Self-learning AI assistant with permanent memory | GPT,Telegram & Pinecone RAG
Your AI secretary that self-learning every day and remembers everything you said (text, audio, image). Imagine having a personal AI secretary accessible right from your Telegram, ready to assist you with information and remember everything you discuss. This n8n workflow transforms Telegram into your intelligent assistant, capable of understanding text, audio, and images, and continuously learning from your interactions. It integrates RAG's offline data ingestion and online querying functionalities, letting you save inspiration and key information permanently in real-time, and giving you an AI assistant that remembers all your dialogues and information. It builds and queries a powerful vector database in real-time, ensuring relevant and accurate responses. Video guidance on how to set up Telegram integration is also included. Who is this for? This template is ideal for: Individuals seeking a personal AI assistant for quick information retrieval and note-taking. Professionals who need to keep track of important conversations and insights. Anyone interested in leveraging the power of Retrieval-Augmented Generation (RAG) and vector databases for personal knowledge management. Users who want a self-learning AI that improves over time based on their interactions. What problem is this workflow solving? This workflow integrates RAG's offline data ingestion and online querying functionalities, letting you save inspiration and key information permanently in real-time, and giving you an AI assistant that remembers all your dialogues and information. This workflow addresses the challenge of information overload and the need for an easily accessible, personalized knowledge base. It eliminates the need to manually organize notes and search through past conversations. By automatically storing and retrieving information from a vector database, this workflow makes it effortless to access the knowledge you need, when you need it. It also provides a way to retain information from various media types like voice notes and images. What this workflow does: This workflow automates the following steps: Instant Information Capture: Receives text messages, audio notes (transcribed), and images (with content analysis) directly from your Telegram. Intelligent Question Answering: When you ask a question, the AI searches its knowledge base (Pinecone vector store) for relevant information and provides a comprehensive answer. It even considers your recent conversations for context. Automatic Knowledge Storage: When you make a statement or provide information, the AI extracts key details and saves them in a Google Docs "memory palace." Daily Self-Learning: Every day, the workflow automatically takes all the information stored in the Google Docs, converts it into a vector representation, and adds it to its knowledge base (Pinecone vector store). This ensures the AI continuously learns and remembers everything you've shared. Image Understanding: Extracts text and information from images you send. Audio Transcription: Automatically transcribes your voice notes into text for processing and storage. Short-Term Memory: Remembers recent interactions within a session for more context-aware conversations. Setup: To get started, you'll need to connect the following services to your n8n instance: Telegram: Connect your Telegram bot API credentials. A video guidance is included for telegram integration setup. OpenAI: Provide your OpenAI API key for audio transcription and image analysis. Pinecone: Set up a Pinecone account and provide your API key and environment. Create a namespace in Pinecone. Google Docs: Connect your Google account with access to Google Docs. You'll need to create a Google Doc that will serve as the daily "memory palace" and provide its ID in the workflow. How to customize this workflow: Adjust the AI Agent's Personality: Modify the system prompt in the "AI Agent" node to tailor the AI's tone and behavior. Expand Knowledge Sources: Integrate other data sources into the daily learning process, such as emails or other documents, by adding more nodes to the scheduled trigger workflow. Add More Tools for the AI Agent: Integrate additional tools into the AI Agent, such as web search or other APIs, to further enhance its capabilities. Modify the Daily Schedule: Adjust the schedule trigger to run at a different time or interval.
By TianyiSync tasks automatically from Todoist to Notion
This workflow checks if the task in Todoist has a specific label and based on that creates a new database page in Notion. Prerequisites Todoist account and Todoist credentials Notion account and Notion credentials How it works To start the workflow add a task to Todoist and mark it with a label, e.g. “send-to-n8n”. Wait a maximum of 30 seconds. Todoist node identifies the tasks marked as “send-to-n8n”. Notion node creates a new Notion database page. Notice Notion has a new task now with the same name as in Todoist.
By n8n TeamViral ASMR video factory: Automatically generate viral videos on autopilot.
