Workflow Templates

This workflow contains community nodes that are only compatible with the self-hosted version of n8n. Overview This workflow is designed for inspiring teams or individuals who need to quickly and efficiently serve files, content, or documents via the web. It offers a straightforward approach while still being flexible and adaptable for different branding needs. The HTML branding can be easily updated through an external LLM, making it possible to fully customize the look and feel without complex coding. You simply prompt the AI (using the JSON as a guide) to output your desired design. This template makes use of a powerful community node, which brings in the benefits of shared knowledge and collective improvement. Setup Instructions Copy the JSON Preset into your AI model or use your own, along with your custom branding requirements. Ask the model for an HTML response, then paste the output into the HTML Preset. Next, connect the JSON inputs into the relevant locations from the structured output parser. Once complete, the static HTML can be served via AWS or another web server using HTTPS, ensuring secure and reliable delivery. Workflow Explanation This AI Agent takes a simple user input and transforms it into dynamic HTML. The structured JSON output forces consistent formatting, while giving you the creative flexibility to adjust visuals on demand. Since the output is relatively consistent the workflow can produce repitive business documents with consistency and accuracy. Requirements LLM account access AWS Account (S3) or HTTPs equivalent Basic HTML/JSON knowledge PDF.co Account

This n8n template serves as a security layer for your marketing efforts, ensuring that only high-quality, human-verified leads reach your CRM while automatically blacklisting bots and VPN-based submissions. How it works Lead Intake: The workflow triggers via a Webhook (e.g., from Tally.so or other form builders) when a new lead is submitted. Dual-Layer Analysis: IP Intelligence:** It queries AbstractAPI to check the lead's IP address for red flags like VPNs, proxies, or data centre origins. AI Intent Analysis:** Simultaneously, it sends the name and message to GPT-4o-mini to analyse the content for non-human patterns, gibberish, or spam scripts. Smart Filtering:** A Merge node combines these data points, and an If Node applies "OR" logic: if the IP is a VPN/Proxy OR the AI detects spam, the lead is flagged. Automated Action: Verified Leads:** Legitimate submissions are saved to a "Verified" Google Sheet for sales follow-up. Fraud Prevention:** Flagged leads are moved to a "Potential Spam" sheet. This list can be synced as an exclusion audience in Google or Meta Ads to prevent wasting budget on retargeting bots. Instant Alerts: The team is notified immediately via Slack whenever a fraudulent submission is neutralized. Requirements OpenAI API Key:** For lead content analysis. AbstractAPI Key:** For IP intelligence & security flags. Google Sheets:** To store verified and blacklisted lead data. Slack:** For real-time fraud alerts. Customising this workflow Field Mapping:** If your form uses different labels (e.g., "Comments" instead of "Message"), update the expressions in the Message model and Google Sheets nodes. Exclusion Logic:** You can tighten the filter by adding more conditions to the If Node, such as specific country blocking or email domain validation.

