Cong Nguyen
I’m a developer specialized in building web and mobile applications with AI integration and intelligent automation. With a solid background in data science, I help businesses build smarter digital solutions using cutting-edge technologies.
Templates by Cong Nguyen
LinkedIn lead finder & Gemini-powered personalized outreach with Google Sheets
📄 What this workflow does This workflow automates the process of finding LinkedIn leads and writing personalized outreach messages. It takes user input (keywords + purpose), generates a Boolean LinkedIn search query with Gemini, fetches up to 20 results via Google Custom Search API, logs them into Google Sheets, and then drafts custom outreach messages for each lead. Finally, the workflow updates the sheet and optionally sends you an email notification with the results. 👤 Who is this for Sales and business development teams who want to automate LinkedIn prospecting. Recruiters searching for candidates and generating outreach at scale. Marketers or founders looking for potential partners, clients, or collaborators. Anyone tired of manual LinkedIn searches and copy-pasting outreach messages. ✅ Requirements Google Sheets account (with a sheet for storing LinkedIn leads + messages). Google Custom Search Engine (CSE) enabled with "Search the entire web" and valid cx. Gemini API access (for Boolean query generation + outreach message drafting). SMTP credentials for optional email notifications. ⚙️ How to set up Connect your Google Sheets account and select the sheet to store results. Configure Gemini API credentials in n8n for both search query + outreach message generation. Create a Google Custom Search Engine and note down the key and cx. Update the HTTP Request node with your credentials (key, cx, hl, gl). Set up SMTP credentials if you want email notifications. Publish the Form trigger and test with sample keywords + purposes. 🔁 How it works Form Submit → Collects user input: keywords + purpose of contact. Gemini (Boolean Generator) → Creates a LinkedIn-specific search query (site:linkedin.com). Google Custom Search API → Fetches up to 20 matching profiles or company pages. Append to Google Sheets → Saves name, LinkedIn URL, description. Split & Loop → Processes each LinkedIn entry one by one. Gemini (Message Writer) → Generates personalized outreach messages using Purpose + company info. Update Google Sheets → Adds outreach message to the matching LinkedIn row. Optional Email Notification → Sends you a link to the updated sheet. 💡 About Margin AI Margin AI is an AI-services agency that acts as your AI Service Companion. We design intelligent, human-centric automation solutions—turning your team’s best practices into scalable, automated workflows and tools. Industries like marketing, sales, and operations benefit from our tailored AI consulting, automation tools, chatbot development, and more.
By Cong NguyenEnglish vocabulary bot for Telegram with Gemini & random word API
📄 What this workflow does Every 3 hours, the workflow fetches 3 random English words, asks Gemini to generate a short Vietnamese vocabulary digest (word, Vietnamese meaning, and an example sentence), and sends it to a Telegram chat. Perfect for steady, low-effort vocab exposure in groups. 👤 Who is this for English learners who want a gentle, automated learning cadence. Teachers/tutors who share daily vocab in Telegram groups. Community admins who want lightweight, useful content for members. Anyone who prefers bite-sized language learning on autopilot. ✅ Requirements Gemini API access (configured in n8n). Telegram Bot token + chat ID (the chat you want to receive messages). Internet access to Random Word API (no API key required). n8n instance with outbound HTTPS access. ⚙️ How to set up Add your Gemini credentials in n8n (the Google Gemini/PaLM node). Add your Telegram credentials and set the chatId in the “Send a text message” node. (Optional) Adjust the schedule interval (default: every 3 hours). (Optional) Change the number of words by updating the HTTP Request URL param words=3. (Optional) Edit the Gemini prompt language/content to fit your style (currently Vietnamese output). Run once to test; confirm the message arrives in Telegram. 🔁 How it works Schedule Trigger → runs every 3 hours. HTTP Request → calls random-word-api to get 3 words. Edit Fields (Set) → wraps the API response under word. Aggregate → prepares the word field for the LLM. Message a model (Gemini) → creates a Vietnamese digest: English word, Vietnamese meaning, and example sentence for each word. Send a text message (Telegram) → posts the digest to your specified chat. 💡 About Margin AI Margin AI is an AI-services agency that acts as your AI Service Companion. We design intelligent, human-centric automation solutions—turning your team’s best practices into scalable, automated workflows and tools. Industries like marketing, sales, and operations benefit from our tailored AI consulting, automation tools, chatbot development, and more.
