by InfraNodus
Teach your AI agent HOW to think, not WHAT to think This workflow demonstrates how you can build an AI agent in n8n that uses the reasoning logic you define. So an LLM learns a way of thinking, which you can then apply to multiple problems: Make an AI chatbot that knows how to convince anybody using the "Getting to Yes" method Build an LLM workflow that uses Ray Dalio's principles to spot investment opportunities Create an AI agent crew of interdisciplinary thinkers: e.g. a specialist in psychology who gives an advice on education programmes. How it works This template uses the n8n AI agent node as an orchestrating agent that has access to a certain reasoning logic defined by an InfraNodus knowledge graph. This graph contains a list of reasoning rules (ontology), which is extracted to provide an advice that is relevant to the original prompt. It uses GraphRAG under the hood to traverse the parts of the graph relevant to the query. This advice and the reasoning logic extracted is then used by the AI agent to generate a response that is relevant to the user's query but that uses the reasoning logic provided through the graph. Here's a description step by step: The user submits a question using the AI chatbot (n8n interface, in this case, a web form that can be embedded to any website, or a webhook that can be connected to a Telegram / WhatsApp bot) The AI agent node accesses the Reasoning Logic HTTP InfraNodus nodes. The description of AI agent and the description of the reasoning InfraNodus node provides the agent with an understanding of how to rephrase the original question to retrieve relevant reasoning logic. The request is sent to the InfraNodus node. It provides a response that contains the reasoning logic needed to answer the question. This reasoning logic is then sent back to an LLM along with the original query to produce the response. InfraNodus uses GraphRAG under the hood: convert user query into graph find the overlap with the reasoning graph (using n=1 or more hops to include more relations) use similarity search to get additional parts of the graph generate a response based on this intersection as well as the context provided provide information about the underlying structure How to use You need an InfraNodus account to use this workflow. Create an InfraNodus account Get the API key at https://infranodus.com/api-access and create a Bearer authorization key for the InfraNodus HTTP nodes. Create a separate knowledge graph for the reasoning logic Use the AI ontology creator to generate an ontology for a certain topic or text using AI. Then augment it with your own data. See our help article on creating ontologies for detailed instructions For each graph, go to the workflow, paste the name of the graph into the request JSON body name field. Change the system prompt in the AI agent node to reflect the nature of your reasoning logic. For instance, if it's an expert in interactions, you specify that, if it's a psychology expert, you need to specify that as well. Change the description of the reasoning node (HTTP tool). Use the InfraNodus summary and Project Notes > RAG prompt buttons to generate a description for the reasoning logic, which you can then reuse in your workflow. add the LLM key to the OpenAI node (or to the model of your choice) and launch the workflow Requirements An InfraNodus account and API key An OpenAI (or any other LLM) API key Customizing this workflow You can use this same workflow with a Telegram bot, so you can interact with it using Telegram. There are many more customizations available. Check out the complete guide at https://support.noduslabs.com/hc/en-us/articles/21429518472988-Using-Knowledge-Graphs-as-Reasoning-Experts Also check out the video tutorial with a demo:
by Parth Pansuriya
Automate SEO Blog Creation with Apify + Google Docs + KIE AI’s Nano Banana API Who’s it for For content creators, SEO specialists, and digital marketers who want to automatically generate SEO-optimized blog posts from trending topics — no manual writing or formatting required. How it works / What it does This workflow turns trending searches into fully structured blog posts using AI: Fetch trending topics from India (or any country) using Apify’s Google Trends scraper. Generate a SEO-optimized blog post with title, meta description, headings, and long-form content using Gemini AI. Refine the System Message (optional) with Gemini AI for better readability and engagement. Create a custom blog image using KIE AI’s Nano Banana API based on the blog title. Automatically insert all content and images into a Google Doc, ready for publishing. How to set up Add your Apify API token in the Google Trends node. Configure Google Docs OAuth2 credentials for the document update node. Add your KIE AI Nano Banana API token for image generation. Schedule the Daily Trigger to your preferred time (default is 8 AM). Requirements Apify API token (for trending search scraping) Google account with Docs access KIE AI Nano Banana API token How to customize the workflow Change country or timeframe for trending searches. Update the AI prompt for tone, length, or style of the blog. Change the Google Doc ID to insert content into a different document. Adjust image generation settings (size, style) in the KIE AI node.
