Access execution data from an error workflow
Sometimes you want to take a different action in your error workflow based on the data that was flowing through it. This template illustrates how you can do that (more specifically, how you can retrieve the data of a webhook node). How it works Use the 'n8n' node to fetch the data of the failed execution Parse that data to find webhook nodes and extract the data of the one that was executed
By David RobertsMulti-modal personal AI assistant with Telegram & Google Gemini for productivity tools
Automate Your Life: The Ultimate AI Assistant in Telegram (Powered by Google Gemini) Transform your Telegram messenger into a powerful, multi-modal personal or team assistant. This n8n workflow creates an intelligent agent that can understand text, voice, images, and documents, and take action by connecting to your favorite tools like Google Calendar, Gmail, Todoist, and more. At its core, a powerful Manager Agent, driven by Google Gemini, interprets your requests, orchestrates a team of specialized sub-agents, and delivers a coherent, final response, all while maintaining a persistent memory of your conversations. Key Features 🧠 Intelligent Automation: Uses Google Gemini as a central "Manager Agent" to understand complex requests and delegate tasks to the appropriate tool. 🗣️ Multi-Modal Input: Interact naturally by sending text, voice notes, photos, or documents directly into your Telegram chat. 🔌 Integrated Toolset: Comes pre-configured with agents to manage your memory, tasks, emails, calendar, research, and project sheets. 🗂️ Persistent Memory: Leverages Airtable as a knowledge base, allowing the assistant to save and recall personal details, company information, or past conversations for context-rich interactions. ⚙️ Smart Routing: Automatically detects the type of message you send and routes it through the correct processing pipeline (e.g., voice is transcribed, images are analyzed). 🔄 Conversational Context: Utilizes a window buffer to maintain short-term memory, ensuring follow-up questions and commands are understood within the current conversation. How It Works The Telegram Trigger node acts as the entry point, receiving all incoming messages (text, voice, photo, document). A Switch node intelligently routes the message based on its type: Voice: The audio file is downloaded and transcribed into text using a voice-to-text service. Photo: The image is downloaded, converted to a base64 string, and prepared for visual analysis. Document: The file is routed to a document handler that extracts its text content for processing. Text: The message is used as-is. A Merge node gathers the processed input into a unified prompt. The Manager Agent receives this prompt. It analyzes the user's intent and orchestrates one or more specialized agents/tools: memory_base (Airtable): For saving and retrieving information from your long-term knowledge base. todoandtask_manager (Todoist): To create, assign, or check tasks. email_agent (Gmail): To compose, search, or send emails. calendar_agent (Google Calendar): To schedule events or check your agenda. research_agent (Wikipedia/Web Search): To look up information. project_management (Google Sheets): To provide updates on project trackers. After executing the required tasks, the Manager Agent formulates a final response and sends it back to you via the Telegram node. Setup Instructions Follow these steps to get your AI assistant up and running. Telegram Bot: Create a new bot using the BotFather in Telegram to get your Bot Token. In the n8n workflow, configure the Telegram Trigger node's webhook. Add your Bot Token to the credentials in all Telegram nodes. For proactive messages, replace the chatId placeholders with your personal Telegram Chat ID. Google Gemini AI: In the Google Gemini nodes, add your credentials by providing your Google Gemini API key. Airtable Knowledge Base: Set up an Airtable base to act as your assistant's long-term memory. In the memory_base nodes (Airtable nodes), configure the credentials and provide the Base ID and Table ID. Google Workspace APIs: Connect your Google account credentials for Gmail, Google Calendar, and Google Sheets. In the relevant nodes, specify the Document/Sheet IDs you want the assistant to manage. Connect Other Tools: Add your credentials for Todoist and any other integrated tool APIs. Configure Conversational Memory: This workflow is designed for multi-user support. Verify that the Session Key in the "Window Buffer Memory" nodes is correctly set to a unique user identifier from Telegram (e.g., {{ $json.chat.id }}). This ensures conversations from different users are kept separate. Review Schedule Triggers: Check any nodes designed to run on a schedule (e.g., "At a regular time"). Adjust their cron expressions, times, and timezone to fit your needs (e.g., for daily summaries). Test the Workflow: Activate the workflow. Send a text message to your bot (e.g., "Hello!"). Estimated Setup Time 30–60 minutes: If you already have your API keys, account credentials, and service IDs (like Sheet IDs) ready. 2–3 hours: For a complete, first-time setup, which includes creating API keys, setting up new spreadsheets or Airtable bases, and configuring detailed permissions.