Description  Automatically assigns new tasks from an Excel/Google Sheets source to the best-fit employee based on expertise, then creates issues in Jira. Gain fast, consistent routing that reduces manual triage and speeds delivery. 🧠📊➡️🗂️ What This Template Does  Fetches new task rows and related areas from Google Sheets/Excel. Analyzes each item with an AI Agent using Azure OpenAI. Selects the best-fit employee by matching the area to expertise stored in the sheet. Returns structured outputs (task, assignee, expertise, ID, bug/task) and creates the Jira issue. Applies rule-based handling for bugs vs tasks via a Switch node. Key Benefits  ⏱ Save time by automating task assignment from new entries. 🎯 Improve accuracy with expertise-based matching. 📋 Keep clean, structured outputs for downstream systems. 🔁 Seamless handoff from Sheets to Jira with no manual steps. Features  Google Sheets Trigger: Reads new task name and related area from the sheet. AI Agent (Azure OpenAI): Evaluates expertise fit and decides the best assignee. Structured Output Parser: Returns exactly five fields: task_name, assignee_name, expertise, employee_id, item_type (bug/task). Jira Create Issue: Creates issues in Jira using selected assignee and item type. Switch (Rules): Routes logic for bugs vs tasks for consistent categorization. Requirements  n8n instance: Cloud or self-hosted. Google Sheets access: Sheet containing employee roster with columns for Name, Expertise, and ID; connect credentials in n8n. Azure OpenAI (GPT-4o-mini): Configure the Azure OpenAI Chat Model credentials for the AI Agent. Jira credentials: Authorized account with permissions to create issues. Output Parser setup: Structured Output Parser configured to the five-field schema: task_name, assignee_name, expertise, employee_id, item_type. Target Audience  🧩 IT Support and Ops teams routing incoming work. 🧭 Project managers orchestrating assignments at scale. 🛠 Engineering managers seeking consistent triage. 📈 Business operations teams automating intake to delivery. Step-by-Step Setup Instructions  Connect Google Sheets credentials and map the task and area fields; ensure roster columns (Name, Expertise, ID) are present. Add Jira credentials and set the Create Issue node to your target project and issue type. Configure Azure OpenAI (GPT-4o-mini) for the AI Agent and provide credentials. Import the workflow, assign all credentials, and align the Structured Output Parser to the five-field schema. Run a test with sample rows; confirm assignee selection and Jira issue creation; then enable scheduling. Security Best Practices  Use least-privilege API tokens for Google Sheets and Jira. Restrict sheet access to only required users and service accounts. Validate and sanitize incoming task data before issue creation. Store credentials securely in n8n and rotate them regularly. Log only necessary fields; avoid sensitive data in workflow logs.

How it works Receives chat messages from customers requesting table reservations. Uses an AI Agent with OpenAI Chat Model to understand and process requests. Checks table information, availability, and existing reservations from Google Sheets. Calculates guest counts and reservation timing using the Calculator node. Updates table availability and reservation records in real-time. Handles reservation changes, including updates and cancellations. Set up steps Add credentials** for OpenAI (Chat Model) and Google Sheets. In the AI Agent node, link: Chat Model → OpenAI Chat Model node. Memory → Simple Memory node. Tools → Calculator and Google Sheets nodes for reservation data handling. Configure Google Sheets nodes: Get Table Information (read sheet) Get Table Availability (read sheet) Get Table Reservations (read sheet) Update Table Availability (update sheet) Update Reservations (append sheet) Cancel Reservations (delete sheet) Ensure your sheets have consistent column names for table IDs, dates, times, and guest counts. Test by sending a reservation request through the chat trigger and verify updates in the Google Sheets.

Prepare external meetings in Google Calendar with AI summaries powered by MadKudu Intelligence Automatically prepare for external meetings by generating AI-powered attendee briefs and sending them to your calendar, using MadKudu MCP. Who’s it for This workflow is designed for customer-facing professionals—such as Account Executives, Customer Success Managers, or Founders—who want to walk into meetings informed, without spending time researching attendees. It’s perfect for teams that use Google Calendar, manage accounts in a CRM, and want to automate meeting prep with real-time enrichment and summaries. How it works The workflow checks Google Calendar every hour for upcoming meetings. It filters out internal-only meetings using your company email domain. For meetings with external attendees, it: Uses MadKudu MCP to enrich attendees and company Summarizes attendee details and context using an OpenAI model It creates a private calendar event with the meeting brief, visible only to you. How to set up Connect your Google Calendar account. Set your MadKudu API Key as a variable Connect your OpenAI credentials. Set your company domain (e.g. acme.com) as a variable Test and Activate the workflow. Requirements Google Calendar integration OpenAI credentials MadKudu account with access to API key How to customize the workflow Adjust the trigger frequency to check more or less often. Update the prompt in the AI Agent node to control the summary format or tone.