by Parth Pansuriya
Create UGC Style Product Ad Video via Telegram + Gemini + Kie.ai’s Veo3.1 API Who’s it for For creators, marketers, and e-commerce sellers who want to instantly generate short UGC-style product videos from a simple Telegram message — no manual editing or video skills required. How it works / What it does This workflow automatically turns a Telegram photo and caption into a 30-second UGC-style video ad using AI. A user sends a photo + caption on Telegram. Gemini AI reads the caption and image to generate a realistic UGC script with tone, benefits, and call-to-action. The photo and script are sent to Kie.ai’s Veo3.1 API, which creates a high-quality vertical video (9:16) using the image and narration. Once rendered, the finished video ad is automatically sent back to the Telegram chat. How to set up Connect your Telegram Bot credentials. Add your Google Gemini API key in the Gemini node. Create a Kie.ai account and obtain your Veo3.1 API key. Paste the key in the HTTP Request nodes where required. Activate the workflow — send a Telegram message with a product photo + caption to test. Requirements Telegram Bot API key Google Gemini API key Kie.ai Veo3.1 API key How to customize the workflow Change Gemini prompt style (e.g., humorous, professional, emotional). Adjust Kie.ai model parameters (aspect ratio, duration, voice, or style). Add branding overlays or logos after video generation. Integrate with Google Drive, Notion, or Airtable to save results automatically. Modify the Telegram response to include both the video and the AI-generated script
by Naveen Choudhary
This workflow automatically enriches company domain lists with comprehensive business information using Perplexity AI's research capabilities and organizes the data in Google Sheets for easy analysis and use. Who's it for Sales teams** building prospect databases with accurate contact information Marketing professionals** researching target companies for campaigns Business development teams** gathering competitive intelligence Data analysts** enriching existing company datasets Researchers** collecting business information for market analysis How it works The workflow reads unprocessed company domains from a Google Sheets document, processes them in batches of 10 using Perplexity AI to research detailed business information, then saves the enriched data back to the spreadsheet. It focuses on German addresses but can be customized for any region. What it does Fetches unprocessed domains - Reads company domains from Google Sheets that haven't been processed yet Batches for efficiency - Groups domains into batches of 10 to optimize API costs and performance AI-powered research - Uses Perplexity AI to find comprehensive business data for each company Parses structured data - Converts AI responses into clean, structured JSON format Updates spreadsheet - Saves enriched data and marks domains as processed to prevent duplicates Requirements Perplexity AI API key** (Get one here) Google Sheets API access** (OAuth2 credentials) Google Sheets template** - Make a copy of this template How to set up Make a copy of the template Google Sheet and update the document ID in both Google Sheets nodes Configure Perplexity AI credentials in the HTTP Request node Set up Google Sheets OAuth2 authentication Add your company domains to the "domain" column in the Data tab Leave the "processed" column empty for new domains Run the workflow using the manual trigger How to customize the workflow Change target region**: Modify the AI prompt to research addresses in different countries Adjust batch size**: Change the batch size in the "Batch Process Domains" node (smaller batches = lower costs) Add custom fields**: Extend the AI prompt and Google Sheets mapping to include additional data points Automate execution**: Replace Manual Trigger with Schedule Trigger for regular processing Filter criteria**: Modify the Google Sheets filter to process specific subsets of domains Output data includes Complete company address (street, city, state, postal code, country) International phone number format Latest employee count and annual revenue (USD) Industry classification LinkedIn company URL Reliable source URL for verification Processing status tracking
by Abdul Aziz Ahwan
Tired of manually checking your YouTube Studio every day just to see how your channel is performing? This workflow is your solution. It automates the entire process of gathering your channel's key statistics and delivers a beautiful, easy-to-read performance report directly to your Telegram chat on a schedule you set. Stay updated on your channel's growth without lifting a finger. How it Works This workflow runs on a custom schedule to give you consistent updates. Scheduled Trigger**: The workflow kicks off automatically at your chosen interval (e.g., every Monday at 6 AM). Fetch Channel Data: It makes a series of requests to the **YouTube Data & Analytics APIs to gather the latest statistics on: Channel Summary (views, watch time, subscribers, etc.) Top Performing Videos Audience Traffic Sources Audience Demographics Process & Format**: The raw data from the APIs is merged and transformed into a clean, human-readable format using Markdown and emojis. Send Telegram Report**: The final formatted summary is sent as a message to your specified Telegram chat, giving you an instant overview of your channel's performance. Setup Steps You'll need to configure credentials for Google and Telegram to get started. Configure Google API Credentials: Create an OAuth 2.0 Client ID from the Google Cloud Console. Make sure to enable the YouTube Analytics API and YouTube Data API v3. In n8n, create new Google API credentials using your Client ID and Client Secret, ensuring you add the required YouTube scopes. Configure Telegram Credentials: Create a new Telegram bot using BotFather to get your API token. Add the token to the Telegram node's credentials. Customize the Workflow: Adjust the Schedule node to set how often you want to receive the report. In the Telegram node, enter the Chat ID for the person or group you want to send the report to.
