Workflow Templates

This n8n template uses AI to automatically classify incoming Gmail messages into five categories and route them to the right people or departments. It can also reply automatically and send WhatsApp alerts for urgent or relevant messages. This helps ensure high-priority emails never get missed, while other messages are handled efficiently. ##How It Works Trigger A new email in Gmail triggers the workflow. Classification (OpenAI GPT) The email is analyzed by an OpenAI GPT model and classified into one of: High Priority Customer Support Promotion Finance/Billing Random/Other Conditional Logic & Actions High Priority → Create draft reply + send WhatsApp alert. Customer Support → Auto-reply + send WhatsApp confirmation alert. Promotion → Summarize email + send WhatsApp promotional alert. Finance/Billing → Forward to finance team + send WhatsApp finance alert. Random/Other → Label and log only. Multi-Channel Output Responses are sent via Gmail. Alerts are sent via WhatsApp (or another compatible API). ##Setup Instructions Step 1: Gmail Authorization Add a Gmail node in n8n. Connect using OAuth2 and grant read/send permissions. Step 2: OpenAI API Key Get your API key from OpenAI. Add it to n8n credentials for the OpenAI node. Step 3: WhatsApp Integration Use your WhatsApp Business API or a provider like Twilio or 360Dialog. Replace placeholders with your details: [YOUR_WHATSAPP_NUMBER] [YOUR_FINANCE_TEAM_NUMBER] [YOUR_SUPPORT_TEAM_NUMBER] Step 4: Import & Run Import the workflow JSON into n8n. Adjust prompts, labels, and routing logic as needed. Execute and monitor results. ##Good to Know Fully customizable — add or remove categories, adjust responses, and change alert channels. Can be integrated with Slack, Discord, Trello, Notion, Jira, or CRM systems. Scales easily across teams and departments. ##Requirements Gmail account with OAuth2 credentials set up in n8n OpenAI API key for classification and content generation WhatsApp (or other messaging service) integration Optional: Slack, Notion, CRM, or accounting tool integrations ##Customization Ideas Create support tickets in Trello, Notion, or Jira from Customer Support emails. Sync Finance emails with QuickBooks, Stripe, or Google Sheets. Replace WhatsApp alerts with Slack or Discord messages. Use Zapier/Make for cross-platform automations.

Automated AWS S3 / Azure / Google to local MinIO Object Backup with Scheduling What this workflow does ? This workflow performs automated, periodic backups of objects from an AWS S3 bucket, an Azure Container or a Google Storage Space to a MinIO S3 bucket running locally or on a dedicated container/VM/server. It can also work if the MinIO bucket is running on a remote cloud provider's infrastructure; you just need to change the URL and keys. Who's this intended for ? Storage administrators, cloud architects, or DevOps who need a simple and scalable solution for retrieving data from AWS, Azure or GCP. How it works This workflow uses the official AWS S3 API to list and download objects from a specific bucket, or the Azure BLOB one, then send them to MinIO using their version of the S3 API. Requirements None, just a source Bucket on your Cloud Storage Provider and a destination one on MinIO. You'll also need to get MinIO running. You're using Proxmox VE ? Create a MinIO LXC Container : https://community-scripts.github.io/ProxmoxVE/scripts?id=minio Need a Backup from another Cloud Storage Provider ? Need automated backup from another Cloud Storage Provider ? $\mapsto$ Check out our templates, we've done it with AWS, Azure, and GCP, and we even have a version for FTP/SFTP servers! For a dedicated source Cloud Storage Provider, please contact us ! $\odot$ These workflow can be integrated to bigger ones and modified to best suit your needs ! You can, for example, replace the MinIO node to another S3 Bucket from another Cloud Storage Provider (Backblaze, Wasabi, Scaleway, OVH, ...)

