Workflow Templates

✅ What problem does this workflow solve? Automatically monitor multiple websites every 5 minutes, log downtime, notify your team instantly via multiple channels, and track uptime/downtime in a Google Sheet—without relying on expensive monitoring tools. ⚙️ What does this workflow do? Triggers every 5 minutes to monitor website health. Fetches a list of website URLs from a Google Sheet. Checks the status of each website one by one. Sends instant alerts if a website is down (Email, Slack, Telegram, Voice Call). Logs downtime events in Google Sheets. Tracks when websites are back up and updates the log. Sends recovery notifications when a site is live again (Email, Slack, Telegram). 🔧 Setup 📄 Google Sheets Setup Sheet 1: List of website URLs to monitor. Sheet 2: Log to store uptime/downtime records. Sample Format: https://docs.google.com/spreadsheets/d/1_VVpkIvpYQigw5q0KmPXUAC2aV2rk1nRQLQZ7YK2KwY/edit?usp=sharing ✉️ Gmail, Slack & Telegram Setup Connect Gmail, Slack, and Telegram to n8n. Configure each service with proper credentials or OAuth. 📞 Vapi (Voice Call) Setup Create a Vapi account. Generate an API key. Configure API Parameters (vapi_api_key, assistant_id, number, phone_number_id) on VAPI Node. Insert the First Message specified in the Workflow. 🧠 How it Works ⏱ 1. Scheduled Monitoring A Schedule Trigger runs the workflow every 5 minutes. It reads the list of URLs from the Google Sheet and loops through each one. 🌍 2. Website Health Check Each website is pinged to check if it’s online. 🔴 3. If Website is Down: It verifies if a downtime record already exists. If not, it: Adds a new row in the Google Sheet with the timestamp. Sends notifications via: 📧 Email 💬 Slack 📲 Telegram 📞 Voice Call via Vapi 🟢 4. If Website is Back Up: It fetches the matching downtime record. Updates the sheet with: ✅ Uptime timestamp ⏱ Total downtime duration Sends recovery notifications via: 📧 Email 💬 Slack 📲 Telegram (No phone call is made for uptime.) 👤 Who can use it? This is perfect for: 🚀 Startups 👨‍💻 Freelance Developers 🛠 SaaS Product Owners 🖥 IT/DevOps Teams If you're looking to replace tools like UptimeRobot, Pingdom, or StatusCake, this no-code solution gives you full control, customization, and cost-efficiency.

Why Teachers now spend 3-4 hours per lesson creating materials and resources from scratch. With additional/special needs, this makes it difficult to create additional materials. This is unsustainable and takes their time away from teaching. Tailored for UK teachers but can be expanded globally with prompt and form enhancements. How it works I built a system with three specialized AI agents that create complete lesson packages and automatically uploads a document in Google drive and puts an appointment in calendar to review the document. Features Research agent to pull specific information including special education needs and curriculums. The scoring and assessment agent to generate tailored assessment plans, assignments, grading mechanism based on chosen requirements. The integration agent just provides ideas to expand to other tools. In nfuture there is opportunity to add on Kahoot or other tools to create quizzes. Finally the enriched document is emailed and a calendar invite is sent for review. What you need N8N Any LLM API Key (I used OpenAI) Google drive integration Google calendar integration Modify the email id from XXX@gmail.com to your Email id in email component. Support Watch this video for intro on how it works. Contact me on info@pankstr.com for any queries.