by Abhiman G S
Quick Summary This workflow connects Telegram, Google Gemini AI, and Notion to make task creation effortless. Whenever you send a message to your Telegram bot, Gemini AI reads your message, understands what task you meant, and automatically creates it in your Notion database - complete with the task name and due date. If you approve, the task is added to Notion and you’ll get a confirmation in Telegram. If you decline, it simply replies that ❌ no task was created. Perfect for anyone who wants to capture ideas or to-dos directly from Telegram without opening Notion every time. Detailed Use Cases Quick task capture from Telegram Send a message like “Buy milk 25 May” to your Telegram bot. The AI extracts the task name and date, asks you to approve, and creates a Notion task once approved. Turn reminders into Notion tasks Message: “Pay rent next Monday” → Approve → Task added to Notion with the correct due date. Perfect for quickly saving reminders while on the go. Tip: For best results, include clear dates in your messages like 25 May or May 25, 2025 so the AI can extract them accurately. Prerequisites / Requirements Before using this workflow, make sure you have the following ready: Telegram Bot Setup Go to @BotFather on Telegram. Create a new bot using the /newbot command. Copy the Bot Token — you’ll need it to connect in the Telegram Trigger and Telegram nodes in n8n. Google Gemini API Key Sign up for a free Google AI Studio account. Create an API key and connect it in your n8n credentials under Google Gemini. This workflow uses the models/gemini-2.5-flash-lite model, which works perfectly on the free tier. Notion Database Setup Create a Notion database for storing tasks. It must have: A Title property — set this as the Task Name (type: Title / text). A Date property — set this as the Due Date (type: Date). Copy your Notion database ID and connect your Notion API credentials in n8n. Optional Security Note In the Telegram Trigger node, restrict the chatId to your own Telegram user ID if this workflow is for personal use. Customization Guide You can easily extend this workflow to capture more details from your Telegram messages using the AI Extract node. Here are a few simple ways to customize it: Add more extracted fields In the AI Extract: TaskName & TaskDue node, open the Attributes section. Add new fields like: Priority → text (e.g., High, Medium, Low) Duration → number or text (e.g., 30 mins, 1 hour) Notes → text (optional extra info) The Gemini model will automatically try to extract these from your message. Example messages you can send “Finish report by Friday — high priority, 2 hours.” “Workout tomorrow evening — medium priority.” Map extra fields to Notion In the Notion: Create Task (Page) node, scroll to the Properties section. Add matching Notion properties for each new field (e.g., Priority, Duration). Map the AI outputs (like output.Priority) to their respective fields. Send confirmation with extra data In the Send and Wait for Response (Approve/Decline) node, include the new extracted details in the Telegram message before approval. Example confirmation message: Task: {{ $json.output.TaskName }} Due: {{ $json.output.TaskDue }} Priority: {{ $json.output.Priority }} Duration: {{ $json.output.Duration }} By doing this, you can build a smarter task capture system that includes priority, time estimation, and other useful details, all directly from your Telegram chat.