Create a Telegram bot that answers questions using Retrieval-Augmented Generation (RAG) powered by Lookio and an LLM agent (GPT-4.1). This template handles both text and voice messages (voice transcribed via a Mistral model by default), routes queries through an agent that can call a Lookio tool to fetch knowledge from your uploaded documents, and returns concise, Telegram-friendly replies. A security switch lets you restrict use to a single Telegram username for private testing, or remove the filter to make the bot public. Who is this for? Internal teams & knowledge workers**: Turn your internal docs into an interactive Telegram assistant for quick knowledge lookups. Support & ops**: Provide on-demand answers from your internal knowledge base without exposing full documentation. Developers & automation engineers**: Use this as a reference for integrating agents, transcription, and RAG inside n8n. No-code builders**: Quickly deploy a chat interface that uses Lookio for accurate, source-backed answers. What it does / What problem does this solve? Provides accurate, source-backed answers: Routes queries to **Lookio so replies are grounded in your documents instead of generic web knowledge. Handles voice & text transparently: Accepts Telegram voice messages, transcribes them (via the **Mistral API node by default), and treats transcripts the same as typed text. Simple agent + tool architecture: Uses a **LangChain AI Agent with a Query knowledge base tool to separate reasoning from retrieval. Privacy control: Includes a **Myself? filter to restrict access to a specific Telegram username for safe testing. How it works Trigger: Telegram Trigger receives incoming messages (text or voice). Route: Message Router detects voice vs text. Voice files are fetched with Get Audio File. Transcribe: Mistral transcribe receives the audio file and returns a transcript; the transcript or text is normalized into preset\_user\_message and consolidated in Consolidate user message. Agent: AI Agent (GPT-4.1-mini configured) runs with a system prompt that instructs it to call the Query knowledge base tool when domain knowledge is required. Respond: The agent output is sent back to the user via Telegram answer. How to set up Create a Lookio assistant: Sign up at https://www.lookio.app/, upload documents, and create an assistant. Add credentials in n8n: Configure Telegram API, OpenAI (or your LLM provider), and Mistral Cloud credentials in n8n. Configure Lookio tool: In the Query knowledge base node, replace <your-lookio-api-key> and <your-assistant-id> placeholders with your Lookio API Key and Assistant ID. Set Telegram privacy (optional): Edit the Myself? If node and replace <Replace with your Telegram username> with your username to restrict access. Remove the node to allow public use. Adjust transcription (optional): Swap the Mistral transcribe HTTP node for another provider (OpenAI, Whisper, etc.) and update its prompt to include your jargon list. Connect LLM: In OpenAI Chat Model node, add your OpenAI API key (or configure another LLM node) and ensure the AI Agent node references this model. Activate workflow: Activate the workflow and test by messaging your bot in Telegram. Requirements An n8n instance (cloud or self-hosted) A Telegram Bot token added in n8n credentials A Lookio account, API Key, and Assistant ID An LLM provider account (OpenAI or equivalent) for the OpenAI Chat Model node A Mistral API key (or other transcription provider) for voice transcription How to take it further Add provenance & sources**: Parse Lookio responses and include short citations or source links in the agent replies. Rich replies**: Use Telegram media (images, files) or inline keyboards to create follow-up actions (open docs, request feedback, escalate to humans). Multi-user access control**: Replace the single-username filter with a list or role-based access system (Airtable or Google Sheets lookup) to allow multiple trusted users. Logging & analytics: Save queries and agent responses to **Airtable or Google Sheets for monitoring, quality checks, and prompt improvement.

What this template does Batch-evaluates compliance controls from Google Sheets using the CyberPulse Compliance API. Each control is scored, mapped to selected frameworks, enriched with crosswalk mappings, and summarized with AI-generated findings and recommendations. How it works Read from Sheets → Build control text (response_text + implementation_notes) → CyberPulse Compliance (scoring, mapping, AI summary) → Normalize → Append results to Sheets. Setup (5–10 min) Add Google Sheets + CyberPulse HTTP Header Auth credentials. Replace YOUR_SHEET_ID and sheet names. Provide your Crosswalk JSON URL (raw GitHub or API endpoint) or use this url: https://www.cyberpulsesolutions.com/xw.json Select frameworks to evaluate against. Run a small test, then full batch. CyberPulse API (required for production) Use hosted scoring/mapping (no local ML code). Create a CyberPulse HTTP Header Auth credential with API Key. In the node: paste Crosswalk URL, select frameworks, set credential. For large sheets, add a short Wait or reduce batch size. Input columns control_id control_description response_text implementation_notes evidence_url_1 … evidence_url_4 Output columns status evaluation score confidence rationale categories evidence_count mapped_count mapping_flat frameworks_selected engine_version ai_summary ai_findings (3 per control) ai_recommendations (3 per control) Troubleshooting No rows → check sheet ID and range. Empty mappings → verify Crosswalk URL. Write errors → confirm results sheet + permissions. Learn more about CyberPulse Compliance Agent: https://www.cyberpulsesolutions.com/solutions/compliance-agent Start free: https://www.cyberpulsesolutions.com/pricing Email: info@cyberpulsesolutions.com

