Workflow Templates

This workflow template, "Chinese Translator via Line x OpenRouter (Text & Image)" is designed to provide seamless Chinese translation services directly within the LINE messaging platform. By integrating with OpenRouter.ai and advanced language models like Qwen, this workflow translates text or images containing Chinese characters into pinyin and English translations, making it an invaluable tool for language learners, travelers, and businesses operating in multilingual environments. This template is ideal for: Language Learners: Who want to practice Chinese by receiving instant translations of text or images. Travelers: Looking for quick translations of Chinese signs, menus, or documents while abroad. Educators: Teaching Chinese language courses and needing tools to assist students with translations. Businesses: Operating in multilingual markets and requiring efficient communication tools. Automation Enthusiasts: Seeking to build intelligent chatbots that can handle language translation tasks. What Problem Does This Workflow Solve? Translating Chinese text or images into English and pinyin can be challenging, especially for beginners or those without access to reliable translation tools. This workflow solves that problem by: Automatically detecting and translating text or images containing Chinese characters. Providing accurate translations in both pinyin and English for better comprehension. Supporting multiple input formats (text, images) to cater to diverse user needs. Sending replies directly to users via the LINE messaging platform , ensuring accessibility and ease of use. What This Workflow Does 1) Receive Messages via LINE Webhook The workflow is triggered when a user sends a message (text, image, or other types) to the LINE bot. 2) Display Loading Animation A loading animation is displayed to reassure the user that their request is being processed. 3) Route Input Types The workflow uses a Switch node to determine the type of input (text, image, or unsupported formats). If the input is text , it is sent to the OpenRouter.ai API for translation. If the input is an image , the workflow extracts the image content, converts it to base64, and sends it to the API for translation. Unsupported formats trigger a polite response indicating the limitation. 4) Translate Content Using OpenRouter.ai The workflow leverages Qwen models from OpenRouter.ai to generate translations: For text inputs, it provides Chinese characters , pinyin , and English translations . For images, it extracts and translates using the qwen-VL model which can take images 5) Reply with Translations The translated content is formatted and sent back to the user via the LINE Reply API. Setup Guide Pre-Requisites Access to the LINE Developers Console to configure your webhook and channel access token. An OpenRouter.ai account with credentials to access Qwen models. Basic knowledge of APIs, webhooks, and JSON formatting. Step-by-Step Setup 1) Configure the LINE Webhook: Go to the LINE Developers Console and set up a webhook to receive incoming messages. Copy the Webhook URL from the Line Webhook node and paste it into the LINE Console. Remove any "test" configurations when moving to production. 2) Set Up OpenRouter.ai: Create an account on OpenRouter.ai and obtain your API credentials. Connect your credentials to the OpenRouter nodes in the workflow. 3) Test the Workflow: Simulate sending text or images to the LINE bot to verify that translations are processed and replied correctly. How to Customize This Workflow to Your Needs Add More Languages: Extend the workflow to support additional languages by modifying the API calls. Enhance Image Processing: Integrate more advanced OCR tools to improve text extraction from complex images. Customize Responses: Modify the reply format to include additional details, such as grammar explanations or cultural context. Expand Use Cases: Adapt the workflow for specific industries, such as tourism or e-commerce, by tailoring the translations to relevant vocabulary. Why Use This Template? Real-Time Translation: Provides instant translations of text and images, improving user experience and accessibility. Multimodal Support: Handles both text and image inputs, catering to diverse user needs. Scalable: Easily integrate into existing systems or scale to support multiple users and workflows. Customizable: Tailor the workflow to suit your specific audience or industry requirements.