AI-powered WhatsApp booking system with instant SMS confirmations Who is this for? This workflow is designed for solo entrepreneurs, consultants, coaches, clinics, or any business that handles client appointments and wants to automate the entire scheduling experience via WhatsApp — without the need for live agents. What problem is this workflow solving? Responding to inbound messages, collecting booking details, suggesting available times, and sending reminders can be a huge time drain. This workflow eliminates manual handling by: Automating WhatsApp conversations with an AI assistant Booking appointments directly into Cal.com Sending timely SMS reminders before appointments It ensures you never miss a lead or a follow-up — even while you sleep. What this workflow does From a single WhatsApp message, the workflow: Triggers via a WhatsApp webhook Uses GPT-4 to handle conversation flow and qualify the prospect Collects name, email, selected service Calls Cal.com API to fetch available time slots Books the appointment and stores it in Google Sheets Sends a confirmation message via WhatsApp Periodically scans for upcoming appointments Sends SMS reminders to clients 2 hours before their session Setup Connect your Webhook node to a WhatsApp API (e.g., 360dialog, Twilio, or Ultramsg) Add your OpenAI API key for the GPT-4 nodes Configure your Cal.com API key and set your calendar ID Link your Google Sheets with fields like: name, email, date, time, status, reminder_sent Connect your SMS service (e.g., sms77) with API credentials Adjust the schedule in the reminder node as needed How to customize this workflow to your needs Change the language or tone of the AI assistant** by editing the system prompt in the GPT node Filter available time slots** by service, team member, or duration Modify the reminder timing** (e.g., 1 hour before, 24h before, etc.) Add conditional logic** to route users to different booking flows based on their responses Integrate additional CRMs** or notification channels like email or Slack 📄 Documentation: Notion Guide Need help customizing? Contact me for consulting and support : Linkedin / Youtube

This n8n template demonstrates one approach to achieve a more natural and less frustration conversations with AI agents by reducing interrupts by predicting the end of user utterances. When we text or chat casually, it's not uncommon to break our sentences over multiple messages or when it comes to voice, break our speech with the odd pause or umms and ahhs. If an agent replies to every message, it's likely to interrupt us before we finish our thoughts and it can get very annoying! Previously, I demonstrated a simple technique for buffering each incoming message by 5 seconds but that approach still suffers in some scenarios when more time is needed. This technique has no arbitrary time limit and instead uses AI to figure out when its the agent's turn based on the user's message, allowing for the user to take all the time they need. How it works Telegram messages are received but no reply is generated for them by default. Instead they are sent to the prediction subworkflow to determine if a reply should be generated. The prediction subworkflow begins by checking Redis for the current user's prediction session state. If this is a new "utterance", it kicks off the "predict end of utterance" loop - the purpose of which is to buffer messages in a smart way! New users message can continue to be accepted by the workflow until enough is collected to allow our prediction classifier to determine the end of the utterance has been reached. The loop is then broken and the buffered chat messages are combined and sent to the AI agent to generate a response and sent to the user via the telegram node. The prediction session state is then deleted to signal the workflow is ready to start again with a new message. How to use This system sits between your preferred chat platform and the AI agent so all you need to do is replace the telegram nodes as required. Where LLM-only prediction isn't working well enough, consider more traditional code-based checking of heuristics to improve the detection. Ideally you'll want a fast but accurate LLM so your user isn't waiting longer than they have to - at time of writing Gemini-2.5-flash-lite was the fastest in testing but keep a look out for smaller and more powerful LLMs in the future. Requirements Gemini for LLM Redis for session management Telegram for chat platform