This workflow fetches recent emails from Outlook and uses OpenAI to assign a category (e.g., Red, Yellow, Green). It then updates each message’s category in Outlook. ⚙️ Setup Instructions 1️⃣ Set Up Outlook Connection In n8n → Credentials → New → Microsoft Outlook OAuth2 API Log in with your Outlook account & approve access Attach this credential to the Get Messages from Outlook and Update Category nodes in the workflow (Optional) Adjust the limit field in Get Messages from Outlook if you want more/less than 5 results 2️⃣ Set Up OpenAI Connection Go to the OpenAI Platform Navigate to OpenAI Billing Add funds to your billing account Copy your API key into the OpenAI credentials in n8n and select it on the OpenAI Chat Model and Categorizing Agent nodes ✅ Notes The agent reads subject + bodyPreview and returns a JSON category. The Update Category node writes that category back to Outlook. You can tweak the category names or logic in the Categorizing Agent system message. 📬 Contact Need help customizing the categorization rules or routing categories to folders? 📧 robert@ynteractive.com 🔗 Robert Breen 🌐 ynteractive.com

Stay informed about the latest n8n updates automatically! This workflow monitors the n8n GitHub repository for new pull requests, filters updates from today, generates an AI-powered summary, and sends notifications to your Telegram channel. Who's it for n8n users who want to stay up-to-date with platform changes Development teams tracking n8n updates Anyone managing n8n workflows who needs to know about breaking changes or new features How it works Daily scheduled check at 10 AM for new pull requests Fetches latest PR from n8n GitHub repository Filters to only process today's updates Extracts the pull request summary AI generates a clear, technical summary in English Sends notification to your Telegram channel

This template adapts Andrej Karpathy’s LLM Council concept for use in n8n, creating a workflow that collects, evaluates, and synthesizes multiple large language model (LLM) responses to reduce individual model bias and improve answer quality. 🎯 The gist This LLM Council workflow acts as a moderation board for multiple LLM “opinions”: The same question is answered independently by several models. All answers are anonymized. Each model then evaluates and ranks all responses. A designated Council Chairman model synthesizes a final verdict based on these evaluations. The final output includes: The original query The Chairman’s verdict The ranking of each response by each model The original responses from all models The goal is to reduce single‑model bias and arrive at more balanced, objective answers. 🧰 Use cases This workflow enables several practical applications: Receiving more balanced answers by combining multiple model perspectives Benchmarking and comparing LLM responses Exploring diverse viewpoints on complex or controversial questions ⚙️ How it works The workflow leverages OpenRouter, allowing access to many LLMs through a single API credential. In the Initialization node, you define: Council member models: Models that answer the query and later evaluate all responses Chairman model: The model responsible for synthesizing the final verdict Any OpenRouter-supported model can be used: https://openrouter.ai/models For simplicity: Input is provided via a Chat Input trigger Output is sent via an email node with a structured summary of the council’s results 👷 How to use Select the LLMs to include in your council: Council member models: Models that independently answer and evaluate the query. The default template uses: openai/gpt-4o google/gemini-2.5-flash anthropic/claude-sonnet-4.5 perplexity/sonar-pro-search Chairman model: Choose a model with a sufficiently large context window to process all evaluations and rankings. Start the Chat Input trigger. Observe the workflow execution and review the synthesized result in your chosen output channel. ⚠️ Avoid using too many models simultaneously. The total context size grows quickly (n responses + n² evaluations), which may exceed the Chairman model’s context window. 🚦 Requirements OpenRouter API access** configured in n8n credentials SMTP credentials** for sending the final council output by email (or replace with another output method) 🤡 Customizing this workflow Replace the Chat Input trigger with alternatives such as Telegram, email, or WhatsApp. Redirect output to other channels instead of email. Modify council member and chairman models directly in the Initialization node by updating their OpenRouter model names.

