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 Ruthwik
⚡ Next-Gen Customer Support: Two-Way WhatsApp + Telegram Integration for 10k+ Clients Who is this workflow for This workflow is designed for **customer support teams, e-commerce founders, and operations managers** who want to handle thousands of customer queries seamlessly. Instead of building a brand-new chat application, it leverages WhatsApp (where customers already are) and Telegram (where your support team operates) to create a scalable, topic-based support system. If you are a brand handling 1000s of daily WhatsApp customer messages and need a structured way to map each customer into a dedicated support thread without chaos, this workflow is for you. What it does / How it works This two-way n8n automation bridges WhatsApp and Telegram by creating one Telegram forum topic per customer and syncing messages both ways: Incoming WhatsApp → Telegram When a new WhatsApp message arrives, the workflow checks if the customer already has a topic in Telegram. If yes → The message is forwarded into that existing topic. If no → A new topic is created automatically, the mapping is saved in the database, and the message is posted there. Result: every customer has a dedicated thread in your Telegram supergroup. Outgoing Telegram → WhatsApp When a support agent replies in a Telegram topic, the workflow looks up the linked WhatsApp number. The reply is sent back to the customer on WhatsApp, preserving context. Result: two-way synced conversations without building a custom app. How to set it up Configure WhatsApp Cloud API Create a Meta Developer account and register a WhatsApp Business number. Generate an access token and phone number ID. Configure Telegram Bot Use BotFather to create a bot and enable it in a **Telegram Supergroup with Topics**. Get the chat_id and allow the bot to create/send messages in topics. Database (Supabase/Postgres) Create a table wa_tg_threads to map phone_e164 ↔ telegram_topic_id ↔ supergroup_id. n8n Workflows Workflow A: WhatsApp → Telegram Trigger: WhatsApp Webhook Steps: Lookup customer → If exists send to topic, else create topic → Save mapping → Forward message. Workflow B: Telegram → WhatsApp Trigger: Telegram Webhook Steps: Filter only topic replies → Lookup mapping → Send WhatsApp message. Testing Send a WhatsApp message → Check Telegram topic created. Reply in Telegram topic → Ensure customer receives WhatsApp reply. Requirements A free or paid n8n instance (self-hosted or cloud). WhatsApp Cloud API credentials** (phone number ID + access token). Telegram Bot token* with access to a *Supergroup with Topics** enabled. A Postgres/Supabase database to store thread mappings. Basic familiarity with editing HTTP Request nodes in n8n. How to customize the workflow Brand personalization:** Pre-populate first message templates (thank you, order status, delivery updates). Routing rules:** Assign specific agents to certain topics by ID ranges. Integrations:** Extend to CRMs (HubSpot, Zoho) or support platforms (Freshdesk, Zendesk). Notifications:** Push high-priority WhatsApp queries into Slack/Teams for instant alerts. Archival:** Auto-close inactive topics after N days and mark customers as dormant. Why Telegram instead of building a new App The client's requirement was clear: **use an existing, reliable, and scalable chat platform** instead of building a new app from scratch. Telegram Supergroups with Topics** scale to 100,000+ members and millions of messages, making them ideal for managing 10k+ customer threads. Agents don't need to install or learn a new tool---they continue inside Telegram, which is fast, free, and mobile-friendly. Building a custom chat app would require authentication, push notifications, scaling infra, and UX---all solved instantly by Telegram. This decision **saves development cost, accelerates deployment, and provides proven scalability**. Why this improves support productivity Organized by customer:** Each WhatsApp number has its own Telegram topic. No missed messages:** Agents can quickly scroll topics without drowning in one endless chat. Two-way sync:** Replies flow back to WhatsApp seamlessly. Scales automatically:** Handle 10k+ conversations without losing track. Leverages existing tools:** WhatsApp (customers) + Telegram (agents). Result: **faster responses, better tracking, and zero need to reinvent chat software.**
by Daniel
