Workflow Templates

AI evaluation in n8n This is a template for n8n's evaluation feature. Evaluation is a technique for getting confidence that your AI workflow performs reliably, by running a test dataset containing different inputs through the workflow. By calculating a metric (score) for each input, you can see where the workflow is performing well and where it isn't. How it works This template shows how to calculate a workflow evaluation metric: text similarity, measured character-by-character. The workflow takes images of hand-written codes, extracts the code and compares it with the expected answer from the dataset. The images look like this: The workflow works as follows: We use an evaluation trigger to read in our dataset It is wired up in parallel with the regular trigger so that the workflow can be started from either one. More info We download the image and use AI to extract the code If we’re evaluating (i.e. the execution started from the evaluation trigger), we calculate the string distance metric We pass this information back to n8n as a metric

📰 This AI-powered agent performs real-time sentiment analysis on Tesla (TSLA) news to support trading decisions. It aggregates headlines from 5 trusted sources and uses DeepSeek Chat to classify sentiment and generate structured summaries. This tool is a critical sub-agent in the broader Tesla Quant Trading AI Agent system. ⚠️ Not standalone — this agent is designed to be executed by the Tesla Quant Trading AI Agent. ⚙️ Requires: DeepSeek Chat API Key 🔌 Workflow Role This tool processes Tesla-related news and produces output like: { "sentiment": "bullish", "summary": "Tesla stock rallied today after strong delivery numbers and Cybertruck updates. Analysts remain optimistic.", "topHeadlines": [ "Tesla beats Q2 delivery forecast – Yahoo Finance", "Cybertruck ramps up in Texas – Electrek", "Berlin Gigafactory expands battery production – CleanTechnica" ] } Its output feeds directly into the master trading agent’s final trade report. 📰 News Sources Used This agent collects real-time headlines from: Google News (filtered by “Tesla” or “TSLA”) Yahoo Finance (TSLA-specific feed) Electrek (Tesla archive) CleanTechnica (Tesla sustainability news) TeslaNorth (app/product release updates) These five tools are always queried together to ensure market-wide signal coverage. 🤖 What the Agent Does Pulls headlines from all 5 Tesla-specific RSS feeds Uses DeepSeek Chat to: Analyze narrative tone (bullish / bearish / neutral) Identify macro/financial drivers Generate a 2–3 sentence summary Return top 3–5 headlines Outputs structured JSON for downstream use 🛠️ Setup Instructions 1. Install & Name Import this file and name it: Tesla_News_and_Sentiment_Analyst_Tool 2. Add DeepSeek API Credentials Go to: Credentials → Add New → DeepSeek API Save as: DeepSeek account 3. Internet Access Required Ensure RSS feeds can fetch live headlines Works best with a cloud-hosted n8n instance or tunnel-enabled local install 4. Must Be Triggered by Parent Triggered via Execute Workflow by the Tesla Quant Trading AI Agent Requires these inputs: message: optional query context sessionId: passed to maintain short-term memory across executions 🧠 Agent Architecture | Node Name | Function | | ---------------------------------- | ------------------------------------------------ | | DeepSeek Chat Model | Performs AI-based sentiment analysis | | Tesla News and Sentiment Analyst | Combines results, formats output in strict JSON | | Simple Memory | Stores session-level context (short-term memory) | | 5x RSS nodes | Aggregate Tesla news from trusted media outlets | 📌 Sticky Notes Included 🟢 Trigger from Parent Workflow – Executed only by main TSLA agent 🟠 News Feeds Overview – Lists and explains each of the 5 feeds 🧠 DeepSeek Chat Notes – Describes LLM behavior and parsing role 🔵 Short-Term Memory – Buffers sentiment context during user session 📘 Sentiment Analyst Agent – Summarizes key responsibilities 📎 Licensing & Attribution © 2025 Treasurium Capital Limited Company This architecture, workflow structure, and prompt design are licensed for educational and operational use only. Commercial resale or rebranding prohibited without authorization. 🔗 Creator: Don Jayamaha 🔗 Templates: https://n8n.io/creators/don-the-gem-dealer/ 🚀 Power your TSLA trading with AI-driven sentiment—built with DeepSeek Chat and 5 trusted news sources. This tool is required by the Tesla Quant Trading AI Agent.

