Workflow Templates

Supabase AI Agent with RAG & Multi-Tenant CRUD Version: 1.0.0 n8n Version: 1.88.0+ Author: Koresolucoes License: MIT Description A stateful AI agent workflow powered by Supabase and Retrieval-Augmented Generation (RAG). Enables persistent memory, dynamic CRUD operations, and multi-tenant data isolation for AI-driven applications like customer support, task orchestration, and knowledge management. Key Features: 🧠 RAG Integration: Leverages OpenAI embeddings and Supabase vector search for context-aware responses. 🗃️ Full CRUD: Manage agent_messages, agent_tasks, agent_status, and agent_knowledge in real time. 📤 Multi-Tenant Ready: Supports per-user/organization data isolation via dynamic table names and webhooks. 🔒 Secure: Role-based access control via Supabase Row Level Security (RLS). Use Cases Customer Support Chatbots: Persist conversation history and resolve queries using institutional knowledge. Automated Task Management: Track and update task statuses dynamically. Knowledge Repositories: Store and retrieve domain-specific information for AI agents. Instructions 1. Import Template Go to n8n > Templates > Import from File and upload this workflow. 2. Configure Credentials Add your Supabase and OpenAI API keys under Settings > Credentials. 3. Set Up Multi-Tenancy (Optional) Dynamic Webhook Path**: Replace the default webhook path with /mcp/tool/supabase/:userId to enable per-user routing. Table Names**: Use a Set Node to dynamically generate table names (e.g., agent_messages_{{userId}}). 4. Activate & Test Enable the workflow and send test requests to the webhook URL. Tags AI Agent RAG Supabase CRUD Multi-Tenant OpenAI Automation Screenshots License This template is licensed under the MIT License.

Create a Branded AI Website Chatbot Engage website visitors with an intelligent chat widget powered by OpenAI. This template includes: 💬 Natural conversation handling 📅 Microsoft Outlook calendar integration 📝 Lead capture and information gathering 🔄 Human handoff capabilities Simply add a JavaScript snippet to your website and configure the workflow to match your needs. Follow our detailed setup guide to get started in minutes. > Note: Widget includes a "Powered By" affiliate link

Who is This For? This is for normal people or people just starting off and wanting to have a AI chatbot that can process data to use when talking to the user. How to Use You will need to have your own OpenRouter (Free) and OpenAI APIs as well as Google Drive, Pinecone, and Airtable. What Do You Want? If you want to have your AI Agent remember the user's preferences even after the session is over then you can keep the Airtable node in, if not you can delete it.

Edit 19/11/2024: As explained on the workflow, the AI Agent with the original system prompt was not effective when using gpt4-o-mini. To address this, I optimized the prompt to work better with this model. You can find the prompts I’ve tested on this Notion Page. And yes, there is one that works well with gpt4-o-mini. AI Agent to chat with you Search Console Data, using OpenAI and Postgres This AI Agent enables you to interact with your Search Console data through a chat interface. Each node is documented within the template, providing sufficient information for setup and usage. You will also need to configure Search Console OAuth credentials. Follow this n8n documentation to set up the OAuth credentials. Important Notes Correctly Configure Scopes for Search Console API Calls It’s essential to configure the scopes correctly in your Google Search Console API OAuth2 credentials. Incorrect configuration can cause issues with the refresh token, requiring frequent reconnections. Below is the configuration I use to avoid constant re-authentication: Of course, you'll need to add your client_id and client_secret from the Google Cloud Platform app you created to access your Search Console data. Configure Authentication for the Webhook Since the webhook will be publicly accessible, don’t forget to set up authentication. I’ve used Basic Auth, but feel free to choose the method that best meets your security requirements. 🤩💖 Example of awesome things you can do with this AI Agent

A sentiment intelligence sub-agent for the Binance Spot Market Quant AI Agent. It aggregates crypto news from major sources, filters by token keyword (e.g., BTC, ETH), and produces a Telegram-ready summary including market sentiment and top headlines—powered by GPT-4o. 🎥 Live Demo: 🛠️ Workflow Function This tool performs the following steps: | 🔧 Step | 📌 Description | | ------------------------ | ----------------------------------------------------------------------------- | | Webhook Input | Accepts { "message": "symbol" } via HTTP POST | | Crypto Keyword Extractor | GPT model extracts the valid crypto symbol (e.g., "SOL", "DOGE", "ETH") | | RSS News Aggregators | Pulls latest headlines from 9+ crypto sources (CoinDesk, Cointelegraph, etc.) | | Merge & Filter Articles | Keeps only articles containing the specified token | | Prompt Builder | Creates prompt for GPT with filtered headlines | | GPT-4o Summarizer | Summarizes news into 3-part response: Summary, Sentiment, Headline Links | | Telegram Formatter | Converts GPT output into a Telegram-friendly message | | Response Handler | Returns formatted message to the caller via webhook | 📥 Webhook Trigger Format { "message": "ETH" } This triggers a full execution of the workflow and returns output like: 📣 ETH Sentiment: Neutral • BlackRock’s tokenized fund expands to Ethereum mainnet (CoinDesk) • Ethereum fees remain high, analysts call for L2 migration (NewsBTC) • Vitalik warns about centralized risks in staking (Cointelegraph) 📚 Installation Guide 1. Import & Enable Load the .json into your n8n Editor Enable webhook trigger in the top-right corner Ensure it's reachable via POST /webhook/custom-path 2. Required Credentials OpenAI API Key** (GPT-4o capable) No API keys required for RSS feeds 3. Connect to Quant Agent Add an HTTP Request node in your main AI agent Point to this workflow's webhook with body { "message": "symbol" } Capture the response to include in your Telegram output 🔍 Real Use Cases | Scenario | Result | | ---------------------------------- | ---------------------------------------------------------------- | | BTC Sentiment before a key event | Returns 8–12 filtered articles with bullish/neutral/bearish tone | | Daily pulse for altcoins like DOGE | Shows relevant headlines, helpful for intraday trading setups | | Telegram chatbot integration | Enables user to query sentiment via /sentiment ETH | | Macro context for Quant AI outputs | Adds emotional/news context to technical-based trade decisions | 🧾 Licensing & Attribution © 2025 Treasurium Capital Limited Company Architecture, prompts, and trade report structure are IP-protected. No unauthorized rebranding or resale permitted. 🔗 For support: LinkedIn – Don Jayamaha

This workflow stores responses form responses of Typeform in Airtable. The workflow also sends the response to a channel on Slack. You will have to configure the Set node if your form uses different fields.

This workflow performs basic XOR-based encryption and decryption using a custom password. It is intended to be triggered by another workflow and processes structured input in JSON format. Input Structure The workflow expects a single array of objects with the following fields: action-type: either "encrypt" or "decrypt" key: the password used for encryption and decryption data: the content to encrypt or decrypt Example: Encryption Input [ { "action-type": "encrypt", "key": "Password", "data": "Hello, this is a secret message" } ] Example: Decryption Input [ { "action-type": "decrypt", "key": "Password", "data": "ChwGAQceF15eE2QXFRcUagxGVgV8TBoNBA4VQVoQZkwVUhImU1FTEg==" } ] Output The output returns an array of results, each containing either the encrypted string (base64 format) or the decrypted plain text. Use Case This workflow is useful for simple internal message encoding, data obfuscation, or testing purposes. It is not recommended for securing sensitive or personal data, as XOR encryption is not cryptographically secure. The workflow logic is written in JavaScript using n8n Function nodes, without any external dependencies.

This workflow allows you to add candidates’ profile assessments to Notion before an interview. Prerequisites Add an input field on your Calendly Invite page where the candidate can enter their LinkedIn URL. Create credentials for your Calendly account. Follow the steps mentioned in the documentation to learn how to do that. Create credentials for Humantic AI following the steps mentioned here. Create a page on Notion similar to this page. Create credentials for the Notion node by following the steps in the documentation. Calendly Trigger node: This node will trigger the workflow when an interview gets scheduled. Make sure to add a field to collect the candidates' LinkedIn URL on your invite page. Humantic AI: This node uses the LinkedIn URL received by the previous node to create a candidate profile in Humantic AI. Humantic AI1: This node will analyze the candidates' profile. Notion node: This node will create a new page in Notion using the information from the previous node.

Unlock adaptive, context-aware AI chat in your automations—no coding required! This template is a plug-and-play n8n workflow that transforms how your chatbots, support agents, and knowledge systems respond to users. Powered by Google Gemini and a Qdrant vector database, it automatically classifies every incoming query and applies a tailor-made strategy for Factual, Analytical, Opinion, or Contextual requests—delivering the right answer, every time. 🛠️ Key Features Automatic Query Classification: Seamlessly detects whether the user wants facts, a deep analysis, opinions, or context—then routes each input to the best answering strategy. Four Dynamic Retrieval Modes: 1) Factual: Delivers precise, accurate information 2) Analytical: Breaks down complex topics for deep dives 3) Opinion: Surfaces diverse viewpoints and perspectives 4) Contextual: Connects the dots using implied or user-specific context End-to-End RAG Pipeline: Uses Gemini to classify and answer, while Qdrant powers fast, smart knowledge retrieval. No-Code Visual Editing: Import into n8n, connect your LLM and vector database credentials, and you’re live—customize, extend, and scale with zero backend code. Reusable in Any Project: Perfect for customer support, research, onboarding bots, internal knowledgebases, or any adaptive AI chat interface. 🚀 How it Works 1) User submits a query (via chat or API) 2) Query is auto-classified as Factual, Analytical, Opinion, or Contextual 3) Adaptive retrieval strategy is triggered (each with its own prompt logic and memory buffer) 4) Smart knowledge search is performed using Gemini and Qdrant 5) Response is generated and sent back to the user—tailored to the query type! 🧩 What’s Included Full n8n workflow (.json) Step-by-step setup instructions Sample prompts and system messages for each strategy Lifetime updates (as the workflow evolves) 💡 Use Cases Chatbots that adapt to every user’s intent Internal/external FAQ and helpdesk automations AI research and summarization agents Product support and onboarding flows Any scenario where smarter, more relevant answers = better user experience Ready to build smarter automations? Import this template, connect your Gemini & Qdrant accounts, and let your AI agent adapt to every conversation.

Boost your productivity with this AI-powered email and calendar assistant: This AI-powered template has 2 workflows. It manages your Gmail inbox and Google Calendar, classifies emails with custom labels, and suggests replies and meeting times — all fully automated with OpenAI and n8n. Automatically analyze your Gmail inbox Suggest replies, priorities, and meeting times Checks your Google Calendar for conflicts and free slots Maintain conversation context using Thread History Vector Store The agent proactively acts using a Tools Agent architecture, with integrated memory and real-time tool invocation. It's perfect for busy professionals who want a personal assistant for communication and scheduling. Included features: ✅ Do actions on incoming mails 8like Labeling etc) ✅ Summarize and Assist fot the latest emails ✅ Draft replies and schedule meetings contextually ✅ Handle time zone conversion and MessageID referencing ✅ Context retention of last conversation history - using VectorStore 📦 Requirements: Gmail + Google Calendar credentials via n8n credentials OpenAI API key n8n VectorStore nodes (or external integration like Pinecone, Qdrant, or Chroma)

This workflow provides a simple approach to counting the items returned by a node. It uses a Set node with the Execute Once option: The expression uses $input.all() (documented here) to fetch all incoming items at once, and .length (documented for example here) to count them.

What It Does This powerful workflow can take hours of difficult research attempting to identify the perfect online tool to aid you with your business and condenses it into a few short seconds. Simply typing the name of an online tool you would like to identify into a chat message will initiate the workflow to begin its search process to identify 5 companies that will provide you with the online tool you desire. The initial chat will prompt the Tool Finder AI agent utilizing the power of GPT-4o in combination with SerpAPI to conduct a search and find 5 top end companies that contain the online tool you desire. It will then send the name of each company to five separate Reviewer Tool Agents that will gather information on each company. Each Reviewer Tools Agent will again harness the power of GPT-4o and SerpAPI to give a detailed descriptions of the online tool available including its price, limitations, summary of reviews, pros and cons, as well as an overall conclusion of the online tool. Who This Is For This is the perfect workflow for anyone who is interested in obtaining an online tool to help automate business or everyday tasks. Rather than spending an excess amount of time searching through websites and review pages to determine the best product available this workflow completes the process for you. It provides five options in a condensed form that easily lets you compare and evaluate the options in a single place. Whether you are searching for an automatic email responder or the best available online spreadsheet, this workflow is exactly what you need to help bring your business to the next level. How It Works Begin by opening the chat trigger node and typing the name of an online tool you would like to use to improve your day to day tasks. Example: Automatic email responder, automatic instagram poster, or online spreadsheet. This will trigger the Tool Finder Tools Agent to begin to utilize GPT-4o to begin to create search queries based off the tool you wish to identify. It will then use these search queries with SerpAPI to identify 5 companies that provide the online tool you desire. After it has obtained the names of five companies it will then in a structured output, send each item to a separate Reviewer Tools Agent. Once the Reviewer Tools Agent has received the name of the item it will then begin an in-depth review of that item. Each Reviewer Tools Agent will again use the power of GPT-4o connected with SerpAPI to obtain the most up to date information on each item from the internet. For each company and its tool you will be provided with: Price: If it is a one time purchase, monthly subscription and if there is a free version. Limits: It will provide any limitations on completing the desired tasks. If there is a limit on number of tasks that can be completed. If it only works with certain software. Summary of reviews: It will provide an overall summary of the reviews, how many reviews, as well as the star rating of each item. It will go in depth on the summary of the reviews. It will provide 3-4 pros and 2-3 cons of each item. Conclusion: It will provide an overall summary of the tool. After each of the Reviewer Tools Agent is complete with its review of the company and the online tool they provide, they will all send the information along to a Compiler Tools Agent. This tools agent uses GPT-4o-mini to arrange the data and present it in a concise, organized fashion. This allows for easy readability. Set Up Steps You will need to obtain an Open AI API key from platform.openai.com/api-keys After you obtain this Open AI API key you will need to connect it to the Open AI Chat Model for all of the Tools agents (Item finder, Reviewer 1, Reviewer 2, Reviewer 3, Reviewer 4, Reviewer 5, and Compiler). You will now need to fund your Open AI account. GPT 4o costs ~$0.03-$0.04 to run the workflow. Next you will need to create a SerpAPI account at https://serpapi.com/users/sign_up After you create an account you will need to obtain a SerpAPI key. You will then need to use this key to connect to the SerpAPI tool for each of the tools agents (Tool finder, Reviewer 1, Reviewer 2, Reviewer 3, Reviewer 4, and Reviewer 5) Tip: SerpAPI will allow you to run 100 free searches each month. This workflow uses ~15-30 SerpAPI searches per run. If you would like to utilize the workflow more than that each month, create multiple SerpAPI accounts and have an API key for each account. When you utilize all 100 free searches for an account, switch to the API key for another account within the workflow.