Workflow Templates

Generate Invoices and Send Reminders for Customers with Jotform and Xero This workflow automates the entire process of receiving a product/service order, checking or creating a customer in Xero, generating an invoice, emailing it — all triggered by a form submission (via Jotform), and sending invoice reminders. How It Works Receive Submission Triggered when a user submits a form. Collects data like customer details, selected product/service, etc. Create/Update The Customer Creates/Updates the customer. Create The Invoice Generates a new invoice for the customer using the item selected. Send The Invoice Automatically sends the invoice via email to the customer. Store The Invoice In DB Stores the needed invoice details in the DB. Send Reminders Every day at 8 AM, the automation checks each invoice to decide whether to: send a reminder email, skip and send it later, or delete the invoice from the DB (if it's paid or all reminders have been sent). Who Can Benefit from This Workflow? Freelancers** Service Providers** Consultants & Coaches** Small Businesses** E-commerce or Custom Product Sellers** Requirements Jotform webhook setup, more info here Xero credentials, more info here Make sure that products/services values in Jotform are exactly the same as your item Code in your Xero account Email setup, update email nodes (Send email & Send reminder email & Send reminders sent summary) Create data table with the following columns: invoiceId (string) remainingAmount (number) currency (string) remindersSent (number) lastSentAt (date time) Update Add reminders config node so update the data table id and intervals in days (default is after 2 days, then after 3 days and finally after 5 days ) LLM model credentials

Revenue Growth Strategy with CRO-led Multi-Agent Team using O3 & GPT-4.1-mini 🔥 Powered by OpenAI O3 & GPT-4.1-mini Multi-Agent System \#RevOps #n8nWorkflows #AIRevenue #OpenAI #GrowthHacking ⚡ Section 1: Start & Orchestrator 💬 Chat Trigger* → Listens for revenue-related requests (e.g., *“Optimize our sales funnel”). 🤖 CRO Agent (O3)* → Acts as the *Chief Revenue Officer**. Thinks strategically with the Think Node. Decides which specialist agents to call. 🧠 OpenAI O3 Model** → Provides advanced reasoning for CRO decisions. Benefit: Central orchestration ensures every request gets a strategic, executive-level response before delegation. 🛠️ Section 2: Specialist Agents Each specialist agent uses GPT-4.1-mini for fast, cost-effective execution. They receive the CRO’s instructions and return insights. 📈 Sales Pipeline Analyst Funnel optimization, conversion tracking, bottleneck fixes. Outputs: Pipeline health, drop-off points, recommendations. 🎯 Revenue Attribution Specialist Multi-touch attribution, ROI analysis, campaign efficiency. Outputs: Attribution models, marketing ROI. 📊 Revenue Forecasting Analyst Predictive modeling, scenario planning, growth projections. Outputs: Forecast reports, “what-if” scenarios. ⚙️ Revenue Operations Manager CRM optimization, territory planning, sales automation. Outputs: Process improvements, efficiency boosts. 💰 Pricing & Packaging Strategist Competitive pricing analysis, packaging strategy, revenue optimization. Outputs: Price models, package recommendations. 🧠 Revenue Intelligence Analyst BI dashboards, performance tracking, KPI insights. Outputs: Reports with actionable intelligence. Benefit: Breaks complex revenue problems into specialized tasks handled by domain experts. 🔄 Section 3: Feedback & Integration Each agent → sends results back to CRO Agent. CRO Agent → compiles a comprehensive revenue strategy. Can integrate with CRM, BI dashboards, or Slack/Email for delivery. Benefit: Clear, actionable insights delivered in one place — like having a virtual RevOps team on demand. 📊 Workflow Overview | Section | Key Nodes | Purpose | Benefit | | ----------------------- | ----------------------------------- | ------------------------------------------------- | ------------------------------------ | | ⚡ Start & Orchestration | Chat Trigger, CRO Agent, O3 Model | Capture request & assign to CRO | Centralized leadership | | 🛠️ Specialists | 6 Agent Nodes + GPT-4.1-mini models | Analyze pipeline, pricing, ops, attribution, etc. | Specialized, cost-efficient insights | | 🔄 Feedback Loop | CRO Agent aggregation | Compiles strategy from multiple agents | Unified, data-driven revenue plan | 💡 Use Cases Pipeline Optimization** → Identify bottlenecks, improve conversions. Attribution Modeling** → Know exactly where revenue comes from. Revenue Forecasting** → Plan growth scenarios and projections. Ops Excellence** → Automate CRM, streamline sales ops. Pricing Strategy** → Compete smarter with optimized pricing models. Revenue Intelligence** → Ongoing tracking and performance monitoring. 💸 Cost Optimization O3 only for CRO decisions** → Strategic layer. GPT-4.1-mini for specialists** → Low-cost execution (\~90% cheaper). Parallel processing** → All agents can run simultaneously. ✅ Final Result: A virtual AI-powered RevOps team that turns any revenue-related question into a comprehensive growth strategy — instantly.

Adaptive LLM Router for Optimized AI Chat Responses Elevate your AI chatbots with intelligent model selection: automatically route simple queries to cost-effective LLMs and complex ones to powerful ones, balancing performance and expenses seamlessly. What It Does This workflow listens for chat messages, uses a lightweight Gemini model to classify query complexity, then selects and routes to the optimal LLM (Gemini 2.5 Pro for complex, OpenAI GPT-4.1 Nano for simple) to generate responses—ensuring efficient resource use. Key Features Complexity Classifier** - Quick assessment using Gemini 2.0 Flash Dynamic Model Switching** - Routes to premium or budget models based on needs Chat Trigger** - Webhook-based for real-time conversations Current Date Awareness** - Injects $now into system prompt Modular Design** - Easy to add more models or adjust rules Cost Optimization** - Reserves heavy models for demanding tasks only Perfect For Chatbot Developers**: Build responsive, cost-aware AI assistants Customer Support**: Handle routine vs. technical queries efficiently Educational Tools**: Simple facts vs. in-depth explanations Content Creators**: Quick ideas vs. detailed writing assistance Researchers**: Basic lookups vs. complex analysis Business Apps**: Optimize API costs in production environments Technical Highlights Harnessing n8n's LangChain nodes, this workflow demonstrates: Webhook triggers for instant chat handling Agent-based classification with strict output rules Conditional model selection for AI chains Integration of multiple LLM providers (Google Gemini, OpenAI) Scalable architecture for expanding model options Ideal for minimizing AI costs while maximizing response quality. No coding required—import, configure credentials, and deploy!

Template presentation This template generates a sales follow-up presentation in Google Slides after a sales call recorded in Claap. The workflow is simplified to showcase the main use case. You can customize and enrich this workflow by connecting to the CRM, researching data online or adding more files in the presentation. The presentation template used in this workflow is available here. Workflow configuration Create a webhook in Claap, by following this article. Edit the labels that trigger the workflow and route on the relevant presentation. Fill your Open AI credentials by creating an API Key in OpenAI Platform Edit the presentation personalization details (user set as editor, content, title) Fill your Slack credentials by following steps in this video.

Build a powerful AI chatbot that provides precise answers from your own company's knowledge base. This template provides a smart AI agent that connects to Lookio, a platform where you can easily upload your documents (from Notion, Jira, Slack, etc.) to create a dedicated knowledge source. What makes this agent "smart" is its efficiency. It's configured to handle simple greetings and small talk on its own, only using its powerful (and paid) knowledge retrieval tool when a user asks a genuine question. This cost-saving logic makes it perfect for building production-ready internal helpdesks, customer support bots, or any application where you need accurate, source-based answers. Who is this for? Customer support teams:** Build internal bots that help agents find answers instantly from your support documentation and knowledge bases. Product & engineering teams:** Create a chatbot that can answer technical questions based on your product documentation or internal wikis. HR departments:** Deploy an internal assistant that can answer employee questions based on company handbooks, policies, and procedures. Any business with a knowledge base:** Provide an interactive, conversational way for employees or customers to access information locked away in your documents. What problem does this solve? Provides accurate, grounded answers:** Ensures the AI agent's responses are based on your trusted, private documents, not the open internet, which prevents factual errors and "hallucinations." Makes your knowledge accessible:** Transforms your static documents and knowledge bases into an interactive, 24/7 conversational resource. Optimizes for cost and efficiency:** The agent is intelligent enough to handle simple small talk without making unnecessary API calls to your knowledge base, saving you credits and money. Simplifies RAG setup:** Provides a ready-to-use template for a common RAG (Retrieval-Augmented Generation) pattern, with the complexities of document management and retrieval handled by the Lookio platform. How it works First, build your knowledge base in Lookio: The process starts on the Lookio platform. You upload your documents (from Notion, Jira, PDFs, etc.) and create an "assistant" which becomes your secure, queryable knowledge base. A user asks a question: The n8n workflow begins when a user sends a message via the Chat Trigger. The agent makes a decision: The AI Knowledge Agent, guided by its system prompt, analyzes the user's message. If it's a simple greeting like "hi," it will respond directly. If it's a substantive question that requires specific knowledge, it decides to use its "Query knowledge base" tool. Query the Lookio knowledge base: The agent passes the user's question to the HTTP Request Tool. This tool securely calls the Lookio API with your specific Assistant ID and API key. Deliver the fact-based answer: Lookio searches your documents, synthesizes a precise answer, and sends it back to the workflow. The n8n agent then presents this answer to the user in the chat interface. Architectural Approaches to RAG in n8n with Lookio From a workflow perspective, integrating RAG natively in n8n involves orchestrating multiple nodes for data handling, embedding, and vector searches. This method provides high visibility and control over each step. An alternative architectural pattern is to use an external RAG service like Lookio, which consolidates these steps into a single HTTP Request node. This simplifies the workflow's structure by abstracting the multi-stage RAG process into one API endpoint. Setup Set up your Lookio assistant (Prerequisite): First, go to Lookio, sign up (you get 50 free credits), create an assistant with your documents, and from your settings, copy your API Key and Assistant ID. Configure the Lookio tool: In the Query knowledge base (HTTP Request Tool) node: Replace the <your-assistant-id> placeholder with your actual Assistant ID. Replace the <your-lookio-api-key> placeholder with your actual API Key. Connect your AI model: In the OpenAI Chat Model node, connect your AI provider credentials. Activate the workflow. Your smart knowledge base agent is now live and ready to chat! Taking it further Adjust retrieval quality:* In the *Query knowledge base** node, you can change the query_mode from flash (fastest) to deep for higher quality but slightly slower answers, depending on your needs. Add more tools:** Enhance your agent by giving it other tools, like a web search for when the internal knowledge base doesn't have an answer, or a calculator for performing computations. Deploy it anywhere:* Swap the *Chat Trigger* for a *Slack* or *Discord** trigger to deploy your agent right where your team works.

Overview Create hyper-personalized cold outreach messages at scale by combining Google Sheets, web scraping, and AI. This workflow is perfect for sales teams, SDRs, and agency owners looking to boost reply rates with icebreakers that actually feel personal. It takes lead info from a Google Sheet—including name, email, company, and website—then visits each site, pulls meaningful text, and crafts a tailored message using AI. The personalized message is then written back into your lead sheet, ready for use in cold email, LinkedIn DMs, or CRM enrichment. Who’s it for Cold email outreach specialists B2B sales and SDR teams Lead generation agencies Founders doing outbound manually How it works Pull lead data from Google Sheets Loop through each lead and scrape their website using an HTTP node Clean and format the website content Use OpenAI to generate a custom-written icebreaker for each lead Write the final icebreaker back into the spreadsheet How to set up Connect your Google Sheets account Replace the spreadsheet ID and column names with your own Set up your OpenAI credentials (or whichever LLM you prefer) Tweak the prompt for tone or style Hit "Execute Workflow" and watch the sheet populate Requirements Google Sheets credentials OpenAI (or any compatible LLM node) The websites listed must be publicly accessible and static How to customize Modify the scraping logic to focus on specific sections (e.g. About page, Case Studies) Adjust the AI prompt to match your brand’s tone Add filtering logic to skip low-value leads Integrate with your CRM to send the data downstream

This n8n is a daily analytics automation that calculates which lead sources generate actual revenue, not just leads. Provides ROI data, conversion rates, and budget allocation recommendations. Use Case: automates marketing ROI tracking by linking closed deals to their lead sources in Airtable, calculating revenue and ROI per channel, and sending daily insights to Slack. What It Does Runs nightly to analyze closed deals from last 30 days Matches deals to their original lead sources Calculates total revenue per source Computes ROI (revenue vs. cost per lead) Determines conversion rates by source Updates Lead Sources table with metrics Sends weekly reports to team How It Works Step 1: Schedule Trigger Runs daily at midnight Step 2: Fetch Closed Won Deals Gets all deals where: Stage = "Closed Won" Actual Close Date in last 30 days Step 3: Fetch Lead Sources Gets cost and lead count data from Lead Sources table Step 4: Calculate ROI (JavaScript) For each source: Total revenue = Sum of all deals from that source Total cost = Cost per lead × Total leads ROI = ((Revenue - Cost) / Cost) × 100 Conversion rate = Deals closed / Total leads × 100 Average deal size = Revenue / Deal count Step 5: Update Lead Sources Writes calculated metrics back to Airtable Step 6: Send Report Slack message with top 3 performing sources Business Impact Marketing ROI:** Know exactly which channels generate revenue Budget optimization:** Allocate spend to highest-ROI sources Data-driven decisions:** Stop guessing, start knowing Cost reduction:** Cut low-performing channels Revenue growth:** Double down on what works Technical Requirements n8n (self-hosted or cloud) Airtable (uses existing tables) Slack (for reports) Gmail for reminder incase CEO missed the report in the Slack channel (optional)

Supercharge your sales and marketing efforts with this powerful automation that transforms a list of LinkedIn profiles into a fully enriched, personalized outreach campaign. This workflow is designed for sales teams, growth marketers, and business development professionals looking to scale their lead generation without sacrificing personalization. It seamlessly integrates LinkedIn scraping, email enrichment with Hunter.io, AI-powered message generation with OpenAI, and data organization in Google Sheets. How It Works Start with Leads: The workflow begins with a list of target LinkedIn profile URLs. Scrape Profile Data: It automatically scrapes each LinkedIn profile to extract key professional information such as name, title, company, and location. A built-in delay helps manage rate limits. Find Verified Emails: Using the scraped company and name, the workflow queries ==Hunter.io to find a verified work email address== for the lead. AI-Powered Personalization: If an email is found, the lead's data is sent to OpenAI (GPT-4), which generates a highly personalized, conversational outreach message based on their role, company, and your value proposition. Sync to CRM/Sheet: Finally, all the enriched data—including the custom AI message—is neatly organized and saved as a new row in your designated Google Sheet. Stop wasting hours on manual lead research and generic outreach. Implement this automated workflow to focus on building relationships and closing deals.

Description: Stay on top of your support pipeline with this Ticket Status Digest automation for Zendesk. Built in n8n, this workflow automatically fetches tickets from Zendesk, filters only open ones, enriches them with requester details, and saves them into Google Sheets. 📊 Instead of manually checking Zendesk, you get a real-time digest of pending tickets with full customer details—perfect for support leads who need a quick snapshot of unresolved cases. Whether you’re tracking team workload, prioritizing open issues, or preparing daily status reports, this automation ensures your support data is always structured, centralized, and up to date. 🚀 What This Template Does (Step-by-Step) 🔔 Trigger – Manual Start (or Schedule) Begin workflow with a manual trigger (ideal for testing). Can be switched to scheduled runs (daily, hourly) for automated digests. 🎫 Fetch All Tickets (Zendesk) Pulls all tickets from Zendesk API. Captures ticket ID, subject, description, status, priority, tags, and timestamps. 🔍 Filter Open Tickets Only Includes only tickets where status = open. Skips closed, solved, or pending tickets. 👤 User Information Enrichment Looks up requester details (name, email, organization). Converts raw IDs into human-readable contact info. 📊 Save to Google Sheets Appends/updates ticket rows in “Ticket status dummy → Sheet1”. Columns: Ticket No. | Description | Status | Owner | Email | Tag. Required Integrations: Zendesk API (OAuth or API Key) Google Sheets (OAuth2 credentials) Best For: 🧑‍💼 Support leads monitoring unresolved tickets 📈 Managers building daily ticket status dashboards 🤝 Teams that need centralized visibility of customer issues ⏱️ Anyone tired of manual Zendesk data exports Key Benefits: ✅ Automated ticket sync to Google Sheets ✅ Real-time visibility of open issues ✅ Centralized view with enriched requester details ✅ Reduces manual tracking and reporting ✅ Scalable for daily, weekly, or custom digest runs

Overview This workflow automates static security analysis for JavaScript, PHP, and Python codebases. It’s designed for bug bounty hunters and security researchers who need fast, structured, and AI-assisted vulnerability detection across multiple sources. Features 🤖 AI-Powered Analysis: Specialized agents for each language: AI JavaScript Expert AI PHP Expert AI Python Expert Each agent detects only exploitable vulnerabilities (AST + regex heuristics). Returns strict JSON with: { "results": [ { "url": "file or URL", "code": "lines + snippet", "severity": "medium|high|critical", "vuln": "vulnerability type" } ] } 🧩 Post-Processing: Cleans, formats, and validates JSON results. Generates HTML tables with clear styling for quick visualization. Output ✅ JSON vulnerability reports per file. 📊 HTML table summaries grouped by language and severity. Usage Import the workflow into n8n. Configure credentials: OpenAI API key GitHub API Key Google Drive API Key Run via the provided webhook form. Select analysis mode and input target. View structured vulnerability reports directly in n8n or Google Drive. Notes Performs static analysis only (no code execution). Detects exploitable findings only; ignores low-impact issues.

Automatically Assign Jira Service Management Reporter from Forwarded Emails This workflow solves a common problem in Jira Service Management: when an email is forwarded to create a ticket, Jira often sets the forwarding system (e.g., support@yourcompany.com) as the reporter, not the original customer. This template automates the process of parsing the original sender's details from the email body and correctly assigning them as the ticket's reporter. If the customer doesn't exist in Jira, a new customer profile is created automatically before the ticket is assigned. What it Does Triggers on New Issue: The workflow starts when a new issue is created in a specified Jira project. Filters Forwarded Emails: An If node checks if the issue was created by one of your internal forwarding email addresses. The workflow only proceeds for these specific issues. Parses Details: A Code node uses regular expressions to parse the issue description (the forwarded email's body) and extract the original sender's name and email address. Searches for Existing Customer: An HTTP Request node checks if a customer with the extracted email already exists in your Jira Service Desk. Creates New Customer: If the customer is not found, another HTTP Request node creates a new customer profile in Jira Service Management. Assigns Reporter: Finally, a Jira node updates the issue's "Reporter" field to the existing or newly created customer, ensuring the ticket is correctly associated with the original sender. Use Cases Shared Support Inboxes**: Automatically process emails sent to a general support inbox (e.g., support@company.com) that are then forwarded to Jira. Departmental Forwarding**: Handle tickets forwarded from specific departments (e.g., sales@company.com or billing@company.com) and assign the original sender correctly. Personal Email Forwarding**: Useful when a team member forwards a customer email from their personal inbox to the Jira Service Management-connected address. Customization The Parse Details From Description node uses a regular expression (regex) to find the sender's email. The default regex is designed for standard forwarded emails that look like this: From: John Doe <john.doe@example.com> If your email client forwards emails in a different format, you may need to adjust the regex in the Code node. For example, if your format is From: [john.doe@example.com], you would need to update the regex pattern to match this structure. Troubleshooting Reporter Not Being Updated**: Verify that the forwarding email addresses in the Filter Forwarding Emails node are correct. Check the body of the Jira ticket's description to ensure the forwarded email content is present and in a format the regex can parse. Customer Not Found/Created**: Ensure your Jira API credentials have the necessary permissions to search for and create customers in Jira Service Management. Workflow Not Triggering**: Confirm that the Jira Trigger is correctly configured for the right project and that the webhook is active in your Jira instance. Requirements An n8n instance (self-hosted or cloud). Jira Software Cloud API credentials with Service Management permissions. How to Set Up Connect Credentials: In the Jira Trigger, Jira, and HTTP Request nodes, select your Jira Software Cloud API credentials. Configure Trigger: In the Jira Trigger node, select the Jira project you want this workflow to monitor. Set Filter Emails: In the Filter Forwarding Emails (If) node, replace the placeholder email addresses with the internal email addresses that forward mail to Jira. Update Jira Domain: In both HTTP Request nodes (Search for Existing Customer and Create Customer), replace the YOUR_JIRA_DOMAIN placeholder with your actual Atlassian domain (e.g., my-company.atlassian.net). Activate Workflow: Save and activate the workflow.

Multi-Agent Cold Email Campaign Generator with O3 Director & GPT-4.1 Specialists 🌍 Overview This workflow simulates a virtual sales & marketing team where each AI agent has a role: A Director Agent (O3) who manages strategy. Multiple Specialist Agents (GPT-4.1-mini) for research, writing, personalization, deliverability, sequencing, and analytics. Everything is triggered automatically when a new chat message request comes in. 🟢 Section 1: Entry & Director 🔗 Nodes: 1️⃣ When chat message received (Trigger) 💬 Starts the workflow when a new request arrives (e.g., “Create a cold email campaign for SaaS CTOs”). 2️⃣ Outreach Director Agent (O3 model) 🎯 The “manager” agent. Decides what kind of campaign is needed and assigns tasks. 3️⃣ Think (Planning Node) 🧠 Helps the Director structure thoughts before delegating. 💡 Why useful? Director uses O3 (strong reasoning model) only where strategy is needed → reduces cost. Provides a single point of control to coordinate all other agents. 🔵 Section 2: Specialist Agents Each is powered by GPT-4.1-mini (cheaper + faster). 🔍 Prospect Research Specialist → researches target companies, roles, pain points. ✍️ Cold Email Copywriter → drafts subject lines, hooks, and persuasive body copy. 🎯 Personalization Specialist → inserts custom variables for each recipient. 📅 Email Sequence Strategist → designs follow-ups, timing, nurture flows. 📬 Email Deliverability Expert → ensures emails land in inbox, not spam. 📊 Outreach Analytics Specialist → tracks performance, runs A/B tests, optimizes campaigns. 💡 Why useful? Each agent is a specialist → just like a real marketing team. Parallel execution** in n8n means faster results. Modular → you can remove or add more specialists. 🟣 Section 3: Execution Flow Request comes in via chat trigger Director (O3) interprets and delegates → calls specialists as tools Specialists generate their pieces (research → copy → personalization → sequence → deliverability → analytics) Director integrates results into a cohesive cold email campaign 🟡 Section 4: Documentation & Notes There are two Sticky Notes inside the workflow: Header Note** → Support info + tutorials (YouTube & LinkedIn by Yaron Been) Main Note** → Full documentation (overview, use cases, cost optimization, tags) 📊 Final Overview | Section | What Happens | Why It’s Useful | | -------------- | ------------------------ | --------------------------- | | 🟢 Director | Trigger + O3 strategy | Ensures smart coordination | | 🔵 Specialists | GPT-4.1-mini agents | Faster, cheaper execution | | 🟣 Flow | Delegation + Integration | Automated campaign building | | 🟡 Docs | Sticky Notes | In-workflow guide for users | 🚀 Benefits ✅ AI-powered cold email team without hiring humans ✅ Cost-optimized (O3 only for strategy, GPT-4.1-mini for tasks → \~90% cheaper) ✅ End-to-end coverage (research → writing → personalization → sequencing → analytics) ✅ Scalable: can run multiple campaigns in parallel ✅ Customizable: swap models, add tools, or expand team