Transform your Telegram bot into a secure content analyzer: send any URL, and get safe, structured Q&A extractions with AI-powered safety checks and web search capabilities. 📋 What This Template Does This workflow activates when a user sends a valid URL to your Telegram bot. It extracts questions and answers from the webpage using Airtop, applies NSFW and PII guardrails to ensure safe content, then uses an OpenRouter AI agent (with optional Tavily search) to generate and send a concise response. If guardrails fail, it alerts the user instead. Filters for valid URLs only to prevent unnecessary processing Extracts structured Q&A from documents or forms Enforces safety checks for harmful or private content Supports web searches for enhanced responses when needed 🔧 Prerequisites A Telegram bot created via @BotFather Accounts with Airtop, OpenRouter, and Tavily 🔑 Required Credentials Telegram API Setup Open Telegram → Search @BotFather → Use /newbot command Follow prompts to create bot and obtain API token Add to n8n as Telegram API credential type Airtop API Setup Visit https://airtop.ai → Sign up or log in → Navigate to Dashboard → API Keys Generate a new API key with extraction permissions Add to n8n as Airtop API credential type OpenRouter API Setup Go to https://openrouter.ai → Sign up or log in → Navigate to API Keys section Generate and copy your API key (free tier sufficient for basic use) Add to n8n as OpenRouter API credential type Tavily API Setup Visit https://app.tavily.com → Sign up or log in → Go to API Keys Generate and copy your API key Add to n8n as Tavily API credential type ⚙️ Configuration Steps Import the workflow JSON into n8n Assign your Telegram, Airtop, OpenRouter, and Tavily credentials to the respective nodes Activate the workflow to register the Telegram trigger Test by sending a plain URL (no extra text) to your bot in Telegram Monitor the first execution and adjust guardrail thresholds if needed 🎯 Use Cases Researchers summarizing academic papers or reports while ensuring no sensitive data leaks Support teams extracting info from customer-submitted docs/forms with automatic safety filtering Content creators pulling Q&A from articles for bots, blocking inappropriate responses Educators analyzing educational resources safely for student-facing chat tools ⚠️ Troubleshooting No response from bot: Verify the message contains only a valid URL; adjust regex in Filter Only URLs node if needed Guardrail failures: Lower NSFW threshold (e.g., from 0.7 to 0.5) or disable PII checks in Apply Safety Guardrails node Extraction errors: Test with public, text-heavy URLs; some JS-heavy sites may require alternative extractors Rate limits hit: Check OpenRouter/Tavily dashboards for usage; upgrade to paid tiers for heavy traffic
by higashiyama
Advanced Code Review Automation (AI + Lint + Slack) Who’s it for For software engineers, QA teams, and tech leads who want to automate intelligent code reviews with both AI-driven suggestions and rule-based linting — all managed in Google Sheets with instant Slack summaries. How it works This workflow performs a two-layer review system: Lint Check: Runs a lightweight static analysis to find common issues (e.g., use of var, console.log, unbalanced braces). AI Review: Sends valid code to Gemini AI, which provides human-like review feedback with severity classification (Critical, Major, Minor) and visual highlights (red/orange tags). Formatter: Combines lint and AI results, calculating an overall score (0–10). Aggregator: Summarizes results for quick comparison. Google Sheets Writer: Appends results to your review log. Slack Notification: Posts a concise summary (e.g., number of issues and average score) to your team’s channel. How to set up Connect Google Sheets and Slack credentials in n8n. Replace placeholders (<YOUR_SPREADSHEET_ID>, <YOUR_SHEET_GID_OR_NAME>, <YOUR_SLACK_CHANNEL_ID>). Adjust the AI review prompt or lint rules as needed. Activate the workflow — reviews will start automatically whenever new code is added to the sheet. Requirements Google Sheets and Slack integrations enabled A configured AI node (Gemini, OpenAI, or compatible) Proper permissions to write to your target Google Sheet How to customize Add more linting rules (naming conventions, spacing, forbidden APIs) Extend the AI prompt for project-specific guidelines Customize the Slack message formatting Export analytics to a dashboard (e.g., Notion or Data Studio) Why it’s valuable This workflow brings realistic, team-oriented AI-assisted code review to n8n — combining the speed of automated linting with the nuance of human-style feedback. It saves time, improves code quality, and keeps your team’s review history transparent and centralized.