What this template does Transforms provider documentation (URLs) into an auditable, enforceable multicloud security control baseline. It: Fetches and sanitizes HTML Uses AI to extract security requirements (strict 3-line TXT blocks) Composes enforceable controls** (strict 7-line TXT blocks with true-equivalence consolidation) Builds the final baseline* (TXT or JSON, see *Outputs) with a Technology: header Returns a downloadable artifact via webhook and can append/create the file in Google Drive Why it’s useful Eliminates manual copy-paste and produces a consistent, portable baseline ready for review, audit, or enforcement tooling—ideal for rapidly generating or refreshing baselines across cloud providers and services. Multicloud support The workflow is multicloud by design. Provide the target cloud in the request and run the same pipeline for: AWS, **Azure, GCP (out of the box) Extensible to other providers/services by adjusting prompts and routing logic How it works (high level) POST /create (Basic Auth) with { cloudProvider, technology, urls[] } Input validation → generate uuid → resolve Google Drive folder (search-or-create) Download & sanitize each URL AI pipeline: Extractor → Composer → Baseline Builder → (optional) Baseline Auditor Append/create file in Drive and return a downloadable artifact (TXT/JSON) via webhook Request (webhook) Method: POST URL: https://<your-n8n>/webhook/create Auth: Basic Auth Headers: Content-Type: application/json Example input (Postman/CLI) { "cloudProvider": "aws", "technology": "Amazon S3", "urls": [ "https://docs.aws.amazon.com/AmazonS3/latest/userguide/security-best-practices.html", "https://www.trendmicro.com/cloudoneconformity/knowledge-base/aws/S3/", "https://repost.aws/knowledge-center/secure-s3-resources" ] } Field reference cloudProvider (string, required) — case-insensitive. Supported: aws, azure, gcp. technology (string, required) — e.g., "Amazon S3", "Azure Storage", "Google Cloud Storage". urls (string\[], required) — 1–20 http(s) URLs (official/reputable docs). Optional (Google Drive destination): gdriveTargetId (string) — Google Drive folderId used for append/create. gdrivePath (string) — Path like "DefySec/Baselines" (folders are created if missing). gdriveTargetName (string) — Folder name to find/create under root. Optional (Assistant overrides): assistantExtractorId, assistantComposerId, assistantBaselineId, assistantAuditorId (strings) Resolution precedence Drive: gdriveTargetId → gdrivePath → gdriveTargetName → default folder. Assistants: explicit IDs above → dynamic resolution by name (expects 1_DefySec_Extractor, 2_DefySec_Control_Composer, 3_DefySec Baseline Builder, 4_DefySec_Baseline_Auditor). Validation Rejects empty urls or non-http(s) schemes; normalizes cloudProvider to aws|azure|gcp. Sanitizes fetched HTML (removes scripts/styles/headers) before AI steps. Outputs Primary:* downloadable *TXT** file controls_<technology>_<timestamp>.txt (via webhook). Composer outcomes:** if no groups to consolidate → NO_CONTROLS_TO_BE_CONSOLIDATED; if nothing valid remains → NO_CONTROLS_FOUND.  JSON path:* when the Builder stage is configured for *JSON-only** output (strict schema), the workflow returns a .json artifact and the Auditor validates it (see next section).  Techniques used (from the built-in assistants) Provider-aware extraction with strict TXT contract (3 lines):* Extractor limits itself to the declared provider/technology, outputs only Description/Reference/SecurityObjective, and applies a *reflexive quality check** before emitting.  Normalization & strict header parsing:** Composer normalizes whitespace/fences, requires the CloudProvider/Technology header, and ignores anything outside the exact 3-line block shape.  True-equivalence grouping & consolidation:* Composer groups *only** when intent, enforcement locus/mechanism, scope, and mode/setting all match—otherwise items remain distinct.  7-line enforceable control format:* Composer renders each (consolidated or unique) control in *exactly seven labeled lines** to keep results auditable and automatable.  Builder with JSON-only schema & technology inference:* Builder parses 7-line blocks, infers technology, consolidates true equivalents again if needed, and returns *pure JSON** matching a canonical schema (with counters in meta).  Self-evaluation loop (Auditor):* Auditor *unwraps transport, validates **schema & content, checks provider terminology/scope/automation, and returns either GOOD_ENOUGH or a JSON instruction set for the Builder to fix and re-emit—enabling reflective improvement.  