Auto Source LinkedIn Candidates with GPT-4 Boolean Search & Google X-ray How It Works: User Input: The user pastes a job description or ideal candidate specifications into the workflow. Boolean Search String Generation: OpenAI processes the input and generates a precise LinkedIn Boolean search string formatted as: site:linkedin.com/in ("Job Title" AND "Skill1" AND "Skill2") This search string is optimized to find relevant LinkedIn profiles matching the provided criteria. Google Sheet Creation: A new Google Sheet is automatically created within a specified document to store extracted LinkedIn profile URLs. Google Search Execution: The workflow sends a search request to Google using an HTTP node with the generated Boolean string. Iterative Search & Data Extraction: The workflow retrieves the first 10 results from Google. If the desired number of LinkedIn profiles has not been reached, the workflow loops, fetching the next set of 10 results until the if condition is met. Data Storage: The workflow extracts LinkedIn profile URLs from the search results and saves them to the newly created Google Sheet for further review. Setup Steps: 1. API Key Configuration Under "Credentials", add your OpenAI API key from your OpenAI account settings. This key is used to generate the LinkedIn Boolean search string. 2. Adjust Search Parameters Navigate to the "If" node and update the condition to define the desired number of LinkedIn profiles to extract. The default is 50, but you can set it to any number based on your needs. 3. Establish Google Sheets Connection Connect your Google Sheets account** to the workflow. Create a document** to store the sourced LinkedIn profiles. The workflow automatically creates a new sheet for each new search, so no manual setup is needed. 4. Authenticate Google Search Google search requires authentication** for better results. Use the Cookie-Editor browser extension to export your header string and enable authenticated Google searches within the workflow. 5. Run the Workflow Execute* the workflow and monitor the *Google Sheet** for newly added LinkedIn profiles. Benefits: ✅ Automates profile sourcing, reducing manual search time. ✅ Generates precise LinkedIn Boolean search strings tailored to job descriptions. ✅ Extracts and saves LinkedIn profiles efficiently for recruitment efforts. This solution leverages OpenAI and advanced search techniques to enhance your talent sourcing process, making it faster and more accurate! 🚀

Introduction This workflow is designed to create and attach notes or comments to any record in your Odoo instance. It acts as a sub-workflow that can be triggered by a main workflow to log messages or comments in a centralized manner. By leveraging the powerful Odoo API, this template ensures that updates to records are handled efficiently, providing an organized way to document important information related to your business processes. Setup Instructions Import the Workflow: Import the provided JSON file into your n8n instance. Odoo Credentials: Ensure you have valid Odoo API credentials (e.g., "Roodsys Odoo Automation Account") configured in n8n. Node Configuration: Verify that the "Odoo" node (consider renaming it to "Odoo Record Manager" for clarity) is set up with your server details and authentication parameters. Check that the workflow trigger ("When Executed by Another Workflow") is configured to receive input parameters from the parent workflow. Execution Trigger: This workflow is designed to be initiated by another workflow. Make sure the main workflow supplies the required inputs. Workflow Details Trigger Node: The workflow begins with the "When Executed by Another Workflow" node, which accepts three inputs: rec_id: A numeric identifier for the Odoo record. message: The text of the comment or note. model: The specific Odoo model (e.g., rs.deployment.action.log) where the note should be attached. Odoo Node: The second node in the workflow calls the Odoo API to create a new log message. It maps the inputs as follows: message_type is set to "comment". model is assigned the provided model name. res_id is assigned the record ID (rec_id). body is assigned the message content. Additional Information: A sticky note node is included to provide a brief overview of the workflow’s purpose directly within the interface. Input Parameters Record ID (rec_id): The unique identifier of the record in Odoo where the note will be added. Message (message): The content of the comment or note that is to be logged. Model (model): The Odoo model name indicating the context in which the note should be created (e.g., rs.deployment.action.log). Usage Examples Internal Logging: Use the workflow to attach internal comments or logs to specific records, such as customer profiles, orders, or deployment logs. Audit Trails: Create a comprehensive audit trail by documenting changes or important events in Odoo records. Integration with Other Workflows: Link this workflow with other automation processes in n8n (like email notifications, data synchronization, or reporting) to create a seamless integration across your systems. Pre-conditions The Odoo instance must be accessible and correctly configured. API permissions