by Fahmi Fahreza
AI-Powered Product Video Generator (Foreplay + Gemini + Sora 2) Sign Up For Foreplay HERE Automatically generate personalized, cinematic-quality product videos using Foreplay’s ad data, Google Gemini AI for creative prompts, and Sora 2 for text-to-video generation. Who’s it for? Perfect for marketers, brand managers, or creators who want to produce quick, high-quality video ads without manual scripting or editing. How it works Fetch product data and related competitor videos from Foreplay. Use Gemini AI to generate creative text-to-video prompts. Send the prompt and image to Kie.ai to generate a short, cinematic product video. Save the finished video automatically to Google Drive. How to set up Connect your Foreplay, Google Drive, Gemini, and Kie.ai credentials. Set your product image folder's permission (Google Drive) as public. Add your API keys inside the Set Workflow Credentials node. Then run the workflow manually to generate your first video ad!
by banan
How it works This workflow syncs Toggl Track time entries to Google Sheets and creates monthly tabs automatically. It fetches: time entries from Toggl project metadata from Toggl Then it: filters entries by your selected project name writes detailed rows to a Detail Sheet writes daily aggregated rows to a Summary Sheet creates/removes monthly tabs to keep both sheets clean and aligned Set up steps Estimated setup time: 10–15 minutes. Configure HTTP Basic Auth for Toggl: Username: your Toggl API token Password: api_token Configure Google Sheets OAuth2 credentials. In Set Date Range, set start_date. In Process Data, set: PROJECT_NAME TIMEZONE Replace placeholders in workflow nodes: YOUR_DETAIL_SPREADSHEET_ID YOUR_SUMMARY_SPREADSHEET_ID Detailed node-by-node guidance is included in sticky notes inside the workflow.
by Miftah Rahmat
⚡ Overview This workflow connects Telegram with an AI Agent (Gemini) and Notion to automate content requests. Team members can request content ideas directly in Telegram. The AI processes the request, then automatically creates a new entry in your Notion Content database. 🛠️ Features 🤖 AI-powered assistant: Gemini AI with memory to understand context and generate better responses. 📲 Telegram integration: Accepts requests directly from your Telegram bot. 🗂️ Notion automation: Auto-creates records in your Notion database (title, content draft, channel, assignee, date, references, type). 🛡️ Secure & flexible: No hardcoded API keys, placeholders used for easy setup. 📝 Setup Instructions Add your Telegram Bot Token, Google Gemini API Key, and Notion Integration Token in n8n credentials. Steps: Import this template JSON into your n8n instance. Configure credentials in n8n (Telegram, Notion, Gemini API). 🎯 Use Cases Content marketing teams managing requests via Telegram. Automating idea collection from distributed teams. Keeping Notion Content updated without manual entry.
by Robert Breen
This workflow pulls all tasks from your Monday.com board each day and logs them into a Google Sheet. It creates a daily snapshot of your project’s progress and statuses for reporting, tracking, or analysis. ⚙️ Setup Instructions 1️⃣ Connect Monday.com API In Monday.com → go to Admin → API Copy your Personal API Token Docs: Generate Monday API Token In n8n → Credentials → New → Monday.com API → paste your token and save 2️⃣ Prepare Your Google Sheet Copy this template to your own Google Drive: Google Sheet Template Add your data in rows 2–100. Make sure each new task row starts with Added = No. Connect Google Sheets in n8n Go to n8n → Credentials → New → Google Sheets (OAuth2) Log in with your Google account and grant access In the workflow, select your Spreadsheet ID and the correct Sheet Name 🧠 How it works Trigger**: Runs on click or via schedule (e.g., daily at 9 AM). Get many items (Monday.com)**: Fetches all tasks and their current status. Today's Date Node**: Adds the current date for snapshot logging. Map Fields**: Normalizes task name and status. Google Sheets (Append)**: Saves all tasks with status + date into your sheet for historical tracking. 📬 Contact Need help customizing this (e.g., filtering by status, emailing daily reports, or adding charts)? 📧 robert@ynteractive.com 🔗 Robert Breen 🌐 ynteractive.com
by Miad Dadbin
How it works This workflow receives messages from Telegram using the Telegram Trigger node. It detects the user’s action (/start or customer name) and decides whether to send a welcome message or perform a customer search. The system fetches customer and access information from Google Sheets, checks if the user is authorized (based on chat IDs in the “Access” sheet), and then proceeds accordingly. If access is granted, the workflow aggregates financial and weight data, formats a summary report, and sends it back to the same Telegram chat automatically. If access is denied or customer data is not found, it sends an appropriate “no permission” or “incorrect name” message to the user. ⚙️ Set up steps Connect your Telegram Bot API credentials in the Input user2, Send Report2, and related Telegram nodes. Connect your Google Sheets account and update: documentId → link to your Google Sheet sheetName → replace with your actual sheet/tab names (“Access”, “Sheet1”, etc.) lookupColumn → update to match column names used in your sheet (e.g., Customer name, Groups). Replace placeholder text such as Your Custom Message and Your Custom Name with your actual message texts or variable names. Test by sending a message to your Telegram bot with either /start or a known customer name. Expected setup time: 10–15 minutes depending on how your Google Sheets and Telegram bot are configured. Keep detailed field mapping or transformation logic (column names, sheet IDs) inside sticky notes within your workflow.