By Anshul ChauhanAutomate job search & resume matching with LinkedIn, Gemini AI & Google Sheets
Description This workflow helps you find and evaluate job opportunities automatically, without spending hours searching and comparing roles. It uses your resume to look for relevant jobs on LinkedIn, checks how well each role matches your profile, and organises everything neatly in Google Sheets so you can focus on applying to the best opportunities. How it works On a schedule, the workflow downloads your resume from Google Drive and analyses it to understand your skills and experience. Based on this, it creates LinkedIn job searches and pulls in recent job listings. Each job is then reviewed using AI to compare the job description with your resume, produce a match score, suggest resume improvements, and generate a tailored cover letter. All results are saved to Google Sheets, and you’re notified by email when the run finishes. How to use Make a copy of the Google Sheets template and keep it for your own job tracking. Upload your resume (PDF) to Google Drive. Connect your Google Drive, Google Sheets, Gmail, and AI credentials in n8n. Update the Config node with your preferences (remote work, Easy Apply, job limit). Paste your copied Google Sheet IDs into the workflow. Turn on the Schedule Trigger and activate the workflow. Requirements Google Drive account for storing your resume Google Sheets account for tracking results Gmail account for notifications AI model access (Google Gemini or similar) n8n (cloud or self-hosted) Customising this workflow You can easily adapt this workflow to suit your goals. Change the job limits, locations, or remote preferences in the Config node. Update the AI prompts to target different roles or industries, or extend the workflow to send results to tools like Notion, a CRM, or your own application tracker. Good to know This workflow is designed to help you screen and prepare for jobs, not to apply automatically. Match scores are a guide, not a guarantee, so it’s always worth reviewing roles manually. Also, since LinkedIn pages can change over time, you may occasionally need to update HTML selectors to keep things running smoothly.
By Dinakar SelvakumarAnalyze trending YouTube videos with Apify, OpenAI, and Google Sheets
⚙️ Trending YouTube Videos Research Workflow: 🧑💻 Author: [Leewei] Automates scraping trending videos based on a keyword, filters high-potential ones, analyzes thumbnails and transcripts with AI, generates optimized titles and outlines, and updates a Google Sheet for content ideas. --- 🚀 Steps to Connect: Apify API Token Sign up for a free account at Apify and generate your API token. Paste the token into the two HTTP Request nodes (replace <token> in the Authorization header). 💡 This enables scraping YouTube video data and transcripts—setup takes about 5 minutes. OpenAI API Key Go to OpenAI and generate your API key. Add it to the credentials for the YouTube Title Generator, Analyze Thumbnail, and Outline Generator nodes. 💡 Use models like GPT-4o-mini for thumbnail analysis and title/outline generation. Google Sheets Credentials Set up OAuth2 credentials in n8n for Google Sheets with access to your Drive. Update the documentId in the Step 1 Results, Find Duplicate Entries, and Update Rows nodes to your own Google Sheet ID (clone the provided sheet if needed). 💡 This stores filtered video data, AI-generated titles, and outlines—expect 10-15 minutes for auth setup. (Optional) Customize Form Trigger If deploying publicly, no changes needed—the form prompts for "Keyword or Topic" to start the search. Test with a sample keyword like "AI automation" to see results in your sheet. ---
By LeeWeiAutomate resume screening & candidate routing with Gemini AI and Google Sheets
Streamline your recruitment process with AI-powered resume analysis that goes beyond keyword matching. Overview This workflow revolutionizes hiring by using specialized AI agents to intelligently analyze resumes for different positions. Unlike traditional ATS systems that rely on keyword matching, this solution provides deep, contextual analysis of candidate qualifications and automatically manages the entire screening process from application to response. How it works Application Submission - Candidates complete a form with personal details, select their desired position (ICT, Customer Care, Accounting, or HR), and upload their resume Secure Storage - Resumes are automatically saved to Google Drive for permanent record-keeping Intelligent Routing - A switch node classifies applications by position and routes them to specialized AI agents AI Analysis - Position-specific agents (each with customized prompts and guardrails) extract text from PDFs and rate candidates on a 1-10 scale with detailed commentary CRM Integration - All data (timestamp, candidate info, position, score, AI comments, resume link) flows into Google Sheets for easy tracking Automated Response - A secondary workflow sends interview invitations to high-scoring candidates (7-10) and professional rejection emails to others (below 7) Key Benefits ✅ Contextual Analysis - AI understands skills and experience, not just keywords ✅ Faster Hiring - Close applications once you have enough qualified candidates ✅ No Expertise Required - HR teams don't need technical knowledge in every field ✅ Fully Automated - From submission to interview invitation without manual intervention ✅ Customizable - Adjust AI prompts and scoring criteria for each position ✅ Transparent - All AI reasoning is logged for review Set up steps Time to set up: ~30-45 minutes Prerequisites: n8n instance (cloud or self-hosted) Google Drive account Google Sheets account AI provider credentials (OpenAI, Anthropic, or compatible API) Email service (Gmail, SMTP, or other n8n-supported service) Quick Setup: Import the workflow into your n8n instance Connect your Google Drive and Google Sheets accounts Configure your AI provider credentials in the agent nodes Customize AI prompts for each position in the respective agent nodes (detailed instructions in sticky notes) Set up your email service credentials Customize email templates for invitations and rejections Test with sample resumes for each position Deploy your application form and share the link Detailed configuration instructions are included in sticky notes within the workflow. Use Cases Startups scaling their team quickly HR departments handling high application volumes Agencies managing recruitment for multiple clients Companies hiring for specialized technical roles Customization Options Adjust scoring thresholds for each position Modify AI evaluation criteria via prompts Add additional positions with dedicated agents Integrate with your existing HRIS or ATS Add SMS notifications for candidates Note: This workflow includes two separate flows - the main screening workflow and an automated response workflow. Both are included in the download.
By Shadrack