and user roles should be validated to ensure that the workflow has the necessary access rights. The workflow expects inputs from an external trigger or parent workflow. Customization & Integration This template offers several customization options to tailor it to your needs: Field Customization: Modify or add new fields to match your logging or commenting requirements. Node Renaming: Rename nodes for better clarity and consistency within your workflow ecosystem. Integration Possibilities: Easily integrate this workflow with other processes in n8n, such as triggering notifications or synchronizing data across different systems. This sub-workflow receives data from a main workflow (for example, a record ID, a message, and the Odoo model) and creates a new note (or comment) in the corresponding Odoo record. Essentially, it acts as a centralized point for logging comments or notes in a specific Odoo model, ensuring that the information remains organized and easy to track. Your model must inherit from _inherit = ['portal.mixin', 'mail.thread.main.attachment']

Who is this for? This workflow is ideal for: HR teams and recruiters seeking to streamline resume screening. Hiring managers who want quick, summarized candidate insights. Recruitment agencies handling large volumes of applicant data. Startups and small businesses looking to automate hiring without complex systems. AI and automation professionals who want to build smart HR workflows using n8n and OpenAI. What problem is this workflow solving? / Use Case Manually reviewing resumes is time-consuming, inconsistent, and prone to human bias. This workflow automates the resume intake and evaluation process—ensuring that each applicant is screened, summarized, and scored using a consistent, data-driven method. It enhances efficiency and supports better hiring decisions. What this workflow does Accepts resume submissions via form and saves files to Google Drive. Extracts key information from resumes using AI (e.g., name, contact, education, experience). Summarizes candidate qualifications into a short, readable profile. Allows HR to rate applicants and leave comments. Logs all extracted data and evaluations into a centralized Google Sheet for tracking. Setup Resume is submitted through an n8n form. The uploaded file is automatically stored in Google Drive. n8n uses OpenAI and document parsing tools to extract candidate data. Extracted information is structured and summarized using GPT. A review form is triggered for internal HR rating and notes. All data is appended to a Google Sheet for records and filtering. How to customize this workflow to your needs** Change the form tool (e.g., Typeform, Tally, or custom HTML) based on your stack. Adapt the summary prompt to align with your specific role requirements. Add filters to auto-flag top-tier candidates based on score or skills. Integrate Slack or email to notify hiring managers when top resumes are processed. Connect to your ATS if you want to push processed resumes into your recruitment system.

This n8n workflow template automates the process of finding LinkedIn profiles for a person based on their name, and company. It scrapes Google search results via Bright Data, parses the results with GPT-4o-mini, and delivers a personalized follow-up email with insights and suggested outreach steps. 🚀 What It Does Accepts a user-submitted form with a person’s full name, and company. Performs a Google search using Bright Data to find LinkedIn profiles and company data. Uses GPT-4o-mini to parse HTML results and identify matching profiles. Filters and selects the most relevant LinkedIn entry. Analyzes the data to generate a buyer persona and follow-up strategy. Sends a styled email with insights and outreach steps. 🛠️ Step-by-Step Setup Deploy the form trigger to accept person data (name, position, company). Build a Google search query from user input. Scrape search results using Bright Data. Extract HTML content using the HTML node. Use GPT-4o-mini to parse LinkedIn entries and company insights. Filter for matches based on user input. Merge relevant data and generate personalized outreach content. Send email to a predefined address. Show a final confirmation message to the user. 🧠 How It Works: Workflow Overview Trigger:** When User Completes Form Search:** Edit Url LinkedIn, Get LinkedIn Entry on Google, Extract Body and Title, Parse Google Results Matching:** Extract Parsed Results, Filter, Limit, IF LinkedIn Profile is Found? Fallback:** Form Not Found if no match Company Lookup:** Edit Company Search, Get Company on Google, Parse Results, Split Out Content Generation:** Merge, Create a Followup for Company and Person Email Delivery:** Send Email, Form Email Sent 📨 Final Output An HTML-styled email (using Tailwind CSS) with: Matched LinkedIn profile Company insights Persona-based outreach strategy 🔐 Credentials Used BrightData account** for scraping Google search results OpenAI account** for GPT-4o-mini-powered parsing and content generation SMTP account** for sending follow-up emails ❓Questions? Template and node created by Miquel Colomer and n8nhackers. Need help customizing or deploying? Contact us for consulting and support.

