Jordan Hoyle
Workflows by Jordan Hoyle
Book club manager & recommendation engine with Mistral AI and Gemini Vision
## 📚 The Literary Curator: AI Book Club Manager & Recommendation Engine Transform your n8n instance into a sophisticated, automated backend for a book club. This "Literary Curator" workflow acts as an all-in-one administrator, archivist, and reading guide. It intelligently analyzes your club's collective reading history to generate personalized recommendations, onboard new members, and manage all your club's data via email, chat, and web forms. ## ✨ Key Features Automated Recommendation Engine: A weekly scheduled agent (using Mistral AI) analyzes the club's "Book Archive" to generate 10 fresh, non-duplicate book recommendations with witty, personalized "Why This Read" justifications. Visual Bookshelf Scanning: Uses Google Gemini Vision to analyze photos of physical bookshelves or Goodreads screenshots and automatically populate the database. The "Literary Oracle" Chatbot: A conversational AI agent that has full context of the club's history. It can answer questions, add books to the archive, or manage members via chat. Full Member Management: Automated onboarding flows for new members, including welcome emails and database entry. Multi-Channel Interaction: Users can interact via Webhooks (API), n8n Forms, or Chat. Weekly Newsletters: Automatically compiles the AI's "Vibe Check" summary and top 10 recommendations into a beautifully formatted HTML email sent via Gmail. ## 🤖 AI Models Used Mistral Cloud (Large/Medium): Powers the core reasoning, recommendation logic, and the chat Oracle. Google Gemini (PaLM/Flash): Used for vision analysis (scanning bookshelf photos) and generating discussion prompts. ## 🛠️ Setup Guide Prerequisites: n8n version with LangChain support. Mistral Cloud API Key Google Gemini API Key Gmail OAuth2 Credentials ## 🚀 How to Use #### Automated Schedule By default, the workflow runs every Friday at 7:00 PM. It checks the archive, generates a new weekly summary and recommendation list, saves it to the database, and emails all members. #### User Forms The workflow includes built-in n8n Forms for user interaction: #### Feedback Form For members to rate books or request specific genres. Idea Board: For submitting general reading ideas. #### Upload Form Accepts images of bookshelves or Goodreads exports to bulk-import reading history. ### API / App Backend This workflow exposes several POST webhooks (e.g., /api/ai/chat, /api/archive/add), allowing you to build a custom frontend (React, Glide, etc.) on top of this n8n workflow.
Automate job searching & resume customization with AI, LinkedIn & Google Sheets
# 🤖 AI-Powered Job Matcher & Resume Customizer ## Description This advanced workflow automates the entire job search and preparation process, moving beyond simple notifications to provide **AI-driven career intelligence**. It connects to LinkedIn to scrape fresh job postings, filters against jobs you've already seen, and then uses powerful LLMs (Mistral Large/Small) to perform a detailed resume-to-job match, generate tailored cover letters, and provide concrete resume improvement suggestions. All data is logged into a Google Sheet for comprehensive tracking, and a clean, single **Daily Digest Email** summarizes the top 5 matches found each day. --- ## ✨ Key Features * **Automated Scheduling:** Runs daily to find new job postings. * **Multi-Keyword Search:** Uses your main job title and three alternate titles generated by an AI Agent for maximum search coverage. * **LinkedIn Web Scraping:** Pulls new job URLs, details, location, and salary data from LinkedIn Search results. * **Duplicate Prevention:** Uses the **Compare Datasets** node to ensure only new, unseen jobs are processed against your master Google Sheet. * **Intelligent Matching (LLM):** The workflow performs a detailed job-to-resume comparison, generating: * A **Match Score (0-100)** with evidence for alignment in skills, experience, and domain. * A **Tailored Cover Letter** specific to the job title and company. * **Actionable Resume Improvement** points (e.g., `[ADD]`, `[QUANTIFY]`) to optimize your resume for the specific role. * **Centralized Tracking:** Saves all job data, match scores, cover letters, and resume suggestions to a **Google Sheet**. * **Professional Daily Digest:** Sends a single, clean **HTML email** summarizing the top 5 highest-scoring job matches for easy review. --- ## 🛠️ Prerequisites 1. **n8n Credentials:** * **Google Drive:** To download your resume (PDF/DOCX file URL). * **Google Sheets:** To connect to your job tracking sheet. * **Gmail:** To send the daily digest email. * **Mistral Cloud:** For the LLM processing (Resume Breakdown, Job Matching, and Resume Analysis). 2. **External Files:** * A **Job Tracking Google Sheet** (used as a master database). * Your current **Resume file** (PDF recommended, hosted on Google Drive). 3. **Setup Notes:** * Update the file links (`Download Resume` node) and Google Sheet details (`Get row(s)`/`Append` nodes). * Set your personal email address in the `Send Digest Email` node. * Review the LLM prompts to tailor the AI agent's persona and output fields to your exact needs.