Create Viral LinkedIn Content with O3 & GPT-4.1-mini Multi-Agent Team This n8n workflow is a multi-agent LinkedIn content factory. At its heart is the Content Director Agent (O3 model), who acts as the project manager. It listens for LinkedIn chat messages, analyzes them, and coordinates a team of AI specialists (all powered by GPT-4.1-mini) to produce viral, engaging, and optimized LinkedIn content. 🟢 Section 1 – Workflow Entry & Strategy Layer Nodes: 🔔 When chat message received → Captures LinkedIn requests (your idea, draft, or prompt). 🧠 Content Director Agent (O3) → Acts as the leader, deciding how the content should be structured and which specialists to call. 💡 Think Node → Helps the Director brainstorm and evaluate possible approaches before delegating. 🤖 OpenAI Chat Model Director (O3) → The Director’s brain, providing strategic-level thinking. ✅ Beginner-friendly benefit: This section is like the “command center.” Any LinkedIn content request starts here and gets transformed into a clear, strategic plan before moving to specialists. ✍️ Section 2 – Content Creation Specialists Nodes: ✍️ LinkedIn Copywriter → Creates viral hooks, compelling posts, and platform-friendly messaging. 🎓 Domain Expert → Ensures technical accuracy and industry authority in the post. 📝 Proofreader & Editor → Polishes content for grammar, tone, and style. Each agent connects to its own GPT-4.1-mini model for cost-efficient, specialized output. ✅ Beginner-friendly benefit: This section is like your content writing team—from drafting, to adding expertise, to polishing for professional LinkedIn standards. 🚀 Section 3 – Engagement & Optimization Specialists Nodes: 🚀 Engagement Strategist → Crafts hashtags, posting times, and audience growth strategies. 🎨 Visual Content Strategist → Designs carousels, infographics, and visual ideas. 📊 Content Performance Analyst → Tracks analytics, measures performance, and suggests improvements. Each of these also relies on GPT-4.1-mini, keeping cost low while delivering specialized insights. ✅ Beginner-friendly benefit: This section is like your growth & marketing team—they ensure your content doesn’t just look good but also performs well and reaches the right audience. 📊 Summary Table | Section | Key Nodes | Role | Beginner Benefit | | ---------------------------- | -------------------------------------- | -------------------- | --------------------------------------- | | 🟢 Entry & Strategy | Trigger, Director, Think, O3 Model | Strategy & planning | Turns your idea into a clear strategy | | ✍️ Content Creation | Copywriter, Domain Expert, Proofreader | Writing & refinement | Produces expert-level, polished content | | 🚀 Engagement & Optimization | Engagement, Visuals, Analytics | Growth & performance | Maximizes reach, visuals, and results | 🌟 Why This Workflow Rocks All-in-one content team** → Strategy + Writing + Optimization Low cost** → O3 only for strategy, GPT-4.1-mini for specialists Parallel agents** → Work simultaneously for faster results Scalable** → Reusable for any LinkedIn content need 👉 Even a beginner can use this workflow: just send a LinkedIn content idea (e.g., “Write a post on AI in finance”), and your AI team handles the rest—writing, polishing, visuals, and engagement tactics.

Who's it for Professionals and teams managing high email volumes who need automatic email triage and responses. What it does This workflow monitors your Outlook inbox and uses AI to classify emails into three urgency levels: Urgent, Important, or Not Important. It automatically generates personalized replies and organizes emails into folders. How it works New emails trigger AI classification based on urgency and deadlines. The system then generates an appropriate reply using GPT-4 and moves the email to the corresponding folder. Requirements Microsoft Outlook account with API access OpenAI API key (GPT-4 access) Three Outlook folders: URGENT, Important, Not Important Setup Connect your Outlook credentials, add your OpenAI API key to all Chat Model nodes, update folder IDs in the Move nodes, and customize the AI prompts to match your tone. Customization Adjust classification criteria, modify reply tone and style, add more categories, or integrate with other tools like Slack or CRM systems.