Automatically backs up your workflows to Github and generates documentation in a Notion database. Weekly run, uses the "internal-infra" tag to look for new or recently modified workflows Uses a Notion database page to hold the workflow summary, last updated date, and a link to the workflow Uses OpenAI's 4o-mini to generate a summarization of what the workflow does Stores a backup of the workflow in GitHub (recommend a private repo) Sends notification to Slack channel for new or updated workflows Who is this for Anyone seeking backup of their most important workflows Anyone seeking version control for their most important workflows Credentials required N8N: You will need an N8N credential created so the workflow can query the N8N instance to find all active workflows with the "internal-infra" tag Notion: You will need an Notion credential created OpenAI: You will need an OpenAI credential, unless you intend on rewiring this with your AI of choice (ollama, openrouter, etc.) GitHub: You will need an GitHub credential Slack: You will require an Slack credential, recommend a Bot / access token configuration Setup Notion Create a database with the following columns. Column type is specified in [type]. Workflow Name [text] isActive (dev) [checkbox] Error workflow setup [checkbox] AI Summary [text] Record last update [date/time] URL (dev) [text/url] Workflow created at [date/time] Workflow updated at [date/time] Slack Create a channel for updates to be posted into Github Create a private repo for your workflows to be exported into N8N Download & install the template Configure the blocks to use your N8N, Notion, OpenAI & Slack credentials for your own Edit the "Set Fields" block and change the URL to that of your N8N instance (cloud or self-hosted) Edit the "Add to Notion" action and specify the Database page you wish to update Edit the Slack actions to specify the Channel you want slack notifications posted to Edit the GitHub actions to specify the Repository Owner & Repository Name Sample output in Notion Workflow diagram

This n8n template demonstrates an approach to perform bot-to-human handoff using Human-in-the-loop functionality as a switch. In this experiment, we play with the idea of states we want our agent to be in which controls it's interacton with the user. First state** - the agent is onboarding the user by collecting their details for a sales inquiry. After which, they are handed-off / transferred to a human to continue the call. Second state** - the agent is essentially "deactivated" as further messages to the bot will not reach it. Instead, a canned response is given to the user. The human agent must "reactivate" the bot by completing the human-in-the-loop form and give a summary of their conversation with the user. Third state** - the agent is "reactivated" with context of the human-to-user conversation and is set to provide after sales assistance. An tool is made available to the agent to again delegate back to the human agent when requested. How it works This template uses telegram to handle the interaction between the user and the agent. Each user message is checked for a session state to ensure it is guided to the right stage of the conversation. For this, we can use Redis as a simple key-value store. When no state is set, the user is directed through an onboarding step to attain their details. Once complete, the agent will "transfer" the user to a human agent - technically, all this involves is an update to the session state and a message to another chat forwarding the user's details. During this "human" state, the agent cannot reply to the user and must wait until the human "transfers" the conversation back. The human can do this by replying to "human-in-the-loop" message with a summary of their conversation with the user. This session state now changes to "bot" and the context is implanted in the agent's memory so that the agent can respond to future questions. At this stage of the conversation, the agent is now expected to handle and help the user with after-sales questions. The user can at anytime request transfer back to the human agent, repeating the previous steps as necessary. How to use Plan your user journey! Here is a very basic example of a sales inquiry with at most 3 states. More thought should be developed when many more states are involved. You may want to better log and manage session states so no user is left in limbo. Try connecting the user and sessions to your CRM. Note, the Onboarding agent and After-Sales agent have separate chat memories. When adding more agents, it is recommend to continue having separate chat memories to help focus between states. Requirements Telegram for chatbot & interface Redis for session store and chat memory OpenAI for AI agent Customising this workflow Not using Telegram? This template works with Whatsapp and other services with equivalent functionality.