Email-to-task automation with Mistral AI (Gmail/Outlook to Google Tasks/Microsoft To Do)
## Description Automate your personal productivity by transforming actionable emails from Gmail and Outlook into structured tasks within Google Tasks or Microsoft To Do, all managed by a multi-agent AI system. This advanced workflow utilizes a powerful Mistral Large AI Agent to orchestrate your daily task management. It operates by fetching recent emails, structuring the data, determining the correct task manager, and delegating the execution to specialized sub-agents. It's built with rate-limiting in mind, ensuring efficient and reliable operation across your connected services. ## ✨ Features - Unified Email Input: Automatically fetches and merges emails from Gmail and Microsoft Outlook received within the last 24 hours. - Centralized Data Storage: Stores and deduplicates raw email data in an n8n Data Table, converting HTML content to plain text for AI processing. - Intelligent Task Extraction: A Main Task Orchestration Agent (powered by Mistral Large) reads the email data, identifies actionable tasks, and structures them with a Title, Due Date, Notes, and a Target System (Google Tasks or Microsoft To Do). - Dedicated Task Execution: Leverages two specialized sub-agents (Google Tasks Agent and Microsoft To Do Agent) that handle the creation or updating of tasks, ensuring API integrity and focused execution. - Scalable and Safe: Implements batch processing (max 5 tasks) and mandatory 5-second delays between sub-agent calls to prevent API rate limits and token overruns. - Conversation History: Uses Memory Buffer Window nodes to maintain context within the AI agents. ## 🛠️ How to Set Up 1. Credentials: Connect your credentials for Gmail, Microsoft Outlook, Google Tasks, Microsoft To Do, and the Mistral Cloud Chat Model. 2. Data Table: Ensure the 'To Do Database' Data Table exists. 3. Customize AI Agents: - In the Tasks AI Agent (the main orchestrator), review the system prompt and verify the mandatory "Jordan Hoyle" filter. Change this to your name or the name of the person whose tasks are being managed. - In the Google Tasks Agent and Microsoft To Do Agent nodes, ensure the Task List ID fields are correctly set to your desired task lists. - Schedule: Set the workflow to run on a schedule (e.g., once daily) or run it manually. This workflow is the perfect solution for anyone overwhelmed by managing tasks scattered across their inbox and multiple to-do apps, bringing AI-driven order to your digital life!
Nested PDF analysis with Mistral AI & OneDrive for document summarization
# Description Automate the discovery and analysis of PDF files across a deeply nested OneDrive folder structure. This workflow recursively searches folders, filters for new or updated PDFs, extracts text, and uses a Mistral AI agent to generate a concise Executive Summary, Key Findings, and Structured Metadata (Date, Location, etc.), storing all insights into a n8n Data Table for easy access and further automation. # Key Features & How It Works #### Scheduled Trigger & Recursive Folder Search: - The workflow runs automatically (scheduled for 8 PM in this template) to monitor a specified main folder on OneDrive. - It performs a deep, multi-level search (up to 8 layers) across subfolders to ensure no documents are missed. #### Smart Deduplication & Filtering: - It checks new files against an internal n8n Data Table using the Compare Datasets node, ensuring only new or unique PDF files are processed, saving AI credits and processing time. - A size check is also included, preventing attempts to process excessively large files. - AI-Powered Document Intelligence (Mistral LLM): #### For each new PDF, the workflow extracts the text and passes it to a Mistral AI model for dual-stream analysis: - Overview Agent: Generates an impartial, professional Executive Summary, a list of Key Findings & Data Points, and the document's Scope/Context. - Document Information Agent: Extracts crucial metadata, including the single most relevant date, location (City/State/Country), and professional information (Name, Title, Organization). #### Structured Output and Archiving: - AI outputs are meticulously validated and reformatted into a clean JSON object using Structured Output Parsers. - The complete analysis, along with the original file name and path, is then logged as a new row in an n8n Data Table. # Setup Notes OneDrive Folder: You must specify the exact name of your main folder in the 'Search for Main Folder' node. Data Table: Ensure your n8n Data Table exists with the required columns: Summary, Key_Findings, Scope, Date, Location, File_Name, and Path. Deep Folder Structure: The current configuration supports up to 8 levels of subfolders. If your files go deeper, you may need to add more "Get items in a folder" and "If" nodes. AI Customization: Review the AI agent prompts and the structured output schemas to customize the fields you want to extract or the summary style you require. # Extend This Workflow #### The final output is organized data. You can easily extend this workflow to: - Send daily/weekly digest emails with new summaries. - Sync the extracted data to a Google Sheet, Airtable, or other database. - Add a secondary AI agent to perform follow-up actions based on the "Key Findings."