AI Agents & Automation Templates
13 workflow templates for ai agents & automation automation
Compare Sequential, Agent-Based, and Parallel Llm Process...
This workflow compares three different approaches to chaining Large Language Model (LLM) operations using Claude 3.7 Sonnet: naive sequential chaining, agent-based processing with memory, and parallel processing for maximum speed. It retrieves content from a website, then processes it using the LLM with these three different methods for comparison.
Agent Personnel - N8n Template
This workflow acts as a personal assistant, interacting with the user via Telegram to understand requests through text and voice messages, then using AI models and sub-agents to perform tasks like sending emails, managing calendars, creating tasks, generating images, and taking notes. It routes messages based on whether they are text or voice and utilizes different AI tools and agents to fulfill various tasks.
Custom Langchain Agent Written in Javascript
This workflow demonstrates the use of custom Language Model (LLM) chains and agents within n8n, leveraging OpenAI for language processing and a custom Wikipedia tool for information retrieval. It processes two distinct queries: one to generate a joke using a custom LLM chain and another to find Einstein's birth year using an AI agent and a Wikipedia tool.
Ai Research Agents to Automate Pdf Analysis with Mistral’...
This workflow automates the process of analyzing PDF documents using Mistral's OCR API and AI agents to generate either in-depth research reports or concise newsletters, tailored to specific user instructions. It takes a PDF document, extracts text, and uses AI models to structure, summarize, and refine the content.
Adaptive Rag Strategy with Query Classification & Retriev...
This n8n workflow implements a version of the Adaptive Retrieval-Augmented Generation (RAG) framework. It recognizes that the best way to retrieve information often depends on the type of question asked. Instead of a one-size-fits-all approach, this workflow adapts its strategy based on the user's query intent.
Ai Agent Content Creator (Text to Speech)
This workflow automates content creation by receiving a chat message, generating content using an AI model, converting the content to speech, and storing both the text and audio in Google services. It also incorporates brand guidelines and content feedback to ensure the generated content aligns with specific branding.
Zapsign Api Agent - N8n Template
This n8n workflow provides an AI-powered support agent for ZapSign API-related queries. It is triggered by any incoming webhook request, processes the request using OpenAI, retrieves relevant ZapSign API documentation, and provides a structured response. Workflow Configuration in n8n 1. Triggering the Workflow Node: Execute Workflow Trigger This node listens for incoming webhook requests and extracts relevant query data. Configuration Steps: Add the Execute Workflow Trigger node. Set it up to receive POST requests. Extract the input query using: n8n Copiar Editar ={{$json.body?.content ?? $json.chatInput}} Ensure the webhook URL is accessible for external systems to send requests. 2. Processing the AI Request Node: AI Agent (@n8n/n8n-nodes-langchain.agent) This node processes the user query and generates an AI-powered response. Configuration Steps: Add an AI Agent node. Set the promptType to "define". Use the extracted query as input: n8n Copiar Editar ={{$json.body?.content ?? $json.chatInput}} Define the system message to enforce AI behavior, ensuring responses are tailored to ZapSign API support. 3. Integrating OpenAI Node: OpenAI Chat Model This node connects to OpenAI’s API to generate responses. Configuration Steps: Add an OpenAI Chat Model node. Configure API credentials under Settings → Credentials in n8n. Connect it to the AI Agent node. 4. Storing Chat History in PostgreSQL Node: Postgres Chat Memory Stores user interactions to maintain context in ongoing conversations. Configuration Steps: Add a PostgreSQL Memory node. Use dynamic values for sessionKey to personalize responses: n8n Copiar Editar ={{$json.body?.event?.user?.email.replace('@','_')?.replaceAll('.','_').replaceAll('-','_') ?? "duvidas_api_agent"}} Connect it to the AI Agent node under ai_memory. 5. Fetching ZapSign API Documentation Nodes: ToolHttpRequest These nodes allow the AI to fetch relevant documentation based on user queries. Configuration Steps: Add multiple HTTP Request nodes. Set the URLs for ZapSign API documentation: Authentication: https://docs.zapsign.com.br/autenticacao/autenticacao Document creation: https://docs.zapsign.com.br/documentos/criar-documento Webhooks: https://docs.zapsign.com.br/webhooks/como-funciona Error handling: https://docs.zapsign.com.br/status-de-erros Set responseType to "html", and enable "onlyContent" to clean up results. Connect these nodes to the AI Agent under ai_tool. Final Deployment and Testing Save and activate the workflow in n8n. Send a test request to the webhook with the following JSON payload: json Copiar Editar { "content": "Como autenticar na API ZapSign?" } The AI should respond with relevant documentation links and structured answers.
Get Exchange & Sentiment Insights with Coinmarketcap Ai a...