This n8n template uses existing emails from customers as context to customise and "finetune" outreach emails to them using AI. By now, it should be common knowledge that we can leverage AI to generate unique emails but in a way, they can remain generic as the AI lacks the customer context to be truly personalised. One way to solve this is by pulling in a source of customer data - and what better way then by using existing email correspondence. How it works Customers to target are pulled from Hubspot and each customer is then run in a loop. We're using a loop as the retrieved emails for each customer become separate items and a loop helps with item reference. We connect to our Gmail account to pull all emails recieved from the customer. The contents of the email will be suitable to build a short persona of the customer. We use the Information Extractor to get our AI model to pull out the key attributes of this persona such as decision making style and communication preferences. With this persona, we can now pass this to our AI model to generate a personalised outreach email specifically for our customer. Finally, a draft email is created for human review before sending. If you would rather send the email straight away, this is also possible. How to use Define the topic of the outreach email in the "variables" node. This directs the AI on what outreach email to generate. Ensure the emails are pulled from the right account. If emails may contain sensitive data, adjust the filters and text parsing to ensure these are not leaked to the AI (which might then leak into the generated email). Requirements Hubspot for Contacts List OpenAI for LLM Gmail for Existing Emails and Sending Emails Customising this workflow Not using Hubspot? Any CRM would work just as well or even a simple text csv! If you have customer past deals or engagements in your CRM, consider using this as additional context for the AI to use.

This workflow template provides a robust solution for efficiently sending multiple prompts to Anthropic's Claude models in a single batch request and retrieving the results. It leverages the Anthropic Batch API endpoint (/v1/messages/batches) for optimized processing and outputs each result as a separate item. Core Functionality & Example Usage Included This template includes: The Core Batch Processing Workflow: Designed to be called by another n8n workflow. An Example Usage Workflow: A separate branch demonstrating how to prepare data and trigger the core workflow, including examples using simple strings and n8n's Langchain Chat Memory nodes. Who is this for? This template is designed for: Developers, data scientists, and researchers** who need to process large volumes of text prompts using Claude models via n8n. Content creators** looking to generate multiple pieces of content (e.g., summaries, Q&As, creative text) based on different inputs simultaneously. n8n users** who want to automate interactions with the Anthropic API beyond single requests, improve efficiency, and integrate batch processing into larger automation sequences. Anyone needing to perform bulk text generation or analysis tasks with Claude programmatically. What problem does this workflow solve? Sending prompts to language models one by one can be slow and inefficient, especially when dealing with hundreds or thousands of requests. This workflow addresses that by: Batching:** Grouping multiple prompts into a single API call to Anthropic's dedicated batch endpoint (/v1/messages/batches). Efficiency:** Significantly reducing the time required compared to sequential processing. Scalability:** Handling large numbers of prompts (up to API limits) systematically. Automation:** Providing a ready-to-use, callable n8n structure for batch interactions with Claude. Structured Output:** Parsing the results and outputting each individual prompt's result as a separate n8n item. Use Cases: Bulk content generation (e.g., product descriptions, summaries). Large-scale question answering based on different contexts. Sentiment analysis or data extraction across multiple text snippets. Running the same prompt against many different inputs for research or testing. What the Core Workflow does (Triggered by the 'When Executed by Another Workflow' node) Receive Input: The workflow starts when called by another workflow (e.g., using the 'Execute Workflow' node). It expects input data containing: anthropic-version (string, e.g., "2023-06-01") requests (JSON array, where each object represents a single prompt request conforming to the Anthropic Batch API schema). Submit Batch Job: Sends the formatted requests data via POST to the Anthropic API /v1/messages/batches endpoint to create a new batch job. Requires Anthropic credentials. Wait & Poll: Enters a loop: Checks if the processing_status of the batch job is ended. If not ended, it waits for a set interval (10 seconds by default in the 'Batch Status Poll Interval' node). It then checks the batch job status again via GET to /v1/messages/batches/{batch_id}. Requires Anthropic credentials. This loop continues until the status is ended. Retrieve Results: Once the batch job is complete, it fetches the results file by making