Reference prioritization:** Across stages, official provider documentation is preferred in References (AWS/Azure/GCP).  Customization & extensions Prompt-reflective techniques:** keep (or extend) the Auditor loop to add more review passes and quality gates.  Compliance assistants:* add assistants to analyze/label controls for *HIPAA, PCI DSS, SOX** (and others), emitting mappings, gaps, and remediation notes. Implementation context:* feed internal implementation docs, runbooks, or *Architecture Decision Records (ADRs); use these as **grounding to generate or refine controls (works with local/self-hosted LLMs, too). Local/self-hosted LLMs:** swap OpenAI nodes for your on-prem LLM endpoint while keeping the pipeline. Provider-specific outputs:** extend the final stage to export Policy-as-Code or IaC snippets (Rego/Sentinel, CloudFormation Guard, Bicep/ARM, Terraform validations). Assistant configuration & prompts Full assistant configurations and prompts (Extractor, Composer, Baseline Builder, Baseline Auditor) are available here: https://github.com/followdrabbit/n8nlabs/tree/main/Lab03%20-%20Multicloud%20AI%20Security%20Control%20Baseline%20Builder/Assistants Security & privacy No hardcoded secrets in HTTP nodes; use n8n’s Credential Manager. Drive operations are optional and folder-scoped. For sensitive environments, switch to a local LLM and provide only sanitized/approved inputs. Quick test (curl) curl -X POST "https://<your-n8n>/webhook/create" \ -u "<user>:<pass>" \ -H "Content-Type: application/json" \ -d '{ "cloudProvider":"aws", "technology":"Amazon S3", "urls":[ "https://docs.aws.amazon.com/AmazonS3/latest/userguide/security-best-practices.html" ] }' \ -OJ

Automating AWS S3 Operations with n8n: Buckets, Folders, and Files Watch the demo video below: This tutorial walks you through setting up an automated workflow that generates AI-powered images from prompts and securely stores them in AWS S3. It leverages the new AI Tool Node and OpenAI models for prompt-to-image generation. Who’s it for This workflow is ideal for: Designers & marketers** who need quick, on-demand AI-generated visuals. Developers & automation builders* exploring *AI-driven workflows** integrated with cloud storage. Educators or trainers** creating tutorials or exercises on AI image generation. Businesses* looking to automate *image content pipelines** with AWS S3 storage. How it works / What it does Trigger: The workflow starts manually when you click “Execute Workflow”. Edit Fields: You can provide input fields such as image description, resolution, or naming convention. Create AWS S3 Bucket: Automatically creates a new S3 bucket if it doesn’t exist. Create a Folder: Inside the bucket, a folder is created to organize generated images. Prompt Generation Agent: An AI agent generates or refines the image prompt using the OpenAI Chat Model. Generate an Image: The refined prompt is used to generate an image using AI. Upload File to S3: The generated image is uploaded to the AWS S3 bucket for secure storage. This workflow showcases how to combine AI + Cloud Storage seamlessly in an automated pipeline. How to set up Import the workflow into n8n. Configure the following credentials: AWS S3 (Access Key, Secret Key, Region). OpenAI API Key (for Chat + Image models). Update the Edit Fields node with your preferred input fields (e.g., image size, description). Execute the workflow and test by entering a sample image prompt (e.g., “Futuristic city skyline in watercolor style”). Check your AWS S3 bucket to verify the uploaded image. Requirements n8n** (latest version with AI Tool Node support). AWS account** with S3 permissions to create buckets and upload files. OpenAI API key** (for prompt refinement and image generation). Basic familiarity with AWS S3 structure (buckets, folders, objects). How to customize the workflow Custom Buckets**: Replace the auto-create step with an existing S3 bucket. Image Variations**: Generate multiple image variations per prompt by looping the image generation step. File Naming**: Adjust file naming conventions (e.g., timestamp, user input). Metadata**: Add metadata such as tags, categories, or owner info when uploading to S3. Alternative Storage: Swap AWS S3 with **Google Cloud Storage, Azure Blob, or Dropbox. Trigger Options: Replace manual trigger with **Webhook, Form Submission, or Scheduler for automation. ✅ This workflow is a hands-on example of how to combine AI prompt engineering, image generation, and cloud storage automation into a single streamlined process.

Quick overview This workflow runs daily to pull knowledge base content from Notion, generate OpenAI embeddings, upsert the documents into Pinecone, and upload two language-specific text knowledge files to Vapi so your voice assistant’s query tool and assistant configuration stay in sync. How it works Runs every day at 2:00 AM on a schedule. Clears the existing Pinecone vectors for the configured namespace and waits briefly for deletion to complete. Fetches pages from multiple Notion databases (services, FAQ, scripts, dialogue tree, objections, and disclaimers) and merges them into tagged, language-aware text records. Splits the merged text into chunks, generates OpenAI embeddings, and upserts the resulting vectors into a Pinecone index. Builds two consolidated knowledge base text files (one per language) from the Notion content. Deletes the previous Vapi knowledge file (if configured), uploads the new file, and creates a Vapi query tool that references it. Retrieves each Vapi assistant, replaces its tool list with the newly created query tool, and logs the sync result. Setup Add Notion credentials, create a Notion integration, share the relevant pages/databases with it, and replace the Notion database ID placeholders in all Notion nodes. Add a Pinecone API key (HTTP header auth and Pinecone vector store credentials), create a Pinecone index, set the correct index name, and replace the Pinecone host URL placeholder used for vector deletion. Add an OpenAI API key for the embeddings step and ensure your Pinecone index dimensions match the selected embedding model. Add a Vapi API key (HTTP header auth), replace the assistant ID placeholders for both languages, and optionally fill in the old Vapi file IDs after the first successful run to enable cleanup. Requirements An n8n instance, Notion, a Vapi account, a Pinecone account, and an OpenAI API key Customization Built for two languages out of the box — easy to extend to more by duplicating the language branch. Remove the Pinecone branch entirely if you only need the Vapi sync half.

Quick overview This workflow syncs an internal Notion knowledge base to Pinecone on a daily schedule, then runs a Slack bot that answers questions in a specific channel using Pinecone retrieval and an OpenAI chat model, replying in a thread with citations back to the source Notion pages. How it works Runs on a daily schedule to sync your Notion knowledge base into a Pinecone vector index. Fetches all pages from a specified Notion database and then pulls each page’s full block content (including nested blocks). Combines each page’s blocks into a single document and attaches metadata such as the Notion title, URL, and last edited time. Splits each document into overlapping text chunks, generates OpenAI embeddings, and inserts them into Pinecone while clearing and rebuilding the target namespace. Triggers when a new message is posted in the configured Slack channel and ignores bot/system messages to prevent reply loops. Uses an OpenAI-powered agent that always queries Pinecone for relevant chunks (including source metadata) and generates an answer in the user’s language. Posts the response back to Slack as a threaded reply, including cited Notion sources. Setup Create a Notion internal integration, connect its token as credentials in n8n, share your knowledge base database with the integration and set the Notion database ID in the Notion database query. Create a Pinecone index (name: knowledge-base-interna, dimension: 1536, metric: cosine), add Pinecone API credentials, and ensure the workflow namespace (kb-digitalcube) matches your desired target. Add an OpenAI API key for both embedding generation and the chat model, and keep the embedding model consistent between ingestion and query. Create a Slack app with channels:history and chat:write scopes, enable Event Subscriptions to point to the workflow’s Slack trigger webhook URL, invite the bot to your channel, and set the Slack channel ID and Slack credentials in the Slack nodes. Replace all REPLACE credential placeholders, run the ingestion branch once to build the Pinecone namespace, and then activate the workflow. Requirements Notion account with your documentation in a database (content in page bodies, database shared with your integration) Pinecone account (free Starter tier works) with a 1536-dimension cosine index OpenAI API key Slack workspace where you can create apps n8n instance reachable from the internet so Slack can deliver events (n8n Cloud, or self-hosted behind a tunnel) Customization Swap Pinecone for Qdrant or Supabase/pgvector by replacing the two vector store nodes Add Google Drive or PDF sources by duplicating the ingestion branch into the same index — the bot branch needs no changes Tune chunk size (1,000/200 worked best for us), topK (5 is the sweet spot) or the sync schedule Edit the agent's system prompt, but keep the rule that forbids answering from memory and requires citing sources — it's what makes the bot trustworthy

