Filter breaking geopolitical news with AI scoring & Telegram alerts
Geopolitics Breaking News Alert System
Workflow Name: Geopolitics Breaking News Alert System Author: Devjothi Dutta Category: Productivity, News & Media, AI/Machine Learning Complexity: Medium Setup Time: 45-60 minutes
📖 Description
An intelligent geopolitical monitoring system that filters 200+ daily news articles down to only the critical breaking news that matters to you. This workflow uses smart keyword filtering and AI-powered scoring to eliminate noise, reduce AI costs, and deliver only high-priority geopolitical alerts to Telegram.
The Problem: Traditional news monitoring is overwhelming - hundreds of articles per hour, 95% irrelevant to your region of interest, no urgency prioritization, and critical breaking news gets buried in noise.
The Solution: This workflow combines dual-layer filtering (primary + secondary keywords) with AI scoring to distinguish actual breaking news from general news coverage. By filtering first and scoring second, you reduce AI API costs by 80-90% while ensuring you never miss critical geopolitical developments. Switch between monitoring India, China, Middle East, Russia-Ukraine, or any region by simply changing a configuration file.
Perfect for government analysts, corporate security teams, investment research firms, news organizations, or anyone who needs to stay informed about geopolitical developments without information overload.
👥 Who's it for
For Government & Defense Analysts:
- Monitor specific regions for military actions, diplomatic developments, and security threats
- Filter by mission-critical keywords to eliminate irrelevant news
- AI scoring identifies genuine breaking news vs routine coverage
- Reduce analyst workload by 90% through intelligent automation
For Corporate Security & Risk Teams:
- Track geopolitical risks affecting global supply chains and operations
- Custom keyword filters for industry-specific concerns (e.g., "semiconductor", "tariff", "sanctions")
- Real-time alerts for events impacting business continuity
- Cost-efficient monitoring with minimal AI API usage
For Investment Research Firms:
- Monitor emerging market geopolitical risks affecting portfolio companies
- AI scoring differentiates market-moving events from background noise
- Configurable alert thresholds based on investment strategy (conservative vs aggressive)
- Track multiple regions simultaneously with different configs
For News Organizations & Journalists:
- Monitor breaking geopolitical developments for editorial coverage
- Filter by urgency to prioritize assignment desk resources
- Aggregate multiple international news sources in one place
- Extend alerts to newsroom Slack channels or email
✨ Key Features
- 🎯 Smart Dual-Layer Filtering - Primary keywords ensure regional relevance, secondary keywords filter by event type (military, diplomatic, economic)
- 🤖 AI-Powered Urgency Scoring - GPT-4o-mini scores articles 1-10 based on geopolitical urgency, distinguishing breaking news from routine coverage
- 💰 Cost-Efficient Design - Filter first, score second approach reduces AI API calls by 80-90% (only ~5 articles analyzed out of 200)
- 🌍 Multi-Region Support - Monitor India, China, Middle East, Russia-Ukraine, or any region by switching config files
- 📰 Multi-Source RSS Aggregation - Combines 6 international news sources (NYT, BBC, Al Jazeera, SCMP, regional feeds)
- 🔄 Duplicate Detection - Persistent storage prevents re-analyzing same articles across multiple executions
- 📊 Consolidated Alerts - Single Telegram message with all breaking news, grouped by urgency score
- ⏰ Flexible Scheduling - Configure trigger interval per your needs (15min for active conflicts, 3hr for routine monitoring)
- 💾 Config-Driven Architecture - All filters, keywords, and scoring rules in Google Drive JSON file
- 🔒 Production Ready - Tested end-to-end with real-world India and China configurations
- 📈 Scalable Design - Run multiple regional configs in parallel, extend to Slack/WhatsApp/Email delivery
🛠️ Requirements
Required Services:
- n8n (version 1.0+) - Workflow automation platform
- Free tier: n8n cloud or self-hosted Docker
- Required feature: Data Tables (for duplicate tracking)
- OpenAI API (GPT-4o-mini) - AI scoring engine
- Cost: ~$0.10/day for 30min intervals
- Free tier: $5 credit for new accounts
- Telegram Bot - Alert delivery
- Free: Create via @BotFather on Telegram
- Get chat ID via @userinfobot
- Google Drive - Config file storage
- Free: Any Google account
- Used for publicly shared JSON config files
Required Credentials:
- OpenAI API Key - Get from platform.openai.com (GPT-4o-mini access)
- Telegram Bot Token - Create bot via @BotFather, get token
- n8n Data Table - Built-in n8n feature (no external credential)
Optional:
- Slack Webhook URL (for extending alerts to Slack)
- SMTP credentials (for email alerts)
- Twilio account (for WhatsApp/SMS alerts)
📦 What's Included
This workflow package includes:
- Complete n8n workflow JSON (ready to import)
- Complete setup guide - Detailed configuration with Data Table setup, troubleshooting
- Technical architecture documentation
- Use cases and customization guide
- 4 pre-built regional configs (India, China, Middle East, Russia-Ukraine)
🚀 Quick Start
Full setup takes 45-60 minutes. For detailed step-by-step instructions, see SETUP_GUIDE.md
Overview
- Create n8n Data Table (
analyzed_articleswith 2 columns) - Upload config to Google Drive (choose region, share publicly, get file ID)
- Import workflow (22 nodes ready to configure)
- Configure nodes:
- Update Google Drive config URL with your file ID
- Update 6 RSS Feed URLs for your region
- Link 3 Data Table nodes to
analyzed_articlestable
- Add credentials (OpenAI API, Telegram Bot)
- Set schedule (15min-daily based on monitoring needs)
- Test workflow (verify filtering, scoring, alerts work)
- Activate (workflow runs automatically on schedule)
Quick Start Result:
- ✅ 200+ articles processed → 5-7 filtered → 3-5 scored → 1-3 alerts sent
- ✅ Telegram receives consolidated breaking news message
- ✅ Workflow runs every 30min (or your chosen interval)
- ✅ Total monthly cost: $3-5 (OpenAI API only)
Need help? See detailed SETUP_GUIDE.md for complete instructions with screenshots and troubleshooting.