🚀 Overview This automation is a complete content creation engine for your social media. It endlessly designs, generates, and organizes unique and oddly satisfying ASMR videos, ensuring you always have fresh, viral-style content ready to post on platforms like TikTok, YouTube Shorts, and Instagram Reels. Video Examples 😩 The Problem Consistently creating viral content is exhausting. You're constantly battling creative burnout, trying to come up with new ideas that are fresh and engaging. For every video, you have to brainstorm an idea, write a detailed prompt for an AI generator, wait for the video, and then manually track what you've already posted. This manual process is slow, repetitive, and a major roadblock to scaling your content output. ✨ The Solution This workflow acts as your personal, automated content creation employee. When you trigger it, the automation first checks a Google Sheet to see what videos it has already made. Then, a built-in "Idea Agent" cleverly brainstorms a brand new, unused concept (like a "glass banana" or "glass pomegranate"). Next, it passes this idea to a "Prompt Agent," which writes a perfectly detailed, sensory-rich script designed to produce a stunning, hyper-realistic video. The script is sent to an AI video generator, and the workflow waits patiently for it to finish. Once the video is ready, the automation saves the final video link neatly into your Google Sheet and cleans up the oldest entry, creating a self-sustaining content machine. ⚙️ Simple Setup This workflow is a pre-built blueprint, designed to be up and running in minutes! Upload: Simply upload the provided JSON file into your n8n instance. Connect: Connect your app credentials (e.g., your Google, OpenAI, and Fal accounts). The workflow will show you exactly where. Activate: Turn the workflow on, and it's ready to go! Let your new automated employee get to work. --- 🌐 Explore more workflows ❤️ Buy more workflows at: adamcrafts 🦾 Custom workflows at: adamcrafts@cloudysoftwares.com adamaicrafts@gmail.com > Build once, customize endlessly, and scale your video content like never before.
By Abdellah HomraniTelegram to Spotify with OpenAI
Search music and play to Spotify from Telegram This workflow is a simple demonstration on accessing a message model from Telegram and it makes searching for songs an easy task even if you can't remember the artist or song name. An OpenAI message model tries to figure out the song and sends it to an active Spotify device. Use case Imagine an office where you play music in the background and the employees can control the music without having to login to the playing account. How it works You describe the song in Telegram. Telegram bot sends the text to n8n. An OpenAI message model tries to find the song. Spotify gets the search query string. First match is then added to queue. -- If there is no match a message is sent to Telegram and the process ends. We change to the next track in the list. We make sure the song starts playing by trying to resume. We fetch the currently playing track. We return "now playing" information to Telegram: Song Name - Artist Name - Album Name. Error handling Every Spotify step has it's on error handler under settings where we output the error. Message parser receives the error and sends it to Telegram. Requirements Active workflow* OpenAI API key Telegram bot Spotify account and Oauth2 API Spotify active on a device .* The Telegram trigger is activated only if this workflow is active. You can however TEST the workflow in the editor by clicking "Test step" and then it waits for the Telegram event. When event is received, just step through all steps or just clicking "Test step" on the "Fetch Now Playing" node. . You must have a Spotify device active when trying to communicate with a device. Open Spotify and play something - not it is active.
By Alexander BentlundAutomate Microsoft Teams meeting analysis with GPT-4.1, Outlook & Mem.ai
Automate Microsoft Teams Meeting Analysis with GPT-4.1, Outlook & Mem.ai Watch the YouTube video to get started Follow along with the blog post Template Overview This advanced n8n template automates Microsoft Teams meeting analysis, knowledge base creation, and email drafting directly from meeting recordings and transcripts. It provides end-to-end automation for the following use cases: Meeting Analysis Connects to Microsoft Graph to retrieve meeting recordings, chat messages, and transcripts. Analyses meeting content using AI models. Extracts key points, action items, questions, and themes from meetings automatically. AI-Powered Web App Automatically creates a detailed report from past meetings. Stores meeting summaries, metadata, and insights into an easy-to-browse frontend. New meetings are added dynamically without manual work. Knowledge Base Indexing (via Mem.ai) Uploads extracted meeting data into a structured knowledge base. Supports categorisation, search and chat functionality across meetings. Draft Follow-Up Emails Draft personalised follow-up emails for meeting participants. Email drafts include: Meeting summary Key decisions Action items Emails can be sent manually with a human in the loop context via Microsoft Outlook integration. Core Components Microsoft Graph API for accessing meetings, chats, files, and user profiles. SharePoint API for file storage and search. n8n Webhooks to trigger processes dynamically. Generic OAuth2 authentication for seamless Microsoft access. JavaScript Code Nodes for flexible, intelligent parsing and structuring of meeting data. AI/LLM nodes for summarisation and content creation. Designed to be scalable, modular, and easily customisable for different organisation sizes and industries. 🛡️ Note Failure to correctly configure Azure permissions will prevent the template from functioning. Ensure admin approval is fully completed during setup. Important Prerequisites ⚠️ Administrator consent is required This template requires a Microsoft 365 Global Administrator or Application Administrator to grant admin consent to a set of Microsoft Graph and SharePoint API scopes. Basic Azure App Registration knowledge is required: You need to set up an Azure App Registration manually, configure OAuth2 authentication, and assign specific API permissions. A setup guide is included, but familiarity with: App registrations API permissions Client secrets OAuth2 flows is highly recommended. Knowledge of Postgres is required The template includes a SQL script to create the required Postgres table (see blog post). You are responsible for hosting your own database (You can use Supabase with the Postgres connection string).
By Wayne SimpsonAutomate testing and collect responses via Telegram in Postgres (module "Quiz")
Who is this for? This template is ideal for educators, HR professionals, and anyone looking to automate testing and collect responses through Telegram, while storing results in a Postgres database. What problem is this workflow solving? Manually organizing and managing tests can be time-consuming and prone to error. This workflow automates the test distribution, response collection, and scoring process, ensuring a seamless and efficient testing experience. What this workflow does Adds test content, including questions and answers, to a Postgres database Sends a Telegram bot link to test participants Automatically delivers the test via the Telegram bot Collects and stores responses Displays the participant's ranking at the end of the test Setup Create tables in Postgres Replace "n8n" in the provided SQL script with the name of your actual schema Run the script in your database to create the required tables Add credentials Set up and connect your Telegram credentials Set up and connect your Postgres credentials How to customize this workflow to your needs Modify the test content directly in the Postgres database Customize the Telegram bot messages to match your tone and branding. Adjust scoring logic if needed to reflect different evaluation methods.
By AndrewAutomate income and expense tracking in Google Sheets via Telegram
Who’s it for This template is perfect for freelancers, small business owners, or financial assistants who want to record and approve financial transactions like income and expenses directly from Telegram, without opening a spreadsheet manually. It’s also useful for teams that require a supervisor to approve expenses before they’re finalized. What it does This workflow allows users to: Start a conversation via Telegram using the /start command. Choose to record an income or expense. Submit transaction data using a structured format. Store the data into Google Sheets in real time. For expenses, automatically notify a supervisor for approval. The supervisor can Approve ✅, Reject ❌, or View Details 👁. Sends feedback to the user based on supervisor action. 🔧 How it works Telegram Bot Trigger: Captures user input via message or inline button callback. Message Detection Logic: Differentiates between text input and button interactions. Switch Node: Routes the message type: /start: Displays income/expense buttons. Input text: Validates formatting and parses data. Callback: Handles approval/rejection process. Google Sheets Integration: Appends or updates entries in different sheets based on the data type. Notifications: User gets feedback (recorded, pending, approved, rejected). Supervisor receives inline button options for approval. Google Sheets Details You will need a Google Sheet with the following two worksheets: Sheet 1: income Sheet 2: Sheet1 (Default tab for expenses) 📱 Telegram Setup Instructions Create a bot using @BotFather. Save the bot token. Go to n8n Credentials → Telegram API and add: Access Token = your bot token In Telegram, send /start to your bot. Make sure your bot has enabled privacy mode (or disabled, if used in a group). 💡 For the approval flow, update the node Send Approval Request with the correct chatId of the supervisor's Telegram account. You can hardcode a static ID (e.g., "123456789") or pull from a variable if dynamic. 🛠 Requirements | Tool | Description | | -------------------------- | ----------------------------------- | | n8n (Cloud or Self-hosted) | Use latest stable version | | Telegram Bot | For user input and notifications | | Google Sheets | To store income and expense records | | Google OAuth2 Credentials | Required for Google Sheets node | ⚙️ How to customize the workflow Change the chat ID for supervisors in the node Send Approval Request. Modify the text or add new buttons in the inline keyboard node. Update Google Sheet ID and tab names if you’re using different sheets. Customize the approval logic, for example, route to different teams. ✅ Setup Steps Import the workflow JSON into your n8n instance. Configure Telegram API credential with your bot token. Connect your Google Sheets OAuth2 credential. Replace Google Sheet document ID and tab names with your own (via UI or “Expression” mode). Deploy and activate the workflow.
By Fahmi OktafianGenerate empathetic customer replies with Claude AI and auto-escalation
🧠 Overview Generate empathetic, professional reply drafts for customer or user messages. The workflow detects sentiment, tone, and risk level, drafts a concise response, sanitizes PII/links/emojis, and auto-escalates risky or low-confidence cases to human review. --- ⚙️ How It Works Input — Manual Test or Webhook Trigger AI Agent (Empathy) — returns { sentiment, tone, reply, confidence, needs_handover } Post-Process & Sanitize — removes URLs/hashtags, masks PII, caps length Risk & Handover Rules — checks confidence threshold, risk words, and negativity Routing — auto-send safe replies or flag to Needs Review --- 🧩 Setup Instructions (3–5 min) Open Set Config1 and adjust: MAX_LEN (default 600) ADDFOLLOWUPQUESTION (true/false) FORMALITY (auto | casual | polite) EMOJIALLOWED (true/false), BLOCKLINKS (true/false) RISK_WORDS (e.g., refund, lawsuit, self-harm) Connect Anthropic credential to Anthropic Chat Model (Optional) Replace Manual Trigger with Webhook Trigger for real-time use > Tip: If you need to show literal angle brackets in messages, use backticks like <example> (no HTML entities needed). --- 📚 Use Cases 1) SaaS Billing Complaints Input: “I was billed after canceling. This is unacceptable.” Output: Calm, apologetic reply with refund steps; escalates if refund is in RISK_WORDS or confidence < 0.45. 2) Product Bug Reports Input: “Upload fails on large files since yesterday.” Output: Acknowledges impact, requests logs, offers workaround; routes to auto-send if low risk and high confidence. 3) Delivery/Logistics Delays Input: “My order is late again. Should I file a complaint?” Output: Empathetic apology, ETA guidance, partial credit policy note; escalates if language indicates legal action. 4) Community Moderation / Abuse Input: “Support is useless—you’re all scammers.” Output: De-escalating, policy-aligned response; auto-flags due to negative sentiment + risk keyword match. 5) Safety / Self-harm Mentions Input: “I feel like hurting myself if this isn’t fixed.” Output: Immediate escalation, inserts approved resources; never auto-sends. --- 🚨 Auto-Escalation Rules (defaults) Negative sentiment Message matches any RISK_WORDS confidence < 0.45 Mentions of legal, harassment, or self-harm context --- 🧪 Notes & Best Practices 🔐 No hardcoded API keys — use n8n Credentials 🧭 Tune thresholds and RISK_WORDS to your org policy 🧩 Works on self-hosted or cloud n8n ✅ Treat outputs as drafts; ship after human/policy review --- 🔗 Resources GitHub (template JSON): https://github.com/yskmtb0714/n8n-workflows/blob/main/empathy-reply-assistant.json
By Yusuke