🧠 About this workflow This workflow automatically generates personalized B2B outreach email messages by combining AI-based company research and text generation. It’s designed to help sales and marketing professionals automate the creation of tailored cold emails for prospects. ⚙️ How it works Get rows from Google Sheets — Retrieves companies marked as “ready” for outreach. Loop Over Items — Processes each company individually. Company Research (LangChain Agent) — Uses the Tavily search tool to collect key company insights such as overview, offerings, and recent news. Generate Outreach Message (LLM Chain) — Drafts a professional, concise, and fully personalized email body in English using the AI training context from YOUR_COMPANY_NAME. This example uses an AI training and automation service context, but you can easily modify the prompt to fit your own company’s products, services, or industry. Add to Google Sheets — Writes the generated messages back into the sheet. (Optional) Add to Instantly.ai — Sends the finalized lead data to your Instantly campaign for cold email distribution. 👥Use Cases 💼Sales & CRM:Automatically build and update your client database from received business cards 🏢Back Office & Admin: Digitize incoming cards for unified company records 📧Marketing Teams: Collect and manage leads efficiently 📚 AI / OCR Research: Build structured datasets for training AI models or internal automation 🧩 Troubleshooting If the workflow does not generate emails or data fails to appear in Google Sheets, please check the following: Google Sheets credentials — Ensure that the connected account has edit permissions and the document ID and sheet name are correctly set. API keys — Verify that your OpenRouter and Tavily API credentials are valid and not expired. Rate limits — Tavily and OpenRouter may throttle requests when processing multiple records. Try lowering the batch size in the “Limit” node. Empty company background — If the “Company Research” node returns no output, make sure the input company name is correct and includes sufficient context (e.g., full company name, not abbreviation). LLM output format — Ensure the “Generate Outreach Message” node is set to return plain text, not JSON or markdown. Instantly.ai integration (optional) — If leads are not added, confirm that your API key and campaign ID are valid, and that the node is not disabled. If the issue persists, enable “Always Output Data” in key nodes (such as Company Research and Generate Outreach Message) to debug intermediate results. You can also use the Execution Log to inspect where the flow stops or returns an empty output. ⚠️ Disclaimer This workflow uses AI language models and third-party APIs (OpenRouter, Tavily). Ensure that you add your own API credentials securely and verify all AI-generated content before sending emails.

Automatically enrich company records with comprehensive firmographic data by pulling domains from Google Sheets, setting up custom HubSpot fields, enriching through Sona API, and syncing complete profiles to HubSpot CRM with custom property mapping. Import company domains from a Google Sheet, configure custom HubSpot fields for Sona data, automatically enrich domains with detailed firmographic intelligence, and create fully populated company records in HubSpot—so you can build rich prospect databases without manual research. How it works Step 1: Get Company List Reads company domains from your Google Sheet Aggregates all domains into a single array Prepares data for batch processing Step 2: Setup HubSpot Fields Creates custom Sona fields in HubSpot CRM Defines all enrichment data fields needed Ensures proper field mapping for incoming data Step 3: Prepare for Processing Converts aggregated domains into individual items Sets data for batch loop processing Readies each company for enrichment Step 4: Enrich & Sync to HubSpot Loops through each company domain Calls Sona API for enrichment data Creates company in HubSpot with standard fields Formats and updates custom Sona properties Combines firmographics + tech data in one profile Includes 2-second wait between operations for rate limiting What you'll get The workflow enriches each company record with: Firmographic Data**: Company size, employee count, revenue estimates, headquarters location, and founding year Contact Information**: Phone numbers, social media profiles, and timezone details Business Intelligence**: Company descriptions and industry positioning Custom HubSpot Properties**: All Sona data mapped to dedicated custom fields Organized CRM Records**: All data automatically synced to HubSpot for immediate use Domain Tracking**: Companies linked to their websites for future reference Why use this Eliminate manual research**: Save 10-15 minutes per company by automating firmographic lookups Build rich databases**: Transform basic domain lists into comprehensive company profiles Custom field management**: Automatically creates and populates HubSpot custom properties Improve targeting**: Segment and prioritize accounts based on size, location, and other firmographics Keep data current**: Run scheduled enrichments to maintain up-to-date company information Scale your prospecting**: Process hundreds of companies in minutes instead of days Better lead qualification**: Make informed decisions with complete company intelligence Streamlined workflow**: One-click enrichment from spreadsheet to CRM with custom field setup Setup instructions Before you start, you'll need: Google Sheets with a column named website_Domain containing company domains (e.g., example.com) HubSpot Account & App Token - Get an app token by creating a legacy app: Go to HubSpot Settings → Integrations → Legacy Apps Click Create Legacy App Select Private (for one account) In the scopes section, enable the following permissions: crm.schemas.companies.write crm.objects.companies.write crm.schemas.companies.read crm.objects.companies.read Click Create Copy the access token from the Auth tab Sona API Key (for company enrichment) Sign up at https://app.sonalabs.com Free tier available for testing Configuration steps: Prepare your data: Create a Google Sheet with a "website_Domain" column and add 2-3 test companies (e.g., example.com, anthropic.com) Connect Google Sheets: In the "Get Company List from Sheet" node, authenticate with Google and select your spreadsheet and sheet name Configure HubSpot field creation: In the "Create Custom HubSpot Fields" node (Step 2), authenticate with your HubSpot access token and review the custom Sona fields that will be created Add Sona credentials: In the "Sona Enrich" node, authenticate with your Sona API key Connect HubSpot for company creation: In the "Create HubSpot Company" and "Update Company with AI Data" nodes, authenticate using your HubSpot access token Test with sample data: Run the workflow with 2-3 test companies and verify: Custom fields are created in HubSpot Company records appear correctly in HubSpot All firmographic data is populated in custom properties Add error handling: Configure notifications for failed enrichments or API errors (optional but recommended) Scale and automate: Process your full company list, then optionally add a Schedule Trigger for automatic daily or weekly enrichment to keep your CRM data fresh

Automated Facebook Page Story Video Publisher (Google Drive → Facebook → Google Sheet) > Recommended: Self-hosted via tino.vn/vps-n8n?affid=388 — use code VPSN8N for up to 39% off. This workflow is an automated solution for publishing video content from Google Drive to your Facebook Page Stories, while using Google Sheets as a posting queue manager. What This Workflow Does (Workflow Function) This automation orchestrates a complete multi-step process for uploading and publishing videos to Facebook Stories: Queue Management: Every 2 hours and 30 minutes, the workflow checks a Google Sheet (Get Row Sheet node) to find the first video whose Stories column is empty — meaning it hasn’t been posted yet. Conditional Execution: An If node confirms that the video’s File ID exists before proceeding. Video Retrieval: Using the File ID, the workflow downloads the video from Google Drive (Google Drive node) and calculates its binary size (Set to the total size in bytes node). Facebook 3-Step Upload: It performs the Facebook Graph API’s three-step upload process through HTTP Request nodes: Step 1 – Initialize Session: Starts an upload session and retrieves the upload_url and video_id. Step 2 – Upload File: Uploads the binary video data to the provided upload_url. Step 3 – Publish Video: Finalizes and publishes the uploaded video as a Facebook Story. Status Update: Once completed, the workflow updates the same row in Google Sheets (Update upload status in sheet node) using the row_number to mark the video as processed. Prerequisites (What You Need Before Running) 1. n8n Instance > Recommended: Self-hosted via tino.vn/vps-n8n?affid=388 — use code VPSN8N for up to 39% off. 2. Google Services Google Drive Credentials:** OAuth2 credentials for Google Drive to let n8n download video files. Google Sheets Credentials:** OAuth2 credentials for Google Sheets to read the posting queue and update statuses. Google Sheet:** A spreadsheet (ID: 1RnE5O06l7W6TLCLKkwEH5Oyl-EZ3OE-Uc3OWFbDohYI) containing: File ID — the video’s unique ID in Google Drive. Stories — posting status column (leave empty for pending videos). row_number — used for updating the correct row after posting. 3. Facebook Setup Page ID:** Your Facebook Page ID (currently hardcoded as 115432036514099 in the info node). Access Token:* A *Page Access Token** with permissions such as pages_manage_posts and pages_read_engagement. This token is hardcoded in the info node and again in Step 3. Post video. Usage Guide and Implementation Notes How to Use Queue Videos: Add video entries to your Google Sheet. Each entry must include a valid Google Drive File ID. Leave the Stories column empty for videos that haven’t been posted. Activate: Save and activate the workflow. The Schedule Trigger will automatically handle new uploads every 2 hours and 30 minutes. Implementation Notes ⚠️ Token Security:* Hardcoding your *Access Token* inside the info node is *not recommended**. Tokens expire and expose your Page to risk if leaked. 👉 Action: Replace the static token with a secure Credential setup that supports token rotation. Loop Efficiency:* The *“false”** output of the If node currently loops back to the Get Row Sheet node. This creates unnecessary cycles if no videos are found. 👉 Action: Disconnect that branch so the workflow stops gracefully when no unposted videos remain. Status Updates:* To prevent re-posting the same video, the final Update upload status in sheet node must update the *Stories** column (e.g., write "POSTED"). 👉 Action: Add this mapping explicitly to your Google Sheets node. Automated File ID Sync:** This workflow assumes that the Google Sheet already contains valid File IDs. 👉 You can build a secondary workflow (using Schedule Trigger1 → Search files and folders → Append or update row in sheet) to automatically populate new video File IDs from your Google Drive. ✅ Result Once active, this workflow automatically: pulls pending videos from your Google Sheet, uploads them to Facebook Stories, and marks them as posted — all without manual intervention.

Description This powerful workflow automates the evaluation of new digital tools, websites, or platforms with the goal of assessing their potential impact on your business. By leveraging Telegram for user input, Apify for deep content extraction, advanced AI for contextual analysis, and Google Sheets for personalized data integration and record-keeping, this tool delivers clear, actionable verdicts that help you determine whether a tool is worth adopting or exploring further. Key Features and Workflow User-Friendly Input: Submit URLs of tools or websites directly through Telegram for quick and easy evaluation requests. Dynamic Content Extraction: The workflow retrieves detailed content from the submitted URLs using the Apify web crawler, capturing rich data for analysis. AI-Powered Cleaning & Analysis: Sophisticated AI models filter out noise, distill meaningful insights, and contextualize findings based on your business profile and goals stored in Google Sheets. Personalized Business Context: Integration with Google Sheets brings in your company’s specialization, current focus, and strategic objectives to tailor the analysis specifically to your needs. Structured Analysis Output: Receive a thorough, structured report including concise summaries, key considerations, business impact, benefits, risks, actionable insights, and an easy-to-understand final verdict on the tool’s relevance. Decision Support: The tool estimates effort, time to value, urgency, and confidence levels, enabling informed prioritization and strategic decision-making. Seamless Communication: Results are sent back via Telegram, ensuring you get timely and direct feedback without needing to leave your messaging app. Record Keeping & Tracking: All analyses and decisions are logged automatically into Google Sheets, creating a searchable knowledge base for ongoing reference and reporting. Setup Instructions for Key Nodes Telegram Trigger Node: Configure your Telegram bot API credentials here. Link the bot to your Telegram account to receive messages for URL submissions. URL Extraction Node: No credentials needed. This node extracts URLs from incoming messages for processing. Apify Web Crawler Node Setup Guide: Go to Apify's website, sign up for an account if you don’t have one, and get your API token from your profile’s API tokens section. Then, paste this token into the Apify Node’s API Key field in n8n. AI Cleaning and Analysis Nodes: Configure OpenRouter or compatible AI service API keys for content processing. Customize prompts or models if desired to align analysis style. Google Sheets Nodes: Connect using your Google account and provide access to the specified Google Sheet. Ensure sheets for Company Details and Analysis Results exist with proper columns as per this workflow. Telegram Reply Node: Use the Telegram bot API credentials to send analysis summaries and verdicts back to users. Access and Edit the Google Sheet You can access the Google Sheet used by this workflow here: Access the google sheet here Please make a copy of the sheet to your own Google Drive before connecting it with this workflow. This allows you to customize the sheets, update company information, and manage analysis results securely without affecting the original template. Extendibility Beyond manual URL submissions, you can enhance this workflow by scheduling automated daily checks of new product launches from platforms like Product Hunt. The system can proactively analyze emerging tools and deliver timely updates via Telegram, email, or other channels, helping you stay ahead of innovation effortlessly.

This flow is supported by a Chrome plugin created with Cursor AI. The idea was to create a Chrome plugin and a backend service in N8N to do chart analytics with OpenAI. It's a good sample on how to submit a screenshot from the browser to N8N. Who is it for? N8N developers who want to learn about using a Chrome plugin, an N8N webhook and OpenAI. What opportunity does it present? This sample opens up a whole range of N8N connected Chrome extensions that can analyze screenshots by using OpenAI. What this workflow does? The workflow contains: a webhook trigger an OpenAI node with GPT-4O-MINI and Analyze Image selected a response node to send back the Text that was created after analysing the screenshot. All this is needed to talk to the Chrome extension which is created with Cursor AI. The idea is to visit the tradingview.com crypto charts, click the Chrome plugin and get back analytics about the shown chart in understandable language. This is driven by the N8N flow. With the new image analytics capabilities of OpenAI this opens up a world of opportunities. Requirements/setup OpenAI API key Cursor AI installed The Chrome extension. Download The N8N JSON code. Download How to customize it to your needs? Both the Chrome extension and N8N flow can be adapted to use on other websites. You can consider: analyzing a financial screen and ask questions about the data shown analyzing other charts extending the N8N workflow with other AI nodes With AI and image analytics the sky is the limit and in some cases it saves you from creating complex API integrations. Download Chrome extension

CallForge - AI-Powered Product Insights Processor from Sales Calls Automate product feedback extraction from AI-analyzed sales calls and store structured insights in Notion for data-driven product decisions. 🎯 Who is This For? This workflow is designed for: ✅ Product managers tracking customer feedback and feature requests. ✅ Engineering teams identifying usability issues and AI/ML-related mentions. ✅ Customer success teams monitoring product pain points from real sales conversations. It streamlines product intelligence gathering, ensuring customer insights are structured, categorized, and easily accessible in Notion for better decision-making. 🔍 What Problem Does This Workflow Solve? Product teams often struggle to capture, categorize, and act on valuable feedback from sales calls. With CallForge, you can: ✔ Automatically extract and categorize product feedback from AI-analyzed sales calls. ✔ Track AI/ML-related mentions to gauge customer demand for AI-driven features. ✔ Identify feature requests and pain points for product development prioritization. ✔ Store structured feedback in Notion, reducing manual tracking and increasing visibility across teams. This workflow eliminates manual feedback tracking, allowing product teams to focus on innovation and customer needs. 📌 Key Features & Workflow Steps 🎙️ AI-Powered Product Feedback Processing This workflow processes AI-generated sales call insights and organizes them in Notion databases: Triggers when AI sales call data is received. Detects product-related feedback (feature requests, bug reports, usability issues). Extracts key product insights, categorizing feedback based on customer needs. Identifies AI/ML-related mentions, tracking customer interest in AI-driven solutions. Aggregates feedback and categorizes it by sentiment (positive, neutral, negative). Logs insights in Notion, making them accessible for product planning discussions. 📊 Notion Database Integration Product Feedback** → Logs feature requests, usability issues, and bug reports. AI Use Cases** → Tracks AI-related discussions and customer interest in machine learning solutions. 🛠 How to Set Up This Workflow 1. Prepare Your AI Call Analysis Data Ensure AI-generated sales call insights are available. Compatible with Gong, Fireflies.ai, Otter.ai, and other AI transcription tools. 2. Connect Your Notion Database Set up Notion databases for: 🔹 Product Feedback (logs feature requests and bug reports). 🔹 AI Use Cases (tracks AI/ML mentions and customer demand). 3. Configure n8n API Integrations Connect your Notion API key** in n8n under “Notion API Credentials.” Set up webhook triggers** to receive AI-generated sales insights. Test the workflow** using a sample AI sales call analysis. 🔧 How to Customize This Workflow 💡 Modify Notion Data Structure – Adjust fields to align with your product team's workflow. 💡 Refine AI Data Processing Rules – Customize how feature requests and pain points are categorized. 💡 Integrate with Slack or Email – Notify teams when recurring product issues emerge. 💡 Expand with Project Management Tools – Sync insights with Jira, Trello, or Asana to create product tickets automatically. ⚙️ Key Nodes Used in This Workflow 🔹 If Nodes – Detect if product feedback, AI mentions, or feature requests exist in AI data. 🔹 Notion Nodes – Create and update structured feedback entries in Notion. 🔹 Split Out & Aggregate Nodes – Process multiple insights and consolidate AI-generated data. 🔹 Wait Nodes – Ensure smooth sequencing of API calls and database updates. 🚀 Why Use This Workflow? ✔ Eliminates manual sales call review for product teams. ✔ Provides structured, AI-driven insights for feature planning and prioritization. ✔ Tracks AI/ML mentions to assess demand for AI-powered solutions. ✔ Improves product development strategies by leveraging real customer insights. ✔ Scalable for teams using n8n Cloud or self-hosted deployments. This workflow empowers product teams by transforming sales call data into actionable intelligence, optimizing feature planning, bug tracking, and AI/ML strategy. 🚀