By Cong NguyenGenerate product videos automatically with Gemini, FAL and Google Workspace
📄 What this workflow does This workflow turns your n8n into an automated product-video generator powered by Google Sheets. When a new row is added with status = run, it: Downloads the product image from Google Drive. Converts the image to base64 and sends it to Gemini, which creates a branded ad-style variant. Saves the generated image back into a designated Google Drive folder. Sends the image to FAL (image-to-video) to generate a short promotional video clip. Polls FAL’s response_url until the video is ready. Uploads the video to Google Drive (videos folder). Updates the original Google Sheet row with the video link and sets status = finished. Handles API latency via wait/polling and logs failures into the sheet if needed. 👤 Who is this for Marketing teams automating creative asset production. E-commerce businesses needing quick product promo videos. Agencies creating branded ad content at scale. ✅ Requirements An n8n instance. A Google Sheet with at least these columns: STT, linkimage, note, status, linkvideo. Google Sheets & Google Drive OAuth2 credentials connected in n8n. Gemini API key (for ad-style image generation). FAL API key (for image-to-video). ⚙️ How to set up Import the provided workflow JSON into n8n. Connect Google Sheets credentials and point to your sheet (documentId + gid). Connect Google Drive credentials and update folder IDs in the two Upload File nodes (images/videos). Add Gemini and FAL API keys in the respective HTTP Request headers (via Credentials). Test: add a row with link_image, note, and status = run. The workflow should generate and save a video, then update the sheet with the link. 🔁 How it works Trigger → Google Sheets Trigger fires on rowAdded where status = run. Pre-processing → Download the product image from Google Drive → extract base64. LLM Image Generation → Gemini generates an ad-style variant based on note. Storage → Upload the generated image into the “images” Drive folder. Video Creation → FAL converts the branded image into a short video. Polling → Wait node + HTTP Request check job status until video is completed. Write-back → Upload final video into the “videos” Drive folder, update the sheet with the link_video, and set status = finished.
By Cong NguyenConversational sales agent for WooCommerce with GPT-4, Stripe and CRM integration
📄 What this workflow does This workflow transforms your n8n instance into a fully automated AI sales assistant for WooCommerce stores. It detects customer intent from chat, searches products, answers FAQs, generates Stripe payment links, captures leads into your CRM, and even escalates to human support when needed. It provides smooth conversational memory and syncs with your knowledge base to ensure accurate, human-like responses. 👤 Who is this for WooCommerce store owners who want to automate customer support and sales. Sales and marketing teams looking to scale personalized product recommendations. E-commerce managers who want to reduce manual chat handling. Anyone aiming to integrate AI assistants with payments, CRM, and FAQs. ✅ Requirements WooCommerce account with API access. Qdrant vector store (for FAQ and RAG retrieval). OpenAI/Gemini API credentials (for intent detection + message generation). Google Drive account (to sync and update knowledge base docs). Stripe account (to generate instant payment links). CRM account (HubSpot, Pipedrive, etc.) if lead capture is required. Telegram account for optional human escalation. ⚙️ How to set up Connect WooCommerce API credentials in n8n. Configure Gemini/OpenAI API for intent extraction and chat generation. Set up Qdrant for document retrieval, and link to your Google Drive Sales Docs folder. Configure Stripe API to enable instant payment link generation. Connect your CRM to capture new leads automatically. Add Telegram bot credentials for human escalation (optional). Enable conversational memory and test chat flows end-to-end. 🔁 How it works Intent Extraction → AI analyzes chat messages to detect Product Search, FAQ, Payment, or Lead Capture. Product Search → Queries WooCommerce catalog by keyword, SKU, or price range. FAQ Answering → Retrieves company policies/docs from Qdrant + Google Drive, answered via RAG. Payment Links → Stripe generates instant checkout links for customers ready to buy. Lead Capture → Name + email are auto-stored into CRM. Human Escalation → If intent is unclear, conversation is forwarded to Telegram. Conversational Memory → Maintains last 12 exchanges for natural dialogue. Knowledge Sync → Google Drive docs auto-update into Qdrant for live FAQ support. 💡 About Margin AI Margin AI is an AI-services agency that acts as your AI Service Companion. We design intelligent, human-centric automation solutions—turning your team’s best practices into scalable workflows and tools. Industries like marketing, sales, and operations benefit from our tailored AI consulting, automation tools, and chatbot development.
By Cong NguyenGenerate branded article images with GPT-4o, FAL Flux and Google Drive
📄 What this workflow does This workflow automatically turns a topic and a reference image URL into a finished, branded article image. It uses GPT-4o to generate a short, detailed image prompt, sends it to FAL Flux image-to-image for rendering, polls until the job is completed, downloads and resizes the image, overlays your company logo, and finally saves the branded result into a specified Google Drive folder. 👤 Who is this for Content teams who need consistent, on-brand article images. Marketing teams looking to scale blog and landing page visuals. Designers who want to automate repetitive resizing and branding tasks. Anyone who needs a pipeline from topic → AI illustration → Google Drive asset. ✅ Requirements OpenAI (GPT-4o) API credentials (for image prompt generation). FAL API key for Flux image-to-image generation. Google Drive OAuth2 connection + target folder ID for saving images. A company logo file/URL (direct download link from Google Drive or any public URL). ⚙️ How to set up Connect OpenAI GPT-4o in the “Create prompt” node. Add your FAL API key to all HTTP Request nodes (generate image, check image finish, Get image link). Replace the logo link in “Get company’s logo” with your own logo URL. Configure the Google Drive node with your OAuth2 credentials and set the correct Folder ID. Update the image_url in “Link image” (or pass from upstream data). Test the workflow end-to-end with a sample subject and image. 🔁 How it works Form/Manual Trigger → Input subject + reference image URL. GPT-4o → Generates a <70-word sharp/detailed prompt (no text/logos). FAL Flux (HTTP Request) → Submits job for image-to-image generation. Polling Loop → Wait + check status until COMPLETED. Download Image → Retrieves generated image link. Resize Image → Standardize to 800×500 pixels. Get & Resize Logo → Fetch company logo, resize for branding. Composite → Overlay logo onto article image. Save to Google Drive → Final branded image saved in target folder. 💡 About Margin AI Margin AI is your AI Service Companion. We help organizations design intelligent, human-centric automation — from content pipelines and branding workflows to customer insights and sales enablement. Our tailored AI solutions scale marketing, operations, and creative processes with ease.
By Cong NguyenAutomated request-to-quote with OpenAI, Google Sheets & CraftMyPDF
📄 What this workflow does Turns a simple form submission into a polished, priced PDF quote—automatically. Captures lead details via Form: Request a Quote. Loads your Google Sheets catalog (SKUs, price, stock, min qty, etc.). Uses OpenAI to select SKUs and build a strict JSON quote (respects instock and minqty, optional discount ≤10%). Maps data in a Code node to compute line totals, discount, VAT, and a unique invoicenumber; validates/falls back duedate. Renders a branded PDF via CraftMyPDF, fetches the file link, and emails the customer the quote. 👤 Who is this for SMBs and sales teams needing instant quotes from website forms. Ops teams managing catalogs in Sheets who want LLM-assisted SKU selection. Agencies/shops that must generate consistent, branded PDFs and email them automatically. ✅ Requirements A self-hosted n8n instance. Google Sheets catalog with (recommended) columns: sku, name, uom, unitprice, currency, instock (TRUE/FALSE), minqty, leadtime_days, notes. Connected credentials: Google Sheets OAuth2, OpenAI (or compatible), CraftMyPDF, SMTP. A CraftMyPDF template whose fields match the Code node output (invoicenumber, items[], grosstotal, etc.). CraftMyPDF provides a drag-and-drop editor and PDF Generation API that work well with n8n. ⚙️ How to set up Import the workflow JSON into n8n. In Google Sheets: Products, set real documentId/sheetName (IDs) and connect OAuth. In LLM node, keep or change model (default gpt-4.1-mini), and keep the “JSON-only” system prompt. In Create a PDF, set your CraftMyPDF templateId. In Email: Send Quote, set fromEmail and SMTP credentials. Submit a test form; verify LLM JSON → PDF render → email delivery. (Optional) Adjust defaults in the Code node: vatpct (default 10), paymentterms, currency fallback, and valid_days. 🧩 CraftMyPDF template — quick guide (UI) Create & open a template: Log in → Manage Templates → New Template (choose blank or a starter) → Edit to open the editor. The editor has four core tabs: Designer, Preview, Data, Settings. Paste sample JSON: Go to the Data tab and paste a sample that mirrors what n8n will send (e.g., includes invoice_number, client, items[]). This JSON powers the editor’s auto-complete and live preview. Bind fields fast: In Designer, use Data Fields to drag pre-bound text/image components that auto-insert expressions from your JSON—much quicker than manual binding. Add line items: For repeating rows like items[], use Simple Table (set Data Source to {{data.items}}, then in each column use {{row.field}}, e.g., {{row.description}}, {{row.quantity}}, {{row.unit_price}}, {{row.total}}). Use expressions: Anywhere you need dynamic text, enter {{ data.<field> }}—for example {{data.invoicenumber}}, {{data.client}}, {{data.grosstotal}}. Preview the result and/or generate a real PDF from the Preview tab. Finish & integrate: Save the template, note its Template ID, and use it in the n8n CraftMyPDF node. You can return to the editor anytime to tweak layout/styles; the next workflow run will use the updated design. The editor and API are built for reusable templates. 🔁 How it works Trigger → Form submission captures: Full Name, Email, Company, Requirements, Budget Min/Max, Need By, Notes. Catalog Load → Sheets node returns rows; passed to the LLM as JSON. LLM Quote → Model selects SKUs/qty, pricing, discount (≤10%), terms, and returns VALID JSON only. Code Mapping → Parses JSON (strips code fences if present), computes discounts/VAT/totals, assigns invoicenumber (Q-YYYYMMDD-ABCDE), and validates duedate (falls back to today + valid_days). PDF Render → CraftMyPDF generates the branded quote and returns a file URL. Delivery → HTTP node fetches the file; SMTP node emails the customer with dynamic subject and totals. 💡 About Margin AI Margin AI is your AI Service Companion. We help organizations design intelligent, human-centric automation — from content pipelines and branding workflows to customer insights and sales enablement. Our tailored AI solutions scale marketing, operations, and creative processes with ease.
By Cong NguyenGenerate AI-curated sales quotes with OpenAI, Qdrant & CraftMyPDF PDF delivery
👀 Short Description Turn form submissions into AI-curated quotes with SKU selection straight from Qdrant, branded PDF generation, and automatic email—now streamlined for quoting only (FAQ removed). (Improved from the previous workflow: Automated Request-to-Quote System with OpenAI, Google Sheets & CraftMyPDF Email Delivery) 🎉What’s new vs. the old version Products now come directly from Qdrant (no Google Sheets catalog in the loop). Focused quote-only flow — removed FAQ/RAG nodes for a leaner, faster pipeline. Agent enforces a JSON-only contract, keeping pricing/stock grounded in Qdrant payloads. Easier to maintain; fewer moving parts and lower token usage. 📄 What this workflow does Captures lead details via Form: Request a Quote. Searches your Qdrant collection (products) for relevant SKUs by keyword, use-case, features, and budget hints. An AI Agent (OpenAI) selects in-stock SKUs, respects min_qty, and returns a strict JSON quote (optional discount ≤ 10%). A Code step computes line totals, discount, VAT, generates a unique invoicenumber (e.g., Q-YYYYMMDD-ABCDE), and validates or falls back the duedate. CraftMyPDF renders a branded PDF; the file is fetched and SMTP emails the quote to the customer. 👤 Who this is for SMBs and sales teams needing instant, accurate quotes from website forms. Ops teams storing product data in Qdrant and wanting AI-assisted SKU selection. Agencies or shops that must generate consistent, branded PDFs and send them automatically. ✅ Requirements Self-hosted n8n instance. Qdrant collection (default: products) with payload fields: sku, name, uom, unitprice, currency, instock (true/false), min_qty, handle/url, features. Connected credentials: OpenAI (or compatible), Qdrant API, CraftMyPDF, SMTP. A CraftMyPDF template aligned with the Code node output (invoicenumber, items[], grosstotal, etc.). ⚙️ How to set up Import the workflow JSON into n8n. In Qdrant Vector Store (Products), set collection=products and your Qdrant API credentials. In Sales Quote Agent, keep or change the model (default gpt-4.1-mini) and the JSON-only system prompt. In Create a PDF, set your CraftMyPDF templateId. In Email: Send Quote, set fromEmail and SMTP credentials. Submit a test form; verify: Agent JSON → PDF render → email delivery. (Optional) Adjust defaults in the Code node: vatpct (default 10), paymentterms, currency fallback, valid_days. 🔁 How it works (end-to-end) Trigger → Form captures: Full Name, Email, Company, Requirements, Budget Min/Max, Need By, Notes. Product Search → Agent calls PRODUCTS_QDRANT to retrieve relevant SKUs and payload fields from Qdrant. Agent Quote → Selects SKUs and qty, applies pricing and ≤10% discount. 💡 About Margin AI Margin AI is your AI Service Companion. We help organizations design intelligent, human-centric automation — from content pipelines and branding workflows to customer insights and sales enablement. Our tailored AI solutions scale marketing, operations, and creative processes with ease.
By Cong NguyenWordPress SEO publisher with Anthropic AI, Google Docs & media auto
📄 What this workflow does This workflow turns a spreadsheet row into a fully formatted, media-rich WordPress article. It pulls the outline and brand context from Google Sheets/Docs, drafts the article with Anthropic or Gemini, enriches it with internal links, converts it to WordPress-ready HTML, uploads images to the WordPress Media Library, and updates your Google Sheet with links and statuses. Optionally, it can create WooCommerce products (kept disabled by default). 👤 Who is this for Content & SEO teams who publish long-form articles at scale. E-commerce teams creating product blogs/landing pages with galleries. Agencies and freelancers who want a repeatable, trackable content pipeline. Founders/marketers who want “brief → draft → images → publish” in one click. ✅ Requirements Google Sheets (content tracker with columns like Title, Query, Outline Link, Image Links, Status). Google Docs (for outline sources and saving final content). Anthropic &/or Gemini API access (drafting + transformations). WordPress site with REST API enabled (Basic/App Password auth) to upload media (and optionally create posts/products). SerpAPI key (for Google Images cover search) — optional; can be removed. (Optional) Perplexity API if you want the “read official docs once” tool for specs. ⚙️ How to set up Connect Google Sheets and select your tracking sheet/tab. Connect Google Docs (for reading the outline and saving the final article). Add Anthropic and/or Gemini credentials in n8n. Add WordPress credentials (REST API) in the HTTP Request nodes used for media upload (and product/post creation if enabled). (Optional) Add SerpAPI key for the image-cover search node. (Optional) Add Perplexity key in the Sonar node if you’ll parse official docs/specs. Publish/enable the Webhook (or your trigger), then test with a sample row (Status Writing = “Run”). 🔁 How it works Trigger → Get Info (Sheets): Picks the next row marked to run and sets “Processing.” Fetch Outline (Docs): Opens the outline link from the sheet. Content Outline Generator & On-page (Anthropic/Gemini): Writes the article using brand context, E-E-A-T rules, and (optionally) reads official docs once via Perplexity Sonar. Previous Posts → Aggregate → Add Internal Links (Gemini): Loads summaries/keywords of prior posts and injects at least 5 high-relevance internal links into the draft. HTML Version: Converts the draft to strict WordPress-ready HTML (H1–H4, justified paragraphs, links, lists, blockquotes). Post image to WordPress (sub-flow) Image Covers (SerpAPI): Finds a cover image by query. Google Sheets + Code: Parses Image Links and Product Image columns; converts Google Drive shares into direct downloads. Split & HTTP Requests: Downloads each image and uploads to WordPress Media Library. Aggregate + Code: Builds an HTML gallery snippet from uploaded URLs. Update Google Doc: Inserts the final article content into a Google Doc and stores the link. Merge → Update Status to Sheet: Writes back Content Final, Outline Link, statuses (Draft/Complete), and any media links. (Optional) Create WooCommerce Product: Disabled by default—enable if you want automatic product creation using the article HTML and gallery. 💡 About Margin AI Margin AI is an AI-services agency that acts as your AI Service Companion. We design intelligent, human-centric automation solutions—turning your team’s best practices into scalable workflows and tools. Industries like marketing, sales, and operations benefit from our tailored AI consulting, automation tools, and chatbot development.
By Cong NguyenDaily competitor WordPress analysis with charts, Gemini & Telegram reporting
What this workflow does Every night at 22:00 (Asia/HoChiMinh), the workflow fetches the latest posts from multiple competitor WordPress RSS feeds, upserts them into Google Sheets, captures a dashboard screenshot (via ApiFlash), has Gemini Vision analyze the chart, and sends a concise insight report to Telegram. Details Schedule (22:00) → runs daily. Fetch RSS → HTTP Request (or RSS Read) pulls each competitor’s /feed/ (standard WordPress RSS). Normalize & limit → parse XML → JSON, keep the most recent 5 per site for the digest (you can raise/lower this). Upsert to Google Sheets → match on link to avoid duplicates; store fields like guid, site, link, title, excerpt/description, content (if available), pubDate, updated. Screenshot the dashboard → ApiFlash captures the Google Sheets dashboard (specific gid) with your line chart of monthly post counts. Vision analysis → Gemini 1.5-Flash analyzes the chart image and returns a short executive summary, a Markdown table of values (≈ when estimated), insights, and recommended next steps. Telegram push → posts the AI summary (and optionally the screenshot) to your channel/group. Who it’s for SEO/Content/Marketing teams tracking competitor publishing cadence. Founders/PMs who want a nightly snapshot. Competitive intelligence and analytics roles. Requirements n8n (cloud or self-hosted). Google Sheets OAuth2, Telegram Bot, ApiFlash (access key), Google Gemini access. A Google Sheet with columns similar to: id/guid, site, link, title, excerpt, content, pubDate, updated. Setup Import the workflow JSON into n8n. Switch to RSS: Option A (simple): replace HTTP nodes with RSS Read and paste each competitor’s https://{domain}/feed/. Option B (keep HTTP): keep HTTP Request nodes, set Response: XML, then parse with XML node. Mapping to Sheets: point to your documentId and sheetName; set matching column = link for upsert. ApiFlash: add accesskey and the Sheet URL with the correct gid that shows your chart; set scalefactor=2 (or higher for clarity). Gemini Vision: use model gemini-1.5-flash-latest with the included prompt (English output; Markdown table + insights + recommendations). Telegram: set bot credentials and chatId. Schedule: confirm 22:00 Asia/HoChiMinh (adjust as needed). Test: run once → verify rows append/update → see dashboard render → receive AI summary in Telegram. Extending to more competitors Clone an HTTP/RSS node for each additional competitor, update the /feed/ URL, and connect it to the Merge node. No other changes are required—new data will be normalized, upserted, included in charts and in the AI summary automatically. Tips & gotchas WordPress RSS typically includes title, link, pubDate, guid, description, and sometimes content:encoded. If content:encoded is absent, fall back to description. Keep the Sheet chart source range dynamic (e.g., open-ended ranges) so new rows are reflected automatically. If a site’s RSS limits items, you can run multiple feeds (e.g., category feeds) or capture more history on the first run. 💡 About Margin AI Margin Ai is an AI-services agency that acts as your AI Service Companion. We design intelligent, human-centric automation solutions—turning your team’s best practices into scalable workflows and tools. Industries like marketing, sales, and operations benefit from our tailored AI consulting, automation tools, and chatbot development.
By Cong NguyenAutomated tech news report by ApiFlash, Gemini Vision & Sheets to Telegram
📸 What this workflow does Automatically captures a screenshot of a tech news homepage, extracts headlines into structured JSON, logs them in Google Sheets, and posts a daily trend report (7–10 bullet points) to Telegram at 07:00. Details: ApiFlash takes a cropped full-page screenshot of technewsworld.com (configurable). Gemini Vision analyzes the image and returns one strict JSON object (captured_at, source, sentiment, items[]). Code node cleans and parses JSON (removes code fences). Google Sheets stores each headline (headline, topic, highlight, sentiment). Last 3 days of entries (max 30) are aggregated. Gemini writes a concise Trend Report. Telegram sends both the screenshot and the summary. 👤 Who it’s for Editors and creators wanting automated daily news briefs. Marketing/analyst teams logging tech trends. Founders/PMs who want quick morning updates via Telegram. ✅ Requirements n8n (self-hosted or cloud). Accounts/credentials: ApiFlash (API key), Google Gemini, Google Sheets OAuth2, Telegram Bot. A Google Sheet with columns: capturedat, source, sentiment, mainheadlines, topics, highlights. ⚙️ Setup Import the workflow JSON into n8n. Configure ApiFlash node with your access key and target URL. Set Telegram Bot credentials and chatId. Connect Google Sheets OAuth2 and specify documentId/sheetName. Use Gemini (gemini-1.5-flash) for JSON extraction and trend reporting. Adjust schedule (default 07:00). Test: verify JSON parse → Sheet row → trend report → Telegram message. 💡 About Margin AI Margin AI is an AI-services agency that acts as your AI Service Companion. We design intelligent, human-centric automation solutions—turning your team’s best practices into scalable workflows and tools. Industries like marketing, sales, and operations benefit from our tailored AI consulting, automation tools, and chatbot development.
By Cong Nguyen