a GET request to the results_url provided in the batch status response. Requires Anthropic credentials. Parse Results: The results are typically returned in JSON Lines (.jsonl) format. The 'Parse response' Code node splits the response text by newlines and parses each line into a separate JSON object, storing them in an array field (e.g., parsed). Split Output: The 'Split Out Parsed Results' node takes the array of parsed results and outputs each result object as an individual item from the workflow. Prerequisites An active n8n instance (Cloud or self-hosted). An Anthropic API account with access granted to Claude models and the Batch API. Your Anthropic API Key. Basic understanding of n8n concepts (nodes, workflows, credentials, expressions, 'Execute Workflow' node). Familiarity with JSON data structures for providing input prompts and understanding the output. Understanding of the Anthropic Batch API request/response structure. (For Example Usage Branch) Familiarity with n8n's Langchain nodes (@n8n/n8n-nodes-langchain) if you plan to adapt that part. Setup Import Template: Add this template to your n8n instance. Configure Credentials: Navigate to the 'Credentials' section in your n8n instance. Click 'Add Credential'. Search for 'Anthropic' and select the Anthropic API credential type. Enter your Anthropic API Key and save the credential (e.g., name it "Anthropic account"). Assign Credentials: Open the workflow and locate the three HTTP Request nodes in the core workflow: Submit batch Check batch status Get results In each of these nodes, select the Anthropic credential you just configured from the 'Credential for Anthropic API' dropdown. Review Input Format: Understand the required input structure for the When Executed by Another Workflow trigger node. The primary inputs are anthropic-version (string) and requests (array). Refer to the Sticky Notes in the template and the Anthropic Batch API documentation for the exact schema required within the requests array. Activate Workflow: Save and activate the core workflow so it can be called by other workflows. ➡️ Quick Start & Input/Output Examples: Look for the Sticky Notes within the workflow canvas! They provide crucial information, including examples of the required input JSON structure and the expected output format. How to customize this workflow Input Source:* The core workflow is designed to be called. You will build *another workflow that prepares the anthropic-version and requests array and then uses the 'Execute Workflow' node to trigger this template. The included example branch shows how to prepare this data. Model Selection & Parameters:* Model (claude-3-opus-20240229, etc.), max_tokens, temperature, and other parameters are defined *within each object inside the requests array you pass to the workflow trigger. You configure these in the workflow calling this template. Polling Interval:** Modify the 'Wait' node ('Batch Status Poll Interval') duration if you need faster or slower status checks (default is 10 seconds). Be mindful of potential rate limits. Parsing Logic:** If Anthropic changes the result format or you have specific needs, modify the Javascript code within the 'Parse response' Code node. Error Handling:** Enhance the workflow with more specific error handling for API failures (e.g., using 'Error Trigger' or checking HTTP status codes) or batch processing issues (batch.status === 'failed'). Output Processing:* In the workflow that *calls this template, add nodes after the 'Execute Workflow' node to process the individual result items returned (e.g., save to a database, spreadsheet, send notifications). Example Usage Branch (Manual Trigger) This template also contains a separate branch starting with the Run example Manual Trigger node. Purpose:** This branch demonstrates how to construct the necessary anthropic-version and requests array payload. Methods Shown:** It includes steps for: Creating a request object from a simple query string. Creating a request object using data from n8n's Langchain Chat Memory nodes (@n8n/n8n-nodes-langchain). Execution:** It merges these examples, constructs the final payload, and then uses the Execute Workflow node to call the main batch processing logic described above. It finishes by filtering the results for demonstration. Note:** This branch is for demonstration and testing. You would typically build your own data preparation logic in a separate workflow. The use of Langchain nodes is optional for the core batch functionality. Notes API Limits:** According to the Anthropic API documentation, batches can contain up to 100,000 requests and be up to 256 MB in total size. Ensure your n8n instance has sufficient resources for large batches. API Costs:** Using the Anthropic API, including the Batch API, incurs costs based on token usage. Monitor your usage via the Anthropic dashboard. Completion Time:** Batch processing time depends on the number and complexity of prompts and current API load. The polling mechanism accounts for this variability. Versioning:** Always include the anthropic-version header in your requests, as shown in the workflow and examples. Refer to Anthropic API versioning documentation.