📊 Workflow Stats
- Nodes: 22
- Complexity: Medium
- Execution Time: ~30-60 seconds per run
- Monthly Cost: $3-5 (OpenAI API usage only)
- Maintenance: Minimal (update RSS feeds if sources change)
- Scalability: Handles 200+ articles per execution, easily scales to 10+ RSS feeds
🎨 Customization Options
- Add more regions: Create new config JSON files for North Korea, Taiwan, Africa, Latin America, etc.
- Multi-channel alerts: Extend to Slack, WhatsApp, Email, Discord, Microsoft Teams, SMS
- Severity-based routing: Send critical alerts (score 9-10) via SMS, others to Telegram
- Custom scoring models: Switch between GPT-4o-mini, GPT-4o, Claude based on config
- Exclude keywords: Add "exclude_keywords" array to filter out sports, entertainment, weather
- Alert digest mode: Aggregate alerts into daily/weekly summary emails instead of real-time
- Dashboard integration: Connect to Grafana or Metabase for visual trend analysis
- Webhook triggers: Use workflow output to trigger other n8n workflows or external systems
- Custom RSS feeds: Add industry-specific or regional news sources
- Adjust alert threshold: Change from score >= 6 to higher/lower based on notification preferences
🔧 How it Works
- Schedule Trigger (Configurable):
- Workflow runs at your configured interval (15min, 30min, 1hr, 3hr, daily, etc.)
- Trigger frequency depends on use case: active conflicts need more frequent monitoring
- Config Loading:
- HTTP Request node fetches JSON config from Google Drive
- Config contains: keywords, scoring rules, AI role, alert threshold, Telegram chat ID
- RSS Aggregation:
- 6 RSS Feed nodes fetch articles from international news sources
- Merge node combines all feeds (~200 articles per execution)
- RSS Cleanup node strips HTML and normalizes to 5 fields (60-75% size reduction)
- Smart Filtering (Cost Optimization Layer 1):
- Dynamic Filter checks PRIMARY keywords (geographic/entity: "india", "modi", "delhi")
- Also checks SECONDARY keywords (event type: "military", "conflict", "trade deal")
- Both conditions required: Article must mention at least one primary AND one secondary
- Result: 200 articles reduced to ~5-7 relevant articles (95% reduction)
- Why this matters: Eliminates noise BEFORE expensive AI scoring
- Duplicate Detection (Cost Optimization Layer 2):
- Queries Data Table for previously analyzed article links
- Filters out articles already scored in last 7 days
- Result: ~5-7 filtered articles reduced to ~3-5 new articles
- Why this matters: Prevents redundant AI API calls (saves 80% on repeat articles)
- Dynamic AI Prompt Generation:
- Code node builds system prompt from config.ai_role and config.scoring_criteria
- Instructs AI: "You are a geopolitical analyst for [REGION]. Score articles 1-10..."
- Includes scoring rubric: 9-10 = Military Action, 7-8 = Trade/Economic, etc.
- AI Urgency Scoring (Breaking News Detection):
- Breaking News Analyzer (GPT-4o-mini) evaluates geopolitical urgency
- Scores 1-10: Distinguishes genuine breaking news from routine coverage
- Returns: score, category, reasoning, should_alert (true/false based on threshold)
- Cost: ~$0.002 per article (only ~3-5 articles scored per execution)
- Alert Decision:
- IF node checks: should_alert === true (score >= config.alert_threshold)
- Only high-priority alerts proceed to Telegram
- Articles below threshold are logged but not sent
- Alert Aggregation:
- Consolidates multiple breaking news alerts into single Telegram message
- Groups by urgency score with color-coded emojis (🔴 9-10, 🟠 7-8, 🟡 6-7)
- Includes: score, category, title, link for each alert
- Telegram Delivery:
- Sends consolidated alert to configured Telegram chat
- Uses HTML formatting for bold text and clickable links
- Chat ID dynamically loaded from config (different regions → different chats)
💡 Pro Tips
- Start with Higher Threshold: Begin with alert_threshold = 7 to avoid alert fatigue, lower to 6 after tuning keywords
- Regional RSS Matters: Use region-specific news sources for better coverage (e.g., Times of India for India, not just BBC/NYT)
- Test Keywords First: Run workflow manually with "Test Workflow" to verify keyword filtering before activating schedule
- Monitor AI Costs: Check OpenAI usage dashboard after first week to confirm ~$0.10/day cost estimate
- Tune Secondary Keywords: Add domain-specific terms to secondary keywords (e.g., "semiconductor" for tech supply chain monitoring)
- Use Separate Configs for Critical Regions: Clone workflow for high-priority regions instead of switching configs manually
- Schedule Based on Time Zones: Align execution intervals with business hours in monitored region (e.g., 9AM-6PM IST for India)
- Clear Duplicates for Testing: Manually clear analyzed_articles Data Table when testing new configs for fresh results
- Backup Working Configs: Export and version control config files before making major keyword changes
- Consider Alert Fatigue: Score 9-10 events are rare (0-1 per day), score 6-8 events are common (2-5 per day) - set threshold accordingly
🔗 Related Workflows
- Multi-Region Geopolitics Dashboard - Combine multiple regional configs into single monitoring dashboard
- Geopolitical Risk Scoring for Portfolios - Integrate with stock portfolