Workflow Templates

This n8n workflow automates the creation of high-quality, SEO-optimized blog posts using AI. It pulls keyword data from Google Sheets, conducts research via Perplexity AI, generates structured content (title, introduction, key takeaways, body, conclusion, and FAQs) with OpenAI and Anthropic models, assembles the post, performs final edits, converts to HTML, and publishes directly to WordPress. Ideal for content marketers, bloggers, or agencies looking to scale content production while maintaining relevance and engagement. Key Features Keyword-Driven Generation: Fetches primary keywords, search intent, and related terms from a Google Sheets spreadsheet to inform content strategy. AI Research & Structuring: Uses Perplexity for in-depth topic research and OpenAI/Anthropic for semantic analysis, outlines, and full content drafting. Modular Content Creation: Generates sections like introductions, key takeaways, outlines, body, conclusions, and FAQs with tailored prompts for tone, style, and SEO. Assembly & Editing: Combines sections into a cohesive Markdown post, adds internal/external links, and applies final refinements for readability and flow. Publishing Automation: Converts Markdown to styled HTML and posts drafts to WordPress. Customization Points: Easily adjust AI prompts, research depth, or output formats via Code and Set nodes. Requirements Credentials: OpenAI API (for GPT models), Perplexity API (for research), Google Sheets OAuth2 (for keyword input), WordPress API (for publishing). Setup: Configure your Google Sheets with columns like "keyword", "search intent", "related keyword", etc. Ensure the sheet is shared with your Google account. Dependencies: No additional packages needed; relies on n8n's built-in nodes for AI, HTTP, and data processing. How It Works Trigger & Input: Start manually or schedule; pulls keyword data from Google Sheets. Research Phase: Uses Perplexity to gather topic insights and citations from reputable sources. Content Generation: AI nodes create title, structure, intro, takeaways, outline, body, conclusion, and FAQs based on research and SEO guidelines. Assembly & Refinement: Merges sections, embeds links, edits for polish, and converts to HTML. Output: Publishes as a WordPress draft or outputs the final HTML for manual use. Benefits Time Savings: Automate 80-90% of content creation, reducing manual writing from hours to minutes. SEO Optimization: Incorporates primary/related keywords naturally, aligns with search intent, and includes semantic structures for better rankings. Scalability: Process multiple keywords in batches; perfect for content calendars or high-volume blogging. Quality Assurance: Built-in editing ensures engaging, error-free content with real-world examples and data-backed insights. Versatility: Adaptable for any niche (e.g., marketing, tech, finance) by tweaking prompts or sheets. Potential Customizations Add more AI models (e.g., via custom nodes) for varied tones. Integrate image generation or social sharing for full content pipelines. Filter sheets for specific topics or add notifications on completion.

How It Works This template is an n8n workflow that integrates with Jira to provide automated replies. When a ticket is assigned to a user, the workflow analyzes the ticket content, retrieves relevant knowledge from a vector database, and generates a response. By continuously enriching the knowledge base, the system improves response quality in Jira. Prerequisites A Jira account with API access A Pinecone account and credentials (API key and environment settings) An AI provider credential (e.g., OpenAI API key) Setup Instructions Jira Credentials Create Jira credentials in n8n (API token and email). In the Jira node, select the registered Jira account ID. Vector Database Setup (Pinecone) Register your Pinecone credentials (API key and environment variables) in n8n. Ensure that your knowledge base is indexed in Pinecone. AI Assistant Node Configure the OpenAI (or other LLM) node with your API key. Provide a system prompt that explains how to respond to Jira tickets using retrieved knowledge. Workflow Execution The workflow runs only via the Scheduled Trigger node at defined intervals. When Jira tickets are assigned, their summary, description, and latest comments are retrieved. These details are passed to the AI assistant, which queries Pinecone and generates a response. The generated response is then posted as a Jira comment. Step by Step Scheduled Trigger The workflow is executed at regular intervals using the Scheduled Trigger node. Jira Trigger (Issue Assigned) Retrieves the summary, description, and latest comments of assigned tickets. AI Assistant Sends ticket details to the AI assistant, which searches and summarizes relevant knowledge from Pinecone. Response Generation / Ticket Update The AI generates a response and automatically posts it as a Jira comment. (Optionally, the workflow can update the ticket status or mention the assignee.) Notes Keep your Pinecone knowledge base updated to improve accuracy. You can customize the AI assistant’s behavior by adjusting the system prompt. Configure the Scheduled Trigger frequency carefully to avoid API rate limits. Further Reference For a detailed walkthrough (in Japanese), see this article: 👉 Automating Jira responses with n8n, AI, and Pinecone (Qiita) You can find the template file on GitHub here: 👉 Template File on GitHub

This n8n template demonstrates how to build an intelligent entity research system that automatically discovers, researches, and creates comprehensive profiles for business entities, concepts, and terms. Use cases are many: Try automating glossary creation for technical documentation, building standardized definition databases for compliance teams, researching industry terminology for content creation, or developing training materials with consistent entity explanations! Good to know Each entity research typically costs $0.08-$0.34, depending on the complexity and sources required. The workflow includes smart duplicate detection to minimize unnecessary API calls. The workflow requires multiple AI services and a vector database, so setup time may be longer than simpler templates. Entity definitions are stored locally in your Qdrant database and can be reused across multiple projects. How it works The workflow checks your existing knowledge base first to avoid duplicate research on entities you've already processed. If the entity is new, an AI research agent intelligently combines your vector database, Wikipedia, and live web research to gather comprehensive information. The system creates structured entity profiles with definitions, categories, examples, common misconceptions, and related entities - perfect for business documentation. AI-powered validation ensures all entity profiles are complete, accurate, and suitable for business use before storage. Each researched entity gets stored in your Qdrant vector database, creating a growing knowledge base that improves research efficiency over time. The workflow includes multiple stages of duplicate prevention to avoid unnecessary processing and API costs. How to use The manual trigger node is used as an example, but feel free to replace this with other triggers such as form submissions, content management systems, or automated content pipelines. You can research multiple related entities in sequence, and the system will automatically identify connections and relationships between them. Provide topic and audience context to get tailored explanations suitable for your specific business needs. Requirements OpenAI API account for o4-mini (entity research and validation) Qdrant vector database instance (local or cloud) Ollama with nomic-embed-text model for embeddings Automate Web Research with GPT-4, Claude & Apify for Content Analysis and Insights workflow (for live web research capabilities) Anthropic API account for Claude Sonnet 4 (used by the web research workflow) Apify account for web scraping (used by the web research workflow) Customizing this workflow Entity research automation can be adapted for many specialized domains. Try focusing on specific industries like legal terminology (targeting official legal sources), medical concepts (emphasizing clinical accuracy), or financial terms (prioritizing regulatory definitions). You can also customize the validation criteria to match your organization's specific quality standards.

Instantly access live Bybit Spot Market data in Telegram! This workflow integrates the Bybit REST v5 API with Telegram and optional GPT-4.1-mini formatting, delivering real-time crypto market insights such as latest prices, order books, trades, and candlesticks — all presented in clean, structured Telegram messages. 🔎 How It Works A Telegram Trigger node listens for incoming user requests. User Authentication checks the Telegram ID against an allowlist. A Session ID is created from chat.id for lightweight memory across interactions. The Bybit AI Agent orchestrates multiple API requests via HTTP nodes: Latest Price & 24h Stats (/v5/market/tickers?category=spot&symbol=BTCUSDT) Order Book Depth (/v5/market/orderbook?category=spot&symbol=BTCUSDT&limit=50) Best Bid/Ask Snapshot (from order book top levels) Candlestick Data (Klines) (/v5/market/kline?category=spot&symbol=BTCUSDT&interval=15&limit=200) Recent Trades (/v5/market/recent-trade?category=spot&symbol=BTCUSDT&limit=100) Utility Nodes process and format the response: Calculator → computes spreads, mid-prices, % changes. Think → transforms JSON into human-readable reports. Simple Memory → stores symbol, sessionId, and previous inputs. Message Splitter ensures responses over 4000 characters are broken into chunks. Final results are sent back to Telegram in structured, readable format. ✅ What You Can Do with This Agent Get real-time Bybit prices & 24h statistics. Retrieve spot order book depth and liquidity snapshots. Analyze candlesticks (OHLCV) across multiple timeframes. View recent trades for market activity. Monitor bid/ask spreads & mid-prices with calculated values. Receive Telegram-ready reports, cleanly formatted and auto-split when long. 🛠️ Setup Steps Create a Telegram Bot Use @BotFather to create a bot and get a token. Configure in n8n Import Bybit AI Agent v1.02.json. Update the User Authentication node with your Telegram ID. Add your Telegram API credentials (bot token). Add OpenAI API key (Optional) Add Bybit API key if you want AI-enhanced formatting. Deploy and Test Activate the workflow in n8n. Send a message like BTCUSDT to your bot. Instantly receive Bybit Spot data inside Telegram. 📺 Setup Video Tutorial Watch the full setup guide on YouTube: ⚡ Unlock Bybit Spot Market insights in Telegram — fast, structured, and API-key free. 🧾 Licensing & Attribution © 2025 Treasurium Capital Limited Company Architecture, prompts, and trade report structure are IP-protected. No unauthorized rebranding permitted. 🔗 For support: Don Jayamaha – LinkedIn

How it works: This template turns rows in a Google Sheet into polished newsletter drafts in Notion using an AI writing agent. You click Execute workflow in n8n. It fetches all rows marked N8n Status = Pending, generates a draft from Newsletter Title and About the Newsletter, creates a Notion page, writes the full draft, then flips the sheet row to Done before moving to the next one. Before you start (use your own credentials): Create and select your credentials in n8n: Google Sheets (OAuth2 or Service Account) with access to the target spreadsheet. Notion (Internal Integration) with access to the target database. OpenAI (API Key) for the Chat Model. Replace any placeholders in nodes: Spreadsheet ID/URL and sheet/tab name (e.g., newsletter). Notion Database ID / Parent and any page or block IDs used by HTTP Request nodes. OpenAI model name if you prefer a different model. Give the Notion integration access to the database (Share → Invite the integration). Do not hard-code secrets in nodes. Store them in n8n Credentials. Step-by-step: Manual Trigger Start the run with When clicking ‘Execute workflow’. Fetch pending input (Google Sheets → Get row(s) in sheet) Read the newsletter tab and pull only rows where N8n Status = Pending. Iterate (Split In Batches → Loop Over Items) Process one sheet row at a time for stable memory use and pacing. Generate the newsletter (AI Agent + OpenAI Chat Model) AI Agent loads the “System Role Instructions” that define style, sections, and format. Pass Newsletter Title and About the Newsletter to the OpenAI Chat Model to produce the draft. Create a Notion page (Notion → Create Page) Create a page in your Newsletter Automation database with the page title set from Newsletter Title. Prepare long content for Notion (Code) Split the AI output into \~1,800-character chunks and wrap as Notion paragraph blocks to avoid payload limits. Write content blocks to Notion (HTTP Request → UpdateNotionBlock) Send a PATCH request to append all generated blocks so the full draft appears on the page. Mark the sheet row as done (Google Sheets → Update row in sheet) Update N8n Status = Done for the processed Newsletter Title. Continue the loop Return to Split In Batches for the next pending row until none remain. Tools integration: Google Sheets** — input queue and status tracking (Pending → Done) OpenAI** — LLM that writes the draft from provided fields Notion** — destination database for each draft page n8n Code + HTTP Request** — chunking and Notion API block updates Want auto-runs? Add a Cron trigger before step 2 and keep the flow unchanged.

Instantly fetch live Gate.io Spot Market data directly in Telegram! This workflow integrates the Gate.io REST v4 API with GPT-4.1-mini-powered AI and Telegram, giving traders real-time access to price action, order books, candlesticks, and trade data. Perfect for crypto traders, analysts, and DeFi builders who need fast and reliable exchange insights. ⚙️ How It Works A Telegram bot listens for user queries (e.g., "BTC_USDT"). The workflow securely processes the request, authenticates the user, and attaches a sessionId. The Gate AI Agent orchestrates data retrieval via Gate.io Spot Market API, including: ✅ Latest Price & 24h Stats (/spot/tickers) ✅ Order Book Depth (with best bid/ask snapshots) ✅ Klines (candlesticks) for OHLCV data ✅ Recent Trades (up to 100 latest trades) Data is optionally cleaned using Calculator (for spreads, midpoints, % changes) and Think (for formatting). An AI-powered formatter (GPT-4.1-mini) structures results into Telegram-friendly reports. The final Gate.io Spot insights are sent back instantly in HTML-formatted Telegram messages. 💡 What You Can Do with This Agent This AI-driven Telegram bot enables you to: ✅ Track real-time spot prices for any Gate.io pair ✅ Monitor order book depth (liquidity snapshots) ✅ View recent trades for activity insights ✅ Analyze candlesticks across multiple intervals ✅ Compare bid/ask spreads with calculated metrics ✅ Get clean, structured data without raw JSON clutter 🛠️ Setup Steps Create a Telegram Bot Use @BotFather on Telegram to create a bot and obtain an API token. Configure Telegram API Credentials in n8n Add your bot token under Telegram API credentials. Replace the placeholder Telegram ID in the Authentication node with your own. Import & Deploy Workflow Load Gate AI Agent v1.02.json into n8n. Configure your OpenAI API key for . Configure your Gate api key. Save and activate the workflow. Run & Test Send a query (e.g., "BTC_USDT") to your Telegram bot. Receive instant Gate.io market insights formatted for easy reading. 📺 Setup Video Tutorial Watch the full setup guide on YouTube: ⚡ Unlock real-time Gate.io Spot Market insights directly in Telegram — fast, clean, and reliable. 🧾 Licensing & Attribution © 2025 Treasurium Capital Limited Company Architecture, prompts, and trade report structure are IP-protected. No unauthorized rebranding permitted. 🔗 For support: Don Jayamaha – LinkedIn

Auto-detect news from n8n and turn into a human-approved LinkedIn post. gotoHuman is used to keep a human in the loop. There you can manually edit the AI draft of the post or request to regenerate it. How it works The workflow is triggered each day to fetch the latest version of https://blog.n8n.io. It then fetches each article, checks if it was published in the last 24 hours and uses an LLM to summarize it. An LLM then drafts a related LinkedIn post which is sent to gotoHuman for approval. In gotoHuman, the reviewer can manually edit it or ask to regenerate it with the option to even edit the prompt (Retries loop back to the AI Draft LinkedIn Post node) Approved Posts are automatically published to LinkedIn How to set up Most importantly, install the gotoHuman node before importing this template! (Just add the node to a blank canvas before importing) Set up your credentials for gotoHuman, OpenAI, and LinkedIn In gotoHuman, select and create the pre-built review template "Blog scraper agent" or import the ID: sMxevC9tSAgdfWsr6XIW Select this template in the gotoHuman node Requirements You need accounts for gotoHuman (human supervision) OpenAI (summary, draft) LinkedIn How to customize Change the blog URL to monitor. Adapt to its' HTML structure Provide the AI Draft LinkedIn Post with examples of previous posts so it picks up your writing style (consider adding gotoHuman's dataset of approved examples) Use the workflow to target other publications, like your newsletter, blog or other socials

How it works This workflow automates customer feedback management by capturing reviews through a form, analyzing them with AI for sentiment and insights, and then creating structured tasks across Monday.com, ClickUp, and HubSpot. It ensures that customer concerns are categorized, prioritized, and assigned to the right teams with actionable metadata. Step-by-step Trigger & Input The workflow starts when a customer submits the Feedback Form containing their Name, Message, Rating, and Product/Service. The submitted data is pre-processed with a Code node to cleanly extract fields for analysis. AI Analysis & Processing The extracted review is sent to OpenAI GPT-4 for analysis. AI identifies sentiment, sentiment score, category (e.g., product, service, support, delivery, pricing), department, priority, required actions, keywords, and suggested response tone. A Data Processing node enriches the output with due dates, task titles, structured descriptions, and fallback handling in case of parsing issues. Structured Output Generation An AI Agent and OpenAI Chat model transform the enriched data into a strict JSON format that is compatible with Monday.com, ClickUp, and HubSpot. This ensures consistent field order, formatting, and metadata for all downstream integrations. Task Creation in Platforms The structured task data is automatically pushed to: Monday.com → Creates an item in a specified board. ClickUp → Creates a task with mapped fields and priority. HubSpot → Creates an engagement task in CRM with due date and priority. Benefits Automates end-to-end customer feedback analysis and task creation. Ensures structured, AI-driven insights for actionable responses. Reduces manual work in categorizing and assigning reviews. Keeps customer feedback synchronized across multiple platforms (Monday.com, ClickUp, HubSpot). Improves response time by prioritizing high-impact feedback with due dates.

J.A.R.V.I.S. Multimodal AI assistant on Telegram with OpenAI This workflow transforms your Telegram bot into J.A.R.V.I.S., a powerful, multimodal AI assistant. It can understand and process text, voice messages, images, and documents. The assistant can search the web, scrape websites, generate images, perform calculations, and reference uploaded documents to provide comprehensive and context-aware responses in either text or audio format. 🧑‍💻 Who’s it for This workflow is for developers, AI enthusiasts, and businesses who want to create an advanced, interactive AI assistant on Telegram. It’s perfect for automating customer support, creating a personal AI helper, or exploring the capabilities of multimodal large language models (LLMs) in a practical application. ⚙️ How it works The workflow begins when a message is received by your Telegram bot. A Switch node then directs the data based on the message type: Text:** The message is formatted and sent directly to the main AI agent. Voice:** The audio file is downloaded from Telegram and transcribed into text using the OpenAI API. Image:** The image is downloaded and analyzed by an OpenAI vision model to understand its content. Document:** The file is downloaded and its content is stored in a temporary vector store, making it searchable for the AI. The processed input is then passed to the core "J.A.R.V.I.S." Agent node. This agent uses an OpenAI model, conversational memory, and a suite of tools (Google Search, Web Scraper, Image Generator, Calculator, and the document vector store) to formulate a response. Finally, the workflow checks if the initial message was a voice note; if so, it generates an audio response. Otherwise, it sends the answer as a text message back to the user. 🛠️ How to set up Telegram: Create a Telegram Bot - Use @BotFather to create a bot and obtain your bot token; Add Telegram API credentials in n8n with your bot token to the Receive Message Trigger node and all other Telegram nodes. In the Receive Message node, enter the chatId of the user or group authorized to interact with the bot. OpenAI: Add your OpenAI API credentials to all OpenAI, AI Agent, and AI tool nodes. SerpAPI: Add your SerpAPI credentials to the Basic Google Search node to enable web search functionality. Jina AI: Add your Jina AI API key to the Setup Node - The API Key is used on the Webpage Scraper node. ✅ Requirements Telegram Bot API credentials and Bot token. OpenAI API credentials. SerpAPI API credentials. Jina.ai API credentials 🎨 How to customize the workflow Change the AI model:** You can select a different OpenAI model in the OpenAI Chat Model node (e.g., switch from gpt-4.1 to gpt-4o) or in the Analyze Image and Transcribe nodes. Modify the AI's personality:** Edit the system prompt in the J.A.R.V.I.S. Agent node to change its name, tone, instructions, or default language. Expand its tools:** Connect more tools to the J.A.R.V.I.S. Agent node to extend its capabilities, such as connecting to a database or another third-party API. Adjust the response format:** Modify the If Audio Response node to change the conditions for sending text or audio messages. For example, you could configure it to always respond with text. 💬 Need Help? Join the Discord or ask in the Forum

How It Works Scheduled triggers run automated price checks across multiple travel data sources. The collected data is aggregated, validated, and processed through an AI analysis layer that compares trends, detects anomalies, and evaluates multi-criteria factors such as price movement, seasonality, and route demand. The system then routes results into booking preparation, report generation, and notification modules. When target price conditions are met, alerts are sent and records are updated accordingly. Setup Steps Connect Google Flights and Skyscanner APIs using authenticated tokens. Configure the OpenAI API for enhanced analysis and multi-factor evaluation. Link Google Sheets for storing historical price data. Add WordPress site credentials to enable automated report publishing. Enable email notifications for price alerts and updates. Adjust the scheduler frequency within the Schedule Price Check node to control how often the workflow runs. Prerequisites Google Flights API, Skyscanner API, flight booking service credentials, OpenAI API key, Google Sheets access, WordPress admin account, email service configured. Use Cases Travel agencies automating client alerts for price drops. Corporate travel managers monitoring bulk bookings. Customization Modify price thresholds in Multi-Criteria Decision node. Add airline or destination filters in search parameters. Benefits Eliminates manual price monitoring. Reduces booking delays through automation.

Who is this for? Job seekers who want to automate their entire job search pipeline — from discovering new listings to generating tailored resumes and cover letters — without manually browsing LinkedIn every day. What does this workflow do? This workflow runs on a schedule, scrapes LinkedIn jobs via Apify, filters out spam recruiters and wrong locations, then uses a 2-stage AI evaluation to find the best matches for your profile. Matching jobs are logged to Google Sheets and you get a Telegram notification. When you're ready to apply, a second trigger generates a tailored resume + cover letter using AI and fills in your Google Docs templates automatically. How it works Stage 1 — Scrape & Filter (runs on schedule) Schedule Trigger fires hourly (customizable cron) Apify LinkedIn Scraper pulls fresh job listings based on your keywords and location Filter nodes remove unwanted recruiter companies and jobs outside your target country HTML → Markdown converts job descriptions for better AI processing GateKeeper AI (fast, cheap model) does a quick yes/no — rejects 90% of irrelevant jobs Results are saved to a "Gatekeeper Results" Google Sheet Stage 2 — Score & Notify (for GateKeeper matches) Job Match Scorer AI (smarter model) evaluates matches in detail with a 0–100 score Jobs above your threshold are added to a "Roles to Apply" Google Sheet Telegram notification alerts you about new matches Stage 3 — Generate Resume & Apply (triggered from Google Sheets) When you update a row in your sheet, the workflow triggers AI Resume Writer generates a tailored resume + cover letter in JSON format Language detection routes to EN or DE templates (extensible to more languages) Google Drive copies your template documents and fills in all variables Links and status are updated back in Google Sheets — ready to submit Setup Guide Prerequisites n8n instance (self-hosted or cloud) Apify account (free tier works) — for LinkedIn scraping OpenRouter account — for AI models (GateKeeper + Job Match Scorer) OpenAI API key — for resume generation Google Workspace — Sheets, Docs, Drive (OAuth2) Telegram Bot — for notifications Step 1: Credentials Add the following credentials in n8n (do not hardcode API keys): HTTP Query Auth → Apify API token OpenRouter API → your OpenRouter key OpenAI API → your OpenAI key Google Sheets OAuth2 → connect your Google account Google Docs OAuth2 → same Google account Google Drive OAuth2 → same Google account Telegram API → your bot token Step 2: Google Sheets Create two Google Sheets: Sheet 1 — Gatekeeper Results Columns: title, company, location, url, score, reason, match Sheet 2 — Roles to Apply Columns: title, company, url, job_description, status, resume_link Paste each sheet's ID into the corresponding Google Sheets nodes. Step 3: Google Docs Templates Create resume and cover letter templates in Google Docs with placeholder variables like {{summary}}, {{experience_1_title}}, {{experience_1_company}}, etc. The AI output JSON keys map directly to these variables. Step 4: Customize the Workflow Set Profile node — Replace the placeholder with your full career profile (the more detailed, the better the AI results) LinkedIn URLs — Update the Apify scraper with your own search URLs (keywords, geoId, filters) GateKeeper prompt — Customize rejection criteria, "sweet spot" description, and location preferences Job Match Scorer prompt — Adjust scoring criteria to your skills Filter nodes — Update country filter and recruiter blocklist Telegram Chat ID — Set your personal chat ID for notifications Google Sheet/Doc/Drive IDs — Link all nodes to your own documents Step 5: Activate Turn on the Schedule Trigger and the Google Sheets Trigger. You're live! Nodes used in this workflow Schedule Trigger HTTP Request (Apify) Filter, Switch, Merge Markdown (HTML to Markdown) LangChain LLM Chain (OpenRouter — Haiku for GateKeeper, Sonnet for Scorer) OpenAI (GPT for resume generation) Code (JSON parsing) Google Sheets, Google Docs, Google Drive Telegram Questions or need help? If you have any questions about this workflow or want the ready-made Google Docs/Sheets templates to get started faster, feel free to reach out: 👉 Connect with me on LinkedIn

How It Works User sends a reminder request via Telegram (e.g., “Remind me to clean the garage tomorrow at 12 pm”). The request is parsed by AI Agent and stored in Airtable with a unique reminder code. The reminder workflow checks Airtable at scheduled intervals and sends a Telegram notification when the reminder is due. Each reminder includes a unique cancel code (e.g., Reply 4936 to stop this reminder). If the user replies with the code, the bot searches Airtable, deletes the reminder, and confirms the deletion in Telegram. If the code doesn’t exist, the bot replies “Code not found.” ⚡ Setup Steps Create a Telegram Bot Use BotFather on Telegram. Run /newbot and copy your bot token. Add the token in your Telegram Trigger and Telegram Send nodes in n8n. Set Up Airtable Create an Airtable base called REMINDER-TABLE. Add a table with fields: title (Text) – reminder text due_at (Date/Time) – when the reminder is due chat_id (Text) – user’s Telegram chat ID code (Number/Text) – unique cancel code Generate an API key / Personal Access Token and connect it in n8n. Import This Workflow In n8n, click Import Workflow. Paste the JSON template. Connect your Telegram and Airtable credentials. Activate the Workflow Start the workflow in n8n Cloud or Self-Hosted. Send a test reminder in Telegram (e.g., “Remind me in 5 minutes to call mom”). When notified, reply with the cancel code to test deletion. Optional Customizations Modify reminder frequency (Every 5 minutes node). Change reminder message formatting in the Format Message node. Add logging/analytics by connecting Google Sheets or another DB. ⚡ Result: You now have a fully automated AI-powered Telegram Reminder Bot with Airtable storage, cancel codes, and real-time notifications!