How it works: This workflow automates the entire LinkedIn content distribution process — from AI-powered post creation to auto-posting on both personal LinkedIn profiles and LinkedIn groups, using GPT-4o and Google Sheets as the content source and control panel. Auto-generates professional LinkedIn posts from spreadsheet topics using GPT-4o. Posts to your LinkedIn profile and multiple groups. Updates status to avoid duplicate posting. Fully customizable and reusable with your spreadsheet. Set up Steps Create and Upload the Spreadsheet Name it: Linkedin Post Sheet1 (for post topics): Columns: ID | Linkedin Post Title | Status Add post titles under Linkedin Post Title Set Status to Pending Create new sheet name as "Groups" (for group distribution): Column: GroupIds Add LinkedIn Group IDs, one per row Connect Google Sheets Nodes Connect your Google account to these nodes: Linkedin Post topic (Reads post topics) Get group id (Reads LinkedIn groups) Update Status (Writes back the status after posting) Configure GPT-4o (OpenAI) Add your OpenAI API key in the Linkedin Post creator node This node will generate high-quality content from your topic titles Connect LinkedIn Account Add your LinkedIn credentials in the Linkedin user detail node Ensure appropriate permissions to post on profile and groups Activate the Workflow : Once live, the workflow will: Monitor the Google Sheet for Pending posts. Generate content via GPT-4o. Post to: Your LinkedIn Profile Each LinkedIn Group listed in the Groups sheet Update the post Status to Posted Customization Tips Want to personalize this template? Change AI tone or style in the OpenAI node prompt Add a scheduler node if you'd like to post at fixed intervals Use a Slack or Telegram approval step before posting Integrate analytics tools to track post performance Suggested Sticky Notes for Workflow | Node or Section | Sticky Note Content | | ---------------------- | --------------------------------------------------------------------------- | | Linkedin Post topic | Reads the topic titles and statuses from Sheet1 | | OpenAI (GPT-4o) | Generates content using topic title — you can modify the tone/prompt here | | Linkedin user detail | Your personal LinkedIn credentials — required to post | | Group loop | Iterates through LinkedIn Group IDs and posts the content | | Update Status | Updates spreadsheet so the topic isn't re-posted |

This n8n template demonstrates how to calculate the evaluation metric "Relevance" which in this scenario, measures the relevance of the agent's response to the user's question. The scoring approach is adapted from the open-source evaluations project RAGAS and you can see the source here https://github.com/explodinggradients/ragas/blob/main/ragas/src/ragas/metrics/_answer_relevance.py How it works This evaluation works best for Q&A agents. For our scoring, we analyse the agent's response and ask another AI to generate a question from it. This generated question is then compared to the original question using cosine similarity. A high score indicates relevance and the agent's successful ability to answer the question whereas a low score means agent may have added too much irrelevant info, went off script or hallucinated. Requirements n8n version 1.94+ Check out this Google Sheet for a sample data https://docs.google.com/spreadsheets/d/1YOnu2JJjlxd787AuYcg-wKbkjyjyZFgASYVV0jsij5Y/edit?usp=sharing

🔧 How It Works Telegram Trigger – Listens for incoming messages from users via your Telegram bot. Watch Full Step-by-step Guide Video here: https://www.youtube.com/watch?v=GzWO7_1lyI8 AI Agent – Processes the message to determine the user's intent (booking or canceling) and extracts necessary details like date, time, and participant names. Google Calendar Node – Depending on the intent: Booking: Creates a new event in Google Calendar with the extracted details. Canceling: Searches for the specified event and deletes it from the calendar. Telegram Node – Sends a confirmation message back to the user, informing them of the successful booking or cancellation. 🧠 Why This is Useful Managing appointments can be time-consuming. This workflow automates the process, allowing users to schedule or cancel meetings effortlessly through a simple chat interface. It's ideal for: Solopreneurs managing their own schedules. Small businesses coordinating meetings with clients. Anyone looking to streamline their appointment management process. 🪜 Setup Instructions Set Up Telegram Bot: Create a new bot using BotFather on Telegram. Obtain the API token and set up the Telegram Trigger node in n8n with this token. OpenAI Platform API required for OpenAI Chat Model Connect to Google Calendar For the full video tutorial, watch here: https://youtu.be/GzWO7_1lyI8

PromptCraft AI – Telegram Image Generator 🚀 How It Works PromptCraft AI is an n8n automation that transforms simple image ideas sent through Telegram into stunning AI-generated images using OpenAI's DALL·E (or other image models). 🔁 Workflow Overview: Telegram Trigger: Listens for messages from a user on Telegram. Prompt Expansion: The message is transformed into a rich image description using GPT (OpenAI Chat Model). Image Generation: The prompt is passed to OpenAI's image API to generate a high-quality image. Send Image: The final image is sent back to the user on Telegram. (Optional) Log image titles and links to Google Drive and Google Sheets. ⚙️ Setup Instructions 📋 Prerequisites [ ] n8n installed (Self-hosted or via n8n.cloud) [ ] Telegram bot token (via @BotFather) [ ] OpenAI API key (platform.openai.com) [ ] Google Sheets & Drive OAuth2 credentials (optional) 🧠 Step-by-Step Configuration 1. 📥 Import the Workflow Go to n8n → click Import → upload PromptCraft_AI_Template.json 2. 🔐 Set Up Credentials In Credentials, add the following: Telegram API → Paste your bot token OpenAI API → Paste your OpenAI API key (Optional) Google Sheets OAuth2, Google Drive OAuth2 3. 🔄 Replace Placeholders Open each node that requires credentials: Replace REPLACE_OPENAI_API_KEY with your actual OpenAI API key Replace REPLACE_TELEGRAM_API_ID and credential names as needed (Optional) Update Google Drive Folder ID & Sheet ID in respective nodes 4. ✅ Activate the Workflow Turn on the Telegram Trigger node. Deploy and activate the full workflow. 5. ✉️ Test It Out Send your Telegram bot a message like: > a knight riding a robotic horse in the future Receive the generated image back in Telegram! 💡 Pro Tips Use detailed or imaginative inputs for better outputs. Fine-tune the GPT prompt for specific visual styles. Extend with Google Vision, image upscaling, or watermarking. 🛟 Support For setup assistance or custom feature requests, feel free to contact me @dimejicole21@gmail.com Happy Prompting! 🖼✨

🔍 What This Workflow Does This RAG Pipeline in n8n automates document ingestion from Google Drive, vectorizes it using OpenAI embeddings, stores it in Pinecone, and enables chat-based retrieval using LangChain agents. Main Functions: 📂 Auto-detects new files uploaded to a specific Google Drive folder. 🧠 Converts the file into embeddings using OpenAI. 📦 Stores them in a Pinecone vector database. 💬 Allows a user to query the knowledge base through a chat interface. 🤖 Uses a GPT-4o-mini model with LangChain to generate intelligent responses using retrieved context. ⚙️ Setup Instructions Connect Accounts Ensure these services are connected in n8n: ✅ Google Drive (OAuth2) ✅ OpenAI ✅ Pinecone You can do this in n8n > Credentials > New and use the matching names from the file: Google Drive: "Google Drive account 2" OpenAI: "OpenAi success" Pinecone: "PineconeApi account 2" Folder Setup Upload your documents to this folder in Google Drive: 📁 Power Folder The workflow is triggered every minute when a new file is uploaded. Workflow Overview A. File Ingestion Path Google Drive Trigger — detects new file. Google Drive (Download) — downloads the new file. Recursive Text Splitter — splits text into chunks. Default Data Loader — loads content as LangChain documents. OpenAI Embeddings — converts text chunks into embeddings. Pinecone Vector Store — stores them in "ragfile" index. B. Chat Retrieval Path When chat message received — AI Agent — LangChain agent managing tools. OpenAI Chat Model (GPT-4o-mini) — generates replies. Pinecone Vector Store (retrieval) — retrieves matching content. Embeddings OpenAI1 — helps match queries to document chunks.

Automate expense reviews with AI-powered CFO-level analysis. This workflow monitors Airtable expense submissions, uses GPT-4 to analyze expenses like an experienced CFO, flags suspicious expenses with detailed reasoning, and maintains comprehensive audit trails in Pinecone vector database. 🚀 What It Does Smart Monitoring**: Watches Airtable for new expense submissions AI CFO Analysis**: GPT-4 applies financial expertise to review amounts, categories, and descriptions Intelligent Flagging**: Automatically identifies policy violations and suspicious patterns Audit Trail**: Stores all decisions in Pinecone for compliance and searchability Auto Updates**: Updates Airtable records with AI decisions and detailed reasoning 🎯 Perfect For Finance teams needing intelligent expense oversight CFOs wanting to automate expense policy enforcement Growing companies scaling expense management Businesses requiring compliance documentation ⚙️ Key Benefits ✅ 99% faster expense processing vs manual review ✅ CFO-level intelligence applied to every expense ✅ Complete audit trail for compliance ✅ Real-time fraud detection and policy enforcement ✅ Detailed explanations for every decision 🔧 What You Need Airtable base with expense data (template included) OpenAI API for GPT-4 analysis Pinecone account for audit trail storage Basic expense submission process 📊 Sample Results Input: $4,500 business class flight to Tokyo AI Decision: "Flagged - Amount exceeds typical travel thresholds. Requires verification against travel policies and client justification for premium travel." 🛠️ Setup & Support Quick Setup: Deploy in 60 minutes with included templates and documentation YouTube: https://www.youtube.com/@YaronBeen/videos 💼 Expert Support LinkedIn: https://www.linkedin.com/in/yaronbeen/ 📧 Direct Help Email: Yaron@nofluff.online Transform expense management from manual bottleneck to intelligent automation. Let AI handle policy compliance while your finance team focuses on strategy.

A medium-term trend analyzer for the Binance Spot Market that leverages core technical indicators across 4-hour candle data to provide human-readable swing-trade signals via AI. 🎥 Watch Tutorial: 🎯 What It Does Accepts a Binance trading pair (e.g., AVAXUSDT) Sends the symbol to an internal webhook for technical indicator calculation Computes 4h RSI, MACD, Bollinger Bands, SMA, EMA, ADX Returns structured, GPT-analyzed signals ready for Telegram delivery 🧠 AI Agent Details Model:** GPT-4.1-mini (OpenAI Chat) Agent Role:** Translates raw indicator values into sentiment-labeled signals Memory:** Tracks session + symbol context for cleaner multi-turn logic 🔗 Required Backend Workflow To calculate indicators, this tool depends on: POST https://treasurium.app.n8n.cloud/webhook/4h-indicators { "symbol": "AVAXUSDT" } Returns a JSON object with the latest 40×4h candle-based calculations. 📥 Input Format { "message": "AVAXUSDT", "sessionId": "telegram_chat_id" } 📊 Sample Output 🕓 4h Technical Signals – AVAXUSDT • RSI: 64 → Slightly Bullish • MACD: Bullish Cross above baseline • BB: Upper band touch – volatility expanding • EMA > SMA → Confirmed Upside Momentum • ADX: 31 → Strengthening Trend 📚 Use Case Scenarios | Use Case | Result | | ----------------------------- | ---------------------------------------------------- | | Swing trend confirmation | Uses 4h indicators to validate or reject setups | | Breakout signal confluence | Helps assess if momentum is real or noise | | Inputs to Quant AI or Analyst | Supports higher-frame trade recommendation synthesis | 🛠️ Setup Instructions Import the JSON template into your n8n workspace. Set your OpenAI API credentials for the GPT node. Ensure the /webhook/4h-indicators backend tool is live and accessible. Connect this to your Binance Financial Analyst Tool or master Quant AI orchestrator. 🤖 Parent Workflows That Use This Tool Binance SM Financial Analyst Tool Binance Spot Market Quant AI Agent 📎 Sticky Notes & Annotations This workflow includes internal sticky notes describing: Node roles (GPT, webhook, memory) System behavior (reasoning agent logic) Telegram formatting guidance 🔐 Licensing & Attribution © 2025 Treasurium Capital Limited Company All architecture, prompt logic, and signal formatting are proprietary. Redistribution or rebranding is prohibited. 🔗 Connect with the creator: Don Jayamaha – LinkedIn

🚀 How it works (Fonctionnement résumé) : Ce template permet de transformer un document (PDF, TXT, DocX...) en post LinkedIn engageant, prêt à être publié ou validé par email, le tout avec l’aide d’une IA spécialisée en copywriting LinkedIn. Voici les étapes clés : Formulaire de dépôt : L'utilisateur charge un fichier ou colle un texte. Détection du type de contenu : Un Switch analyse le type de fichier (PDF, DOCX, TXT, ou texte brut). Attention pour DocX nécessite un compte Make pour transformer le doc (mais cela fonctionne aussi sans docX) Extraction du contenu : Selon le format, le bon module d'extraction est utilisé. Génération d’un post LinkedIn : L'IA transforme le contenu en post LinkedIn selon une méthodologie de copywriting optimisée. Validation par email : Un email est envoyé à l’utilisateur pour approbation avec possibilité d’ajouter une image. Publication automatique : Si l'utilisateur valide, le post est publié sur LinkedIn. ⚙️ Setup Steps : Connecte tes comptes : Google Docs OAuth LinkedIn OAuth OpenAI (via gpt-4.1-mini ou un autre modèle) SMTP + IMAP pour l'envoi et la lecture d'emails Configure les champs du formulaire dans le nœud Form Trigger selon ton usage. Personnalise le prompt IA dans le nœud AI Agent si tu veux adapter le ton ou la méthodologie. Vérifie les emails dans le nœud d'envoi (Send Email) et de lecture (Email Trigger (IMAP)), pour que la validation fonctionne. Teste le workflow avec différents fichiers pour t'assurer que tous les types sont bien traités (PDF, DOCX, TXT, etc.). 🧩 Cas d’usage typiques : Créer des posts à partir de notes de réunion ou de rapports. Valoriser un article ou une publication professionnelle sous forme de contenu LinkedIn. Déléguer à l'IA le premier jet de ton contenu réseau. Bonus surveille une newsletter de ta messagerie pour proposer un post pertinent sur LinkedIn (vous pouvez supprimer il fonctionne en parallèle)

Try It Out! This n8n template creates a fully automated Instagram content schedule using AI and Google Sheets. It is perfect for content creators, marketing teams, or local businesses looking to organize and scale their social media posting. How it works The workflow starts by reading two sets of inputs from a Google Sheet: Your content strategy inputs (Pillar, Objective, Frequency, Format, Structure, Examples). A list of scraped blog posts with title, URL, and description (fetched from your website). Blog posts are scraped using Apify and parsed to extract key fields, which are stored in a tab labeled "Input (blog month)". You can assign a preferred posting month for each blog (e.g. fall blog posts get tagged for September). The workflow then merges both inputs and extracts the relevant information for further information added by ChatGPT. AI Scheduling & Personalization Once merged, the workflow loops through each content item and: Identifies if the scheduled post falls on or near a holiday (like Mother’s Day) and adjusts the content accordingly. A reference tool is attached to guide structure and tone, based on a library of post examples. Sends the content to an AI Agent (using GPT-4, but customizable) that generates: A compelling Instagram caption A visual description Hashtags Suggested post date, day, content pillar, and format (carousel, reel, image, etc.) Output All generated content including captions, structure, dates, hashtags, and pillar is exported into a tab titled Output in your Google Sheet. The final schedule is ready for manual review, editing, or publishing to social media. How to use The workflow uses a manual trigger to start, but you can replace it with a Webhook, cron job, or form submission. Add/edit your content strategy in Google Sheets. How to Set-Up Initial Input Tab Define your content pillars and structure Create a tab named "Input" or "Strategy" Include these columns: Pillar: e.g., Family images Objective: e.g., Showcase images Frequency: e.g., Bi-weekly Content Form: e.g., Images, Reels Structure: brief description of expected layout (e.g., carousel Q&A, singular photo) Examples: prompts or questions to guide AI (e.g., Why do you think families should do a session?) Input (blog month) Tab – Store scraped blog content Include these columns: URL: direct link to blog post Title: blog post title Description: short summary of the post Preferred Month: month you want it posted (e.g., August, September) This sheet is partially auto-filled by the workflow (except for Preferred Month) Output Tab – Final scheduled content Include these columns: Date: scheduled posting date (YYYY-MM-DD) Day: day of the week Pillar: content category assigned Format: e.g., Images, Reels, Carousel Description: visual summary Caption: Instagram-ready caption Hashtags: complete hashtag block To use the Apify HTTP Request node: Drag in an HTTP Request node into your n8n workflow. Set the Method and URL based on how you're using Apify: Use POST if you want to run an actor live with dynamic input (e.g. scrape blog posts in real time). Use GET if you want to retrieve results from a completed or static dataset run (faster and cheaper if you're reusing previous data). Configure query or body parameters: Include your Apify API token for authentication (e.g. token=YOUR_API_KEY) For POST: include an input object with any required actor settings (e.g., blog URL to scrape). For GET: specify the dataset ID in the URL Test the node to ensure you're retrieving the blog titles, descriptions, and URLs as expected. Requirements Apify account for scraping blog posts OpenAI key (e.g. GPT-4) or another model of your choice Google Sheets Credentials Example Use Cases A photographer repurposing blogs into Instagram carousels A nonprofit automatically generating seasonal posts A small team managing multi-pillar content across weeks or months Need Help? Join the n8n Discord or ask in the n8n Forum! Happy Content Making ! 📅✨

Automate document translation and ensure translation accuracy using Straker Verify, Google Drive and Slack. **How it works?
** A workflow step is set up to "watch" a Google Drive folder. When your team members place new files in this folder, they are downloaded. Straker Verify then translates them and provides a quality score. Once Straker Verify has completed this, the job info is fetched, the translation is saved to an output folder and you are notified via Slack. What problem does this solve? When using AI to translate documents, you have no idea about the quality and accuracy of the output. This template answers the question “How good is my translation?” so you have a high level of confidence before you publish. Who is this for? This workflow template is designed for businesses needing translation and localization of documents such as text docs, presentations, web pages, transcripts, video subtitles and others. Use it to build workflows that localize your content at scale while maintaining translation quality, accuracy and compliance. Set up instructions Straker Verify Integration with n8n **Connect to Straker Verify: Obtain Your API Key Sign Up/Log In:** Visit https://verify.straker.ai/ to create an account or log in. Navigate to API Keys: Go to `Verify → Settings → API Keys. Copy Your Key: Find and copy your API key. Add Key to n8n: In n8n, go to Settings → Credentials → Straker Verify. Set Up Credentials for the Straker Verify Node Open n8n and go to "Credentials". From the left sidebar, click on "Credentials". Search for "Straker Verify" and select "Straker Verify API" from the dropdown. Paste the copied access token from the Verify app and save it. Assign Credentials to the Node 1.Go to your workflow and open the Straker Verify node. 2.Select the "Straker Verify API" credentials you just created from the dropdown (Credentials to connect with), and save. ✅ You are now ready to use the workflow. Workflow Steps Step 1: Initiate Workflow – Upload Files to Google Drive 1.Upload one or more files to the designated Google Drive folder. This triggers the "New File in Google Drive" node in n8n. Step 2: Verify Token Balance The workflow checks your token balance via: Get Current User Balance User Has Enough Tokens Not enough tokens? You will receive a Slack message: Not enough tokens Please top up and re-upload your files. Step 3: Select Workflow The system fetches available workflows via: Fetch All Users Workflows No matching workflow found? You'll be notified via Slack: No workflow found Step 4: Create Project in Straker Verify The following steps are handled automatically: Fetch language/project options Download files from Google Drive Create a new project using: Create Straker Project ✅ You'll receive a Slack confirmation: > "Project created – ID: xxxxxx" Step 5: Process Completion & File Return Once files are processed by Straker: The Incoming Translation Result webhook is triggered. The workflow: Downloads processed files: Get File Content from Strakerh - Uploads them to Google Drive: Upload File to Google Drivee Step 6: Confirmation - Workflow Complete You'll receive a final Slack message: > "Workflow complete – Files are now available in Google Drive"