by Pavel Zamorev
Use OpenAI to generate short, memorable brand names for your app and automatically check .com availability — results go straight into Google Sheets. Categories: AI, Marketing Description This n8n workflow helps you find an available .com domain for your product. It uses OpenAI to generate batches of creative, on-brand names (e.g. for a digital wardrobe / closet app, inspired by names like Whering, Acloset, Stylebook), then checks each suggestion via API Ninjas. Available domains are appended to a sheet, taken ones to a separate sheet. On each run it reads both sheets so it never suggests or re-checks the same names. The loop runs until you have at least 15 available domains or hit 10 iterations (20 names per iteration). Good to know API Ninjas* free tier supports *.com only. Under heavy load you may see occasional 502 errors; the workflow uses Continue On Fail and only processes successful responses. Add a **Wait node (200–500 ms) before "Check domain (API Ninjas)" if needed. OpenAI** usage depends on your plan (tokens and rate limits). Each iteration sends one request for 20 names. State is passed through the pipeline so that newly checked domains are excluded in the next iteration — no duplicates in suggestions or in the sheets. How it works Start: Manual Trigger runs Read sheet available and Read sheet closed (in sequence). Build initial state builds alreadyChecked from both sheets and sets totalFound from the available count. Prepare prompt builds a system and user prompt with your app context and the current alreadyChecked list, then Generate names (OpenAI) returns 20 new names. Normalize to domains cleans and turns them into .com domains. Check domain (API Ninjas) checks each name. Merge name and API result combines normalized names with API results (only items with a valid available field). Filter available only and Closed only split results; Append to sheet available and Append to sheet closed write to Google Sheets. State for next run updates totalFound, appends this round’s domains to alreadyChecked, and increments the iteration. Exit or loop stops when totalFound >= 15 or iteration > 10, otherwise loops back to Prepare prompt with the updated state. How to use Use the Manual Trigger to run the workflow. Configure credentials: OpenAI (e.g. OpenAI Vision), Api ninjas (Header Auth, X-Api-Key from api-ninjas.com), and Google Sheets account. In one Google spreadsheet create two sheets named available and closed, each with header row: domain, name. Set this document and sheet names in the four Google Sheets nodes (Read sheet available, Read sheet closed, Append to sheet available, Append to sheet closed). If you see repeated 502s, add a Wait node (200–500 ms) before Check domain (API Ninjas) or enable Retry On Fail on that node. Requirements n8n (2.2.3+ recommended) OpenAI** API key (for name generation) API Ninjas** API key (for domain availability) or other API Google Sheets* (one document with two sheets: *available, **closed; columns: domain, name) Customising this workflow Different niche:* Edit the *Prepare prompt** node to change the app context and style (e.g. another app category, different reference names). The prompt enforces short names (under 14 characters), letters only, and excludes already-checked domains. Target count and iterations:* In *Exit or loop**, change the conditions (e.g. totalFound > 15 to another number, or iteration = 10 to allow more rounds). Other TLDs:** The free API Ninjas tier is .com only; with a paid plan you could extend the workflow to check other zones.