This workflow acts as a CoinMarketCap AI Agent that retrieves exchange data, market indexes, and community sentiment using the CoinMarketCap API, powered by an AI language model. It allows users to query for information like exchange metadata, token holdings, CMC 100 Index constituents, and the Fear & Greed Index.
Ai-Powered Technical Analyst with Perplexity R1 Research
[](https://youtu.be/D11S0s3PDNc) Leverage the latest AI technology to analyze financial charts and make informed trading decisions with our Technical Analysis AI Agent. This powerful workflow combines Claude Sonnet 3.7 vision capabilities with Perplexity deep reasoning and up-to-date internet information to deliver comprehensive market analysis.
Ai Color Picker Agent Using Openai + Langchain
This n8n workflow sets up a conversational AI agent that intelligently responds to user messages using OpenAI's GPT-4o-mini and LangChain. It features a custom JavaScript tool that returns a random color while excluding green and blue—ideal for interactive UI testing, chatbot demos, and beginner-friendly LangChain AI agents. 🛠️ Tools used: OpenAI GPT-4o-mini LangChain Agent Node Custom JavaScript function Manual Trigger AI Agent, LangChain, GPT-4o, JavaScript, Automation, Tools, Custom Function
Mongodb Ai Agent - Intelligent Movie Recommendations
This workflow creates an intelligent agent that accepts natural language queries about movies, translates user requests into MongoDB aggregation pipelines, queries a movie database, and provides contextual responses using OpenAI's language model. It also allows users to save favorite movies to the database and maintains conversation context.
Agentic Telegram Ai Bot with with Langchain Nodes and New...
Create a Telegram bot that combines advanced AI functionalities with LangChain nodes and new tools. [Nodes as tools](https://community.n8n.io/t/review-node-as-tools-is-finally-here/57539) and the [HTTP request tool](https://community.n8n.io/t/using-the-http-request-tool-with-ai-agents/50616/3) are a new n8n feature that extend [custom workflow tool](https://docs.n8n.io/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolworkflow/) and simplify your setup. We used the workflow tool in the [previous Telegram template](https://n8n.io/workflows/2035-telegram-ai-bot-with-langchain-nodes/) to call the Dalle-3 model. In the new version, we've achieved similar results using the HTTP Request tool and the Telegram node tool instead. The main difference is that Telegram bot becomes more flexible. The LangChain Agent node can decide which tool to use and when. In the previous version, all steps inside the custom workflow tool were executed sequentially. ⚠️ Note that you'd need to select the Tools Agent to work with new tools. Before launching the template, make sure to set up your OpenAI and Telegram credentials. Here’s how the new Telegram bot works: 1. Telegram Trigger listens for new messages in a specified Telegram chat. This node activates the rest of the workflow after receiving a message. 2. AI Tool Agent receives input text, processes it using the OpenAI model and replies to a user. It addresses users by name and sends image links when an image is requested. 3. The OpenAI GPT-4o model generates context-aware responses. You can configure the model parameters or swap this node entirely. 4. Window buffer memory helps maintain context across conversations. It stores the last 10 interactions and ensures that the agent can access previous messages within a session. Conversations from different users are stored in different buffers. 5. The HTTP request tool connects with OpenAI's DALL-E-3 API to generate images based on user prompts. The tool is called when the user asks for an image. 6. Telegram node tool sends generated images back to the user in a Telegram chat. It retrieves the image from the URL returned by the DALL-E-3 model. This does not happen directly, however. The response from the HTTP request tool is first stored in the Agent’s scratchpad (think of it as a short-term memory). In the next iteration, the Agent sends the updated response to the GPT model once again. The GPT model will then create a new tool request to send the image back to the user. To pass the image URL, the tool uses the [new $fromAI() expression](https://docs.n8n.io/advanced-ai/examples/using-the-fromai-function/). 7. Send final reply node sends the final response message created by the agent back to the user on Telegram. Even though the image was already passed to the user, the Agent always stops with the final response that comes from dedicated output. ⚠️ Note, that the Agent may not adhere to the same sequence of actions in 100% of situations. For example, sometimes it could skip sending the file via the Telegram node tool and instead just send an URL in the final reply. If you have a longer series of predefined steps, it may be better to use the “old” custom workflow tool. This template is perfect as a starting point for building AI agentic workflow. Take a look at another agentic [Telegram AI template that can handle both text and voice messages](https://n8n.io/workflows/2534-telegram-ai-bot-assistant-ready-made-template-for-voice-and-text-messages/).
Ai Agent Find the Right Linkedin Profiles in Seconds
This workflow automates LinkedIn prospecting by accepting natural language search queries, extracting relevant search parameters using AI, and then saving the found LinkedIn profile URLs and titles to a Google Sheet. It utilizes an AI Agent to process user input and Google Custom Search API to find relevant LinkedIn profiles.