc49 The report is automatically sent to the configured recipients once the monitoring is complete.\n\n"
},
"typeVersion": 1
}
],
"active": false,
"settings": {},
"versionId": "6d913fbc-919f-49f4-9d3d-4502ec8fbc04",
"connections": {
"Gmail": {
"main": [
[]
]
},
"Think": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"AI Agent": {
"main": [
[
{
"node": "Notion",
"type": "main",
"index": 0
},
{
"node": "Gmail",
"type": "main",
"index": 0
}
]
]
},
"Schedule Trigger": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"OpenRouter Chat Model": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
}
}
}
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.
gmailOAuth2notionApiopenRouterApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Scheduled Trigger Every Monday at 9 AM, the workflow starts automatically. AI Agent Configuration A system prompt defines the role, objectives, and behavior of your AI agent for web monitoring or research tasks. Language Model via OpenRouter The agent uses a powerful model…
Source: https://n8n.io/workflows/6616/ — 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 automatically processes your industry newsletters and creates AI-powered intelligence briefs that filter signal from noise. Perfect for busy professionals who need to stay informed w
Gmail, Agent, Slack +5
Who is this for? Agencies, consultants, and service providers who conduct discovery calls and need to quickly turn conversations into professional proposals.
Tool Think, Tool Calculator, Agent Tool +18
R34 | VeoRobo Template (3 scenes) by RoboNuggets. Uses scheduleTrigger, lmChatOpenRouter, toolThink, agent. Scheduled trigger; 26 nodes.
OpenRouter Chat, Tool Think, Agent +3
2-Utility-SaveInvoices_template. Uses agent, googleSheets, httpRequest, googleDrive. Scheduled trigger; 26 nodes.
Agent, Google Sheets, HTTP Request +4
Aggregates communication data from Slack, Microsoft Teams, Gmail, GitHub, and Confluence into a single, unified AI-powered analysis workflow designed for quality review and automated documentation upd
Slack, Microsoft Teams, Gmail +6