by Avkash Kakdiya
How it works This workflow automates the job curation process by retrieving pending job search inputs from a spreadsheet, querying the JSearch API for relevant job listings, and writing the curated results back to another sheet. It is designed to streamline job discovery and reduce manual data entry. Step-by-step 1. Trigger & Input The workflow starts on a defined schedule (e.g., once per day). It reads a row from the Job Scraper sheet where the status is marked as "Pending". The selected row includes fields like Position and Location, which are used to build the search query. 2. Job Search & Processing Sends a search request to the JSearch API using the Position and Location from the spreadsheet. Parses the API response and extracts individual job listings. Filters out empty, irrelevant, or invalid entries to ensure clean and relevant job data. 3. Output & Status Update Writes valid job listings to the Job Listing output sheet with fields such as job title, company name, location, and more. Updates the original row in the source sheet to mark it as Scraped, ensuring it will not be processed again in future runs. Benefits Reduces manual effort in job research and listing. Ensures only valid, structured data is stored and used. Prevents duplicate processing with automatic status updates. Simple to expand by adding more job sources or filters.
by David Hernández Luján
Who’s it for This workflow is for system administrators or self-hosted n8n users who want to automatically check and update their n8n instance to the latest version — with Telegram notifications for every step. How it works The workflow runs daily at 9 AM or every time n8n starts. It retrieves your current version using the Execute Command node. It checks the latest release from the official n8n GitHub API. It compares both versions and decides whether an update is needed. If an update is available: Sends a Telegram alert. Verifies that there are no running executions. Runs the update command safely. Sends a confirmation message when done. If your instance is already up to date, it sends a “latest version” message instead. Requirements Self-hosted n8n** instance with access to run terminal commands. A valid Telegram Bot API credential (configured in n8n Credentials; not hardcoded). System permissions** to execute global npm commands (sudo privileges). How to set up Import this workflow into your n8n instance. Connect your Telegram Bot credential to the Telegram nodes. Adjust the chat ID and message thread ID if needed. (Optional) Change the schedule time in the Schedule Trigger node. Save and activate the workflow. How to customize Change the update command if you’re running n8n via Docker: docker pull n8nio/n8n:latest
by Mohammad Jibril
Overview This template creates a smart FAQ bot on Telegram, powered by Google Gemini for intelligent answers and Supabase to store user data. The workflow can distinguish between new and existing users. How It Works Trigger: The workflow starts when a user sends any message to the Telegram Bot. Check User: It looks up the user's chat_id in a Supabase telegram_users table. Route (New vs. Existing): New User (True Path): If the user is not found, the workflow saves their chat_id to Supabase and sends a one-time welcome message. Existing User (False Path): If the user exists, the workflow proceeds to the AI step. Generate Answer: It loads a predefined FAQ context and combines it with the user's question. This is sent to Google Gemini via the AI Agent node. Send Response: The AI-generated answer is sent back to the user on Telegram. Setup Instructions Telegram: Connect your Telegram credentials to the Telegram Trigger and both Send a text message nodes. Supabase: Connect your Supabase credentials to the Find user in DB and Create a row nodes. You MUST have a table named telegram_users. This table MUST have a column named chat_id (type: text or varchar). Google Gemini: Connect your Google Gemini (Palm API) credentials to the Google Gemini Chat Model node. (REQUIRED) Customization: Open the Set FAQ Context node and change its contents with Questions (Q) and Answers (A) that are appropriate for your bot. Change the text in the Send a text message (Welcome Message) node as you want.
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 Gtaras
Who’s it for This workflow is perfect for individuals who want a simple expense tracker without needing a full app. If you already use Telegram daily, this makes it effortless to log purchases, track spending, and stay accountable to your budget. How it works / What it does Send an expense in Telegram using the format /spent 5 lunch. n8n parses the message and appends the entry to Google Sheets. Every Sunday at 11:00, the workflow sends a weekly expense summary to Telegram. If you exceed your weekly budget (default €100), you’ll instantly get a budget warning alert. Optionally, the sheet can be cleared weekly to start fresh. How to set up Create a Telegram bot with BotFather, copy the token, and get your Chat ID via getUpdates. Make a copy of the provided Google Sheets template and connect your Google credentials in n8n. Replace <YOUR_CHAT_ID> and <YOUR_SHEET_ID> placeholders in the workflow. Adjust the budget threshold in the “Check Weekly Budget” node if needed. Activate the workflow and test with a sample expense. Requirements A Telegram bot (free, via BotFather). Google Sheets with n8n OAuth2 credentials. An n8n instance (self-hosted or cloud). How to customize the workflow Change the budget threshold in the Code node. Update the summary schedule in the Schedule Trigger node. Expand the Google Sheet with more categories or details. Personalize the Telegram messages to fit your style.
by Țugui Dragoș
How it works This workflow fetches articles from any RSS feed, processes them with an AI model (DeepSeek), and sends only the most relevant alerts directly to Slack. Normalizes and deduplicates RSS items Extracts article text and cleans HTML Summarizes and classifies with AI (sentiment + flags) Filters out irrelevant news Sends real-time alerts to your Slack channel Setup steps Add your Slack Bot Token (via Slack API) Add your DeepSeek API Key Import this workflow into n8n Deploy and start receiving smart news alerts in Slack Use case Perfect for tracking AI, startups, finance, and tech industry news without the noise.
by Kevin Meneses
How it works Runs on a schedule and iterates a watchlist of symbols (e.g., BTC/ETH/SOL). For each symbol, request intraday 1h OHLCV from EODHD. A Code node computes Wilder’s RSI(14) and detects 30/70 crossings. When a signal appears, the bot sends a Telegram alert (HTML message) with price, RSI (prev → now), timestamp, and a “View chart” button that opens the pair on TradingView (BINANCE/USD). Set up steps (≈10–15 min) Prereqs: n8n (cloud or self-hosted), EODHD API key, Telegram bot + your chat_id. Env vars: set EODHD_TOKEN and TELEGRAM_CHAT_ID on your n8n instance. Credentials: add your Telegram credential (bot token). Import the workflow JSON. Edit Fields node: adjust the symbol array to your watchlist. Schedule Trigger: choose how often to run (e.g., every 5–10 min). Test: temporarily flip the Code node’s FORCE_ALERT flag to true to verify Telegram delivery, then set it back to false.
by Diptamoy Barman
🎨 Anime Image Generator with LLM-Enhanced Prompts This workflow turns a short text idea into stunning, AI-generated anime-style images, all from Telegram. It combines a chat LLM for prompt enhancement with Gemini (free) or Leonardo.AI (paid) image models. 🌟 What It Does Accepts a text prompt sent via Telegram. Uses an LLM (DeepSeek via OpenRouter) to expand and enrich the idea into several anime-ready prompts. Lets you choose the image engine: Gemini (90-day free trial with a GCP account). Leonardo.AI (paid, higher-fidelity anime rendering). Generates 4 images per query, converts them to files, and delivers the images back to your Telegram chat. ⚙️ How It Works Telegram Trigger — waits for a text message from you. Image-count Node — stores your prompt & sets how many images to create (default: 4). Prompt Generator (LLM) — transforms your simple prompt into multiple detailed, visually rich anime prompts. Split & Loop — sends each refined prompt to the chosen image generator. Image Generator: Default: HTTP-Gemini node. Alternative: HTTP-Leonardo AI node (swap in for better quality). Convert to File & Send — decodes the generated images and sends them back to you on Telegram. 🔑 Setup Telegram Bot** Create a bot using BotFather. Add your Bot Token & your Telegram User ID to the workflow (look for “Configure Me!” sticky notes). LLM Provider** Default: DeepSeek via OpenRouter — used to expand prompts. You can swap this with any other chat LLM you prefer. Image Engine** Default: Gemini (free trial, good baseline quality). Optional: Leonardo.AI for anime-focused, premium-quality images. Replace the HTTP-Gemini node with the HTTP-Leonardo AI node and set up your Leonardo API key as a Header Auth credential. Optional Adjustments** Change default number of images in the Image-count node. Tweak the LLM prompt template for different artistic styles (e.g., pastel slice-of-life, fantasy, action, cyberpunk). 💡 Tips Start with short, plain prompts — e.g., girl with umbrella in neon city street at night The LLM will enrich it automatically. If images look flat, try Leonardo.AI or adjust the prompt style and guidance scale. Avoid NSFW or copyrighted character prompts — follow the providers’ usage policies. Keep your API keys private and never share them in screenshots. 👥 Who Is This For Anime creators & hobbyists** who want to visualize characters or scenes quickly. Content creators & social posters** who want to share unique anime-style visuals. Anyone who wants easy AI image generation via Telegram, without needing to master prompt engineering. ✨ Ready to go: Run the workflow, send a prompt to your Telegram bot, and watch it turn into beautiful anime images.