✅ What problem does this workflow solve? Shopify and E-Commerce store owners often struggle to create engaging 3D videos from static product images. This workflow automates that entire process—from image upload to video delivery—so store owners can get professional-looking 3D videos without any manual editing or follow-up. ⚙️ What does this workflow do? Accepts a 2D product image and name via a public n8n form. Generates a unique slug and folder in Google Drive for the product. Uploads the original image to Google Drive and logs data in a spreadsheet. Removes the background from the image using remove.bg API. Uploads the cleaned image to Google Drive and updates the spreadsheet. Creates a 3D product video using the cleaned image via the Fal.ai API. Periodically checks the video creation status. Once completed, download the video, upload it to Google Drive, and log the link. Notifies the store owner via email with the video download link. 🔧 Setup 🟢 Google Services Google Drive**: Create and connect a folder where all product assets will be stored. Google Spreadsheet**: A spreadsheet to log the product name, original image link, cleaned image link, and final video URL. Gmail**: Connect Gmail to send the final notification email to the store owner. 🔑 API Keys Required Remove.bg**: Get an API key from remove.bg. Fal.ai**: Sign up at fal.ai and obtain your API key to use the image-to-video generation service. 🧠 How it Works 📝 1. Product Form Submission A store owner submits the product name and 2D image via a public n8n form. 🗂 2. Organize in Google Drive A unique slug is generated for the product. A new folder is created inside Google Drive using that slug. The original image is uploaded into the folder. 📊 3. Record in a Spreadsheet The product name and original image URL are stored in a Google Sheet. 🧹 4. Background Removal The uploaded image is processed through remove.bg API to eliminate noisy or cluttered backgrounds. The cleaned image is uploaded back into the product’s Drive folder. The cleaned image link is updated in the spreadsheet. 🎥 5. Create 3D Video (via Fal.ai) The cleaned image is passed to the Fal.ai video generation API. The workflow periodically checks the status until the video is ready. ☁️ 6. Store Final Video Once the video is ready, the file is downloaded. The final video is uploaded into the same Google Drive folder. Its link is saved in the spreadsheet next to the respective product entry. 📧 7. Notify the Store Owner An automated email is sent to the store owner with the video link, letting them know it's ready for use—no waiting, no manual follow-up needed. 👤 Who can use it? This workflow is ideal for: 🛍 Shopify Sellers 🧺 E-commerce Store Owners 📸 Product Photographers 🎬 Marketing Teams 🤖 Automation Enthusiasts If you want to automate 3D product video creation using AI—this is the no-code workflow you’ve been waiting for!

Transform your meetings into actionable insights automatically! This workflow captures meeting audio, transcribes conversations, generates AI summaries, and emails the results to participants—all without manual intervention. What's the Goal? Auto-record meetings** when they start and stop when they end Transcribe audio** to text using Vexa Bot integration Generate intelligent summaries** with AI-powered analysis Email summaries** to meeting participants automatically Eliminate manual note-taking** and post-meeting admin work Never miss important discussions** or action items again Why Does It Matter? Save 90% of Post-Meeting Time**: No more manual transcription or summary writing Never Lose Key Information**: Automatic capture ensures nothing falls through cracks Improve Team Productivity**: Focus on discussions, not note-taking Perfect Meeting Records**: Searchable transcripts and summaries for future reference Instant Distribution**: Summaries reach all participants immediately after meetings How It Works Step 1: Meeting Detection & Recording Start Meeting Trigger**: Detects when meeting begins via Google Meet webhook Launch Vexa Bot**: Automatically joins meeting and starts recording End Meeting Trigger**: Detects meeting end and stops recording Step 2: Audio Processing & Transcription Stop Vexa Bot**: Ends recording and retrieves audio file Fetch Meeting Audio**: Downloads recorded audio from Vexa Bot Transcribe Audio**: Converts speech to text using AI transcription Step 3: AI Summary Generation Prepare Transcript**: Formats transcribed text for AI processing Generate Summary**: AI model creates concise meeting summary with: Key discussion points Decisions made Action items assigned Next steps identified Step 4: Distribution Send Email**: Automatically emails summary to all meeting participants Setup Requirements Google Meet Integration: Configure Google Meet webhook and API credentials Set up meeting detection triggers Test with sample meeting Vexa Bot Configuration: Add Vexa Bot API credentials for recording Configure audio file retrieval settings Set recording quality and format preferences AI Model Setup: Configure AI transcription service (e.g., OpenAI Whisper, Google Speech-to-Text) Set up AI summary generation with custom prompts Define summary format and length preferences Email Configuration: Set up SMTP credentials for email distribution Create email templates for meeting summaries Configure participant list extraction from meeting metadata Import Instructions Get Workflow JSON: Copy the workflow JSON code Open n8n Editor: Navigate to your n8n dashboard Import Workflow: Click menu (⋯) → "Import from Clipboard" → Paste JSON → Import Configure Credentials: Add API keys for Google Meet, Vexa Bot, AI services, and SMTP Test Workflow: Run a test meeting to verify end-to-end functionality Your meetings will now automatically transform into actionable summaries delivered to your inbox!

Social Media Analysis and Automated Email Generation > by Thomas Vie Thomas@pollup.net Who is this for? This template is ideal for marketers, lead generation specialists, and business professionals seeking to analyze social media profiles of potential leads and automate personalized email outreach efficiently. What problem is this workflow solving? Manually analyzing social media profiles and crafting personalized emails can be time-consuming and prone to errors. This workflow streamlines the process by integrating social media APIs with AI to generate tailored communication, saving time and increasing outreach effectiveness. What this workflow does: Google Sheets Integration: Start with a Google Sheet containing lead information such as LinkedIn URL, Twitter handle, name, and email. Social Media Data Extraction: Automatically fetch profile and activity data from Twitter and LinkedIn using RapidAPI integrations. AI-Powered Content Generation: Use OpenAI's Chat Model to analyze the extracted data and generate personalized email subject lines and cover letters. Automated Email Dispatch: Send the generated email directly to the lead, with a copy sent to yourself for tracking purposes. Progress Tracking: Update the Google Sheet to indicate completed actions. Setup: Google Sheets: Create a sheet with the columns: LinkedIn URL, name, Twitter handle, email, and a "done" column for tracking. Populate the sheet with your leads. RapidAPI Accounts: Sign up for RapidAPI and subscribe to the Twitter and LinkedIn API plans. Configure API authentication keys in the workflow. AI Configuration: Connect OpenAI Chat Model with your API key for text generation. Email Integration: Add your email credentials or service (SMTP or third-party service like Gmail) for sending automated emails. How to customize this workflow to your needs: Modify the AI Prompt:** Adapt the prompt in the AI node to better align with your tone, style, or specific messaging framework. Expand Data Fields:** Add additional data fields in Google Sheets if you require further personalization. API Limits:** Adjust API configurations to fit your usage limits or upgrade to higher tiers for increased data scraping capabilities. Personalize Email Templates:** Tweak email formats to suit different audiences or use cases. Extend Functionality:** Integrate additional social media platforms or CRM tools as needed. By implementing this workflow, you’ll save time on repetitive tasks and create more effective lead generation strategies.

⚠️ Important Disclaimer: This template is only compatible with a self-hosted n8n instance using a community node. Who is this for? This workflow is ideal for digital content creators, marketers, social media managers, and automation enthusiasts who want to produce fully automated vertical video content featuring inspirational or motivational quotes. Specifically tailored for Thai language, it effectively demonstrates integration of AI-generated imagery, video, ambient sound, and visually appealing quote overlays. What problem is this workflow solving? Manually creating high-quality, vertically formatted quote videos is often repetitive, time-consuming, and involves multiple tedious steps like selecting suitable visuals, editing audio tracks, and correctly overlaying text. Additionally, manual uploading to platforms like YouTube and maintaining accurate content records are prone to errors and inefficiencies. What this workflow does: Fetches a quote, author, and scenic background description from a Google Sheet. Automatically generates a vertical background image using the Flux AI (txt2img) API. Transforms the AI-generated image into a subtly animated cinematic vertical video using the Kling video-generation API. Generates an immersive, ambient background sound using ElevenLabs’ sound generation API. Dynamically overlays the selected Thai-language quote and author text onto the generated video using FFmpeg, ensuring visually appealing typography (e.g., Kanit font). Automatically uploads the final video to YouTube. Updates the resulting YouTube video URL back to the Google Sheet, keeping your content records current and well-organized. Setup Requirements: This workflow requires a self-hosted n8n instance, as the execution of FFmpeg commands is not supported on n8n Cloud. Ensure FFmpeg is installed on your self-hosted environment. API keys and accounts setup for Flux, Kling, ElevenLabs, Google Sheets, Google Drive, and YouTube. Google Sheets Setup: Your Google Sheet must include these columns: Index** Unique identifier for each quote Quote (Thai)** Quote text in Thai language (or your chosen language) Pen Name (Thai)** Author or pen name of the quote's creator Background (EN)** Short English description of the scene (e.g., "sunrise over mountains") Prompt (EN)** Detailed English prompt describing the image/video scene (e.g., "peaceful sunrise with misty mountains") Background Image** URL of AI-generated image (updated automatically) Background Video** URL of generated video (updated automatically) Music Background** URL of generated ambient audio (updated automatically) Video Status** YouTube URL (updated automatically after upload) A ready-to-use Google Sheets template is provided [here (provide your actual link)]. To help you get started quickly, you can use this template spreadsheet. Next steps: Authenticate Google Sheets, Google Drive, YouTube API, Flux AI, Kling API, and ElevenLabs API within n8n. Ensure FFmpeg supports fonts compatible with your chosen language (for Thai, "Kanit" font is recommended). Prepare your Google Sheets with desired quotes, authors, and image/video prompts. How to customize this workflow to your needs: Fonts:** Adjust font type, size, color, and positioning within the provided FFmpeg commands in the workflow’s code nodes. Verify that selected fonts properly support your target language. Media Customization:** Customize the scene descriptions in your Google Sheet to change image/video backgrounds automatically generated by AI. Quote Management:** Easily manage, add, or update quotes and associated details directly via Google Sheets without workflow modifications. Audio Ambiance:** Customize or adjust the ambient sound prompt for ElevenLabs within the workflow’s HTTP Request node to match your video's desired mood. Benefits of using AI-generated content and localized fonts: Leveraging AI-generated visual and audio elements along with localized fonts greatly enhances audience engagement by creating visually appealing, professional-quality content tailored specifically for your target audience. This automated workflow drastically reduces production time and manual effort, enabling rapid, consistent content creation optimized for platforms such as YouTube Shorts, Instagram Reels, and TikTok.

Who Is This For? This workflow is designed for AI engineers, automation specialists, and content creators who need a scalable system to dynamically manage prompts stored in GitHub. It eliminates manual updates, enforces required variable checks, and ensures that AI interactions always receive fully processed prompts. 🚀 What Problem Does This Solve? Manually managing AI prompts can be inefficient and error-prone. This workflow: ✅ Fetches dynamic prompts from GitHub ✅ Auto-populates placeholders with values from the setVars node ✅ Ensures all required variables are present before execution ✅ Processes the formatted prompt through an AI agent 🛠 How This Workflow Works This workflow consists of three key branches, ensuring smooth prompt retrieval, variable validation, and AI processing. 1️⃣ Retrieve the Prompt from GitHub (HTTP Request → Extract from File → SetPrompt) The workflow starts manually or via an external trigger. It fetches a text-based prompt stored in a GitHub repository. The Extract from File Node retrieves the content from the GitHub file. The SetPrompt Node stores the prompt, making it accessible for processing. 📌 Note: The prompt must contain n8n expression format variables (e.g., {{ $json.company }}) so they can be dynamically replaced. 2️⃣ Extract & Auto-Populate Variables (Check All Prompt Vars → Replace Variables) A Code Node scans the prompt for placeholders in the n8n expression format ({{ $json.variableName }}). The workflow compares required variables against the setVars node: ✅ If all variables are present, it proceeds to variable replacement. ❌ If any variables are missing, the workflow stops and returns an error listing them. The Replace Variables Node replaces all placeholders with values from setVars. 📌 Example of a properly formatted GitHub prompt: Hello {{ $json.company }}, your product {{ $json.features }} launches on {{ $json.launch_date }}. This ensures seamless replacement when processed in n8n. 3️⃣ AI Processing & Output (AI Agent → Prompt Output) The Set Completed Prompt Node stores the final, processed prompt. The AI Agent Node (Ollama Chat Model) processes the prompt. The Prompt Output Node returns the fully formatted response. 📌 Optional: Modify this to use OpenAI, Claude, or other AI models. ⚠️ Error Handling: Missing Variables If a required variable is missing, the workflow stops execution and provides an error message: ⚠️ Missing Required Variables: ["launch_date"] This ensures no incomplete prompts are sent to AI agents. ✅ Example Use Case 📜 GitHub Prompt File (Using n8n Expressions) Hello {{ $json.company }}, your product {{ $json.features }} launches on {{ $json.launch_date }}. 🔹 Variables in setVars Node { "company": "PropTechPro", "features": "AI-powered Property Management", "launch_date": "March 15, 2025" } ✅ Successful Output Hello PropTechPro, your product AI-powered Property Management launches on March 15, 2025. 🚨 Error Output (If Missing launch_date) ⚠️ Missing Required Variables: ["launch_date"] 🔧 Setup Instructions 1️⃣ Connect Your GitHub Repository Store your prompt in a public or private GitHub repo. The workflow will fetch the raw file using the GitHub API. 2️⃣ Configure the SetVars Node Define the required variables in the SetVars Node. Make sure the variable names match those used in the prompt. 3️⃣ Test & Run Click Test Workflow to execute. If variables are missing, it will show an error. If everything is correct, it will output the fully formatted prompt. ⚡ How to Customize This Workflow 💡 Need CRM or Database Integration? Connect the setVars node to an Airtable, Google Sheets, or HubSpot API to pull variables dynamically. 💡 Want to Modify the AI Model? Replace the Ollama Chat Model with OpenAI, Claude, or a custom LLM endpoint. 📌 Why Use This Workflow? ✅ No Manual Updates Required – Fetches prompts dynamically from GitHub. ✅ Prevents Broken Prompts – Ensures required variables exist before execution. ✅ Works for Any Use Case – Handles AI chat prompts, marketing messages, and chatbot scripts. ✅ Compatible with All n8n Deployments – Works on Cloud, Self-Hosted, and Desktop versions.

🚀 Local Multi-LLM Testing & Performance Tracker This workflow is perfect for developers, researchers, and data scientists benchmarking multiple LLMs with LM Studio. It dynamically fetches active models, tests prompts, and tracks metrics like word count, readability, and response time, logging results into Google Sheets. Easily adjust temperature 🔥 and top P 🎯 for flexible model testing. Level of Effort: 🟢 Easy – Minimal setup with customizable options. Setup Steps: Install LM Studio and configure models. Update IP to connect to LM Studio. Create a Google Sheet for result tracking. Key Outcomes: Benchmark LLM performance. Automate results in Google Sheets for easy comparison. Version 1.0

Automatically scrape X (Twitter) for posts hiring specific roles (e.g., automation engineers, video editors, graphic designers), filter true hiring intent with AI, deduplicate in Google Sheets, and alert via Telegram. What it does Pulls recent X/Twitter posts for multiple role keywords via Apify. Normalizes each post (text, author, links, location). Uses an AI Agent to keep only posts where the author is hiring (not self-promo). Checks Google Sheets for duplicates by URL before saving. Writes qualified posts to a sheet and sends a Telegram notification. We are using n8n automation roles as the example here How it works (Step by Step) Schedule Trigger – Runs on an interval (currently every 12 hours). Scrape X/Twitter – Apify tweet-scraper fetches up to 50 latest posts for keywords like: n8n developer, looking for n8n, n8n expert, hire AI automation, looking for AI automation. Normalize Fields – Set node maps to: url, text, author.userName, author.url, author.location. AI Filter & Dedupe Check Accept only clear hiring posts for n8n/AI automation roles (reject self-promotion). Queries Google Sheets to see if url already exists; duplicates are dropped. Gate – IF node passes only non-empty AI outputs. Parse JSON Safely – Code node extracts/validates JSON from the AI output. Save to Google Sheets – Appends/updates a row (matching on url). Telegram Alert – Sends a message with the tweet URL, author, location, and text. Who it’s for Freelancers, agencies, and job seekers who want a steady radar of real hiring posts for their target roles. Customization Ideas Swap keywords to track other roles (video editors, designers, copywriters, etc.). Add Slack/Discord notifications. Extend the AI rules (e.g., different geographies or role scopes). Treat the sheet as a mini-CRM (status, outreach date, notes).

Turn plain-language chat like “Tomorrow 9 AM: write blog post” into neatly organised Todoist tasks with GPT-4o and n8n—zero code. 🪄 Ultimate Personal Todoist Agent Turn natural-language requests into perfectly-organized Todoist tasks—all on autopilot inside n8n. > “Add Finish quarterly report by Friday afternoon” → the agent creates the task, sets the due date & priority, and even drops it into the right project. ✨ 🌟 Why this workflow rocks All-in-one Todoist super‑powers** – create, update, complete, move, archive… every major Todoist endpoint is wired up (tasks, projects, sections, labels, comments). LLM‑powered intent detection** – an OpenAI model interprets plain-English (or emoji‑filled!) messages so you don’t have to remember slash‑commands. Minimal setup** – just two credentials and you’re live. Battle‑tested building block** – use it as‑is, or plug the Todoist Agent node into your own agents & chatbots. 🛠️ What you’ll need | Credential | Where it’s used | How to set it up | | ------------------ | -------------------------------------- | --------------------------------------------------------------------------------------------- | | OpenAI API | Orchestrator & LLM nodes | Paste your OpenAI secret key into an OpenAI credential in n8n. | | Todoist OAuth2 | Todoist node and HTTP Request node | Log in Todoist from your browser to set up credential in n8n. | > That’s it—no webhooks, no extra secrets. > Tested with *gpt‑4o‑latest* – the fastest & most accurate model in our trials. ⚡ Quick‑start (5 minutes) Import the JSON template (hit ▶️ Try it out on the n8n template page or drag‑drop the file into your canvas). Select your credentials in the two credential dropdowns. Click Test workflow. In the sample Function node, tweak the message field (e.g. “Tomorrow at 9 am: write blog post”). Run → watch your new Todoist task appear. (Optional) Swap the Function node for your favourite chat trigger (Telegram, Slack, WhatsApp, Discord, you name it). Boom—your personal Todoist genie is alive! 🧞‍♂️ 🧩 How it works (under the hood) [Trigger / Chat message] │ ▼ [🗂️ Orchestrator Agent] ← OpenAI Chat Model + Short‑term Memory │ ↳ Parses intent & entities │ ▼ [🤖 Todoist Agent] ← 15+ Todoist endpoints │ ↳ Executes the right call (create, update, complete, etc.) ▼ [Done ✅ ] The Orchestrator is an example. In production you can drop it and simply expose the Todoist Agent as a tool for any other agent workflow. 🎛️ Customising & extending | Idea | How to do it | | ------------------------- | ---------------------------------------------------------------------------------------- | | Notion / Sheets sync | After the Todoist Agent node, add a Notion or Google Sheets node to log completed items. | | Voice commands | Swap the chat trigger for a Speech‑to‑Text node (e.g. Whisper). | 🤝 Need custom automations? Want me to build or tweak something for you? → Email maxemelyanenko@gmail.com and let’s make it happen! ⚠️ What’s not included (yet) Shared projects & other Todoist Pro/Business endpoints. File attachments in the comments. Editing comments. Pull requests welcome! 🙌