Summary Engage multiple, uniquely configured AI agents (using different models via OpenRouter) in a single conversation. Trigger specific agents with @mentions or let them all respond. Easily scalable by editing simple JSON settings. Overview This workflow is for users who want to experiment with or utilize multiple AI agents with distinct personalities, instructions, and underlying models within a single chat interface, without complex setup. It solves the problem of managing and interacting with diverse AI assistants simultaneously for tasks like brainstorming, comparative analysis, or role-playing scenarios. It enables dynamic conversations with multiple AI assistants simultaneously within a single chat interface. You can: Define multiple unique AI agents. Configure each agent with its own name, system instructions, and LLM model (via OpenRouter). Interact with specific agents using @AgentName mentions. Have all agents respond (in random order) if no specific agents are mentioned. Maintain conversation history across multiple turns. It's designed for flexibility and scalability, allowing you to easily add or modify agents without complex workflow restructuring. Key Features Multi-Agent Interaction:** Chat with several distinct AI personalities at once. Individual Agent Configuration:** Customize name, system prompt, and LLM for each agent. OpenRouter Integration:** Access a wide variety of LLMs compatible with OpenRouter. Mention-Based Triggering:** Direct messages to specific agents using @AgentName. All-Agent Fallback:** Engages all defined agents randomly if no mentions are used. Scalable Setup:** Agent configuration is centralized in a single Code node (as JSON). Conversation Memory:** Remembers previous interactions within the session. How to Set Up Configure Settings (Code Nodes): Open the Define Global Settings Code node: Edit the JSON to set user details (name, location, notes) and add any system message instructions that all agents should follow. Open the Define Agent Settings Code node: Edit the JSON to define your agents. Add or remove agent objects as needed. For each agent, specify: "name": The unique name for the agent (used for @mentions). "model": The OpenRouter model identifier (e.g., "openai/gpt-4o", "anthropic/claude-3.7-sonnet"). "systemMessage": Specific instructions or persona for this agent. Add OpenRouter Credentials: Locate the AI Agent node. Click the OpenRouter Chat Model node connected below it via the Language Model input. In the 'Credential for OpenRouter API' field, select or create your OpenRouter API credentials. How to Use Start a conversation using the Chat Trigger input. To address specific agents, include @AgentName in your message. Agents will respond sequentially in the order they are mentioned. Example: "@Gemma @Claude, please continue the count: 1" will trigger Gemma first, followed by Claude. If your message contains no @mentions, all agents defined in Define Agent Settings will respond in a randomized order. Example: "What are your thoughts on the future of AI?" will trigger Chad, Claude, and Gemma (based on your default settings) in a random sequence. The workflow will collect responses from all triggered agents and return them as a single, formatted message. How It Works (Technical Details) Settings Nodes: Define Global Settings and Define Agent Settings load your configurations. Mention Extraction: The Extract mentions Code node parses the user's input (chatInput) from the When chat message received trigger. It looks for @AgentName patterns matching the names defined in Define Agent Settings. Agent Selection: If mentions are found, it creates a list of the corresponding agent configurations in the order they were mentioned. If no mentions are found, it creates a list of all defined agent configurations and shuffles them randomly. Looping: The Loop Over Items node iterates through the selected agent list. Dynamic Agent Execution: Inside the loop: An If node (First loop?) checks if it's the first agent responding. If yes (true path -> Set user message as input), it passes the original user message to the Agent. If no (false path -> Set last Assistant message as input), it passes the previous agent's formatted output (lastAssistantMessage) to the next agent, creating a sequential chain. The AI Agent node receives the input message. Its System Message and the Model in the connected OpenRouter Chat Model node are dynamically populated using expressions referencing the current agent's data from the loop ({{ $('Loop Over Items').item.json.* }}). The Simple Memory node provides conversation history to the AI Agent. The agent's response is formatted (e.g., AgentName:\n\nResponse) in the Set lastAssistantMessage node. Response Aggregation: After the loop finishes, the Combine and format responses Code node gathers all the lastAssistantMessage outputs and joins them into a single text block, separated by horizontal rules (---), ready to be sent back to the user. Benefits Scalability & Flexibility:** Instead of complex branching logic, adding, removing, or modifying agents only requires editing simple JSON in the Define Agent Settings node, making setup and maintenance significantly easier, especially for those managing multiple assistants. Model Choice:** Use the best model for each agent's specific task or persona via OpenRouter. Centralized Configuration:** Keeps agent setup tidy and manageable. Limitations Sequential Responses:** Agents respond one after another based on mention order (or randomly), not in parallel. No Direct Agent-to-Agent Interaction (within a turn):* Agents cannot directly call or reply to each other *during the processing of a single user message. Agent B sees Agent A's response only because the workflow passes it as input in the next loop iteration. Delayed Output:* The user receives the combined response only *after all triggered agents have completed their generation.

This workflow optimizes the management of inquiries received through a contact form (Contact Form 7 - CF7 Plugin) on a WordPress site, automating the process of classification, response drafting, and data storage. This workflow is particularly useful for businesses that receive multiple daily inquiries and want to improve their efficiency in managing customer communications. Benefits: ✅ Automation & Speed – Reduces the time needed to handle inquiries manually. ✅ Better Email Management – Ensures every message receives a timely and accurate response. ✅ Customization – The generated draft can be edited before sending, maintaining a personal touch. ✅ Inquiry History – Storing data in Google Sheets allows for easy tracking of customer interactions. ✅ Easy Integration – Works seamlessly with Contact Form 7 without complex configurations. How It Works Form Submission Handling: The workflow starts with a WordPress form submission captured via a webhook. The form data (first name, last name, email, phone, and message) is extracted and structured using the "Set Fields" node. Message Classification: The submitted message is classified into predefined categories (e.g., "Product Info," "Order Info," or "Other") using the "Message Classifier" node, powered by Google Gemini. Automated Email Drafting: Based on the classification, the workflow generates a professional email draft using one of three "Email Writer" nodes (for Product, Order, or Other requests). Each node uses Google Gemini to craft a personalized response with a structured format (subject and body). Email Draft Creation: The drafted email is sent as a Gmail draft to the appropriate department, including the original form data for context. Data Logging: All submissions, along with their classifications and email drafts, are logged in a Google Sheets spreadsheet for record-keeping and further action. Set Up Steps Install WordPress Plugin: Install the "CF7 to Webhook" plugin on WordPress and configure it to send form submissions to the n8n webhook URL. Configure Webhook in n8n: Set up the "From Wordpress" webhook node in n8n to receive POST requests from the WordPress form. Google Gemini Integration: Ensure the Google Gemini nodes are properly authenticated with the correct API credentials. Gmail and Google Sheets Setup: Authenticate the Gmail and Google Sheets nodes with the appropriate OAuth2 credentials and specify the target spreadsheet and sheet name. Customize Classification Categories: Adjust the categories in the "Message Classifier" node to match your business needs. Test the Workflow: Trigger a test form submission to verify the workflow processes data correctly, classifies the message, generates an email draft, and logs the data. Need help customizing? Contact me for consulting and support or add me on Linkedin.

This workflow demonstrates three distinct approaches to chaining LLM operations using Claude 3.7 Sonnet. Connect to any section to experience the differences in implementation, performance, and capabilities. What you'll find: 1️⃣ Naive Sequential Chaining The simplest but least efficient approach - connecting LLM nodes in a direct sequence. Easy to set up for beginners but becomes unwieldy and slow as your chain grows. 2️⃣ Agent-Based Processing with Memory Process a list of instructions through a single AI Agent that maintains conversation history. This structured approach provides better context management while keeping your workflow organized. 3️⃣ Parallel Processing for Maximum Speed Split your prompts and process them simultaneously for much faster results. Ideal when you need to run multiple independent tasks without shared context. Setup Instructions: API Credentials: Configure your Anthropic API key in the credentials manager. This workflow uses Claude 3.7 Sonnet, but you can modify the model in each Anthropic Chat Model node, or pick an entirely different LLM. For Cloud Users: If using the parallel processing method (section 3), replace {{ $env.WEBHOOK_URL }} in the "LLM steps - parallel" HTTP Request node with your n8n instance URL. Test Data: The workflow fetches content from the n8n blog by default. You can modify this part to use a different content or a data source. Customization: Each section contains a set of example prompts. Modify the "Initial prompts" nodes to change the questions asked to the LLM. Compare these methods to understand the trade-offs between simplicity, speed, and context management in your AI workflows! Follow me on LinkedIn for more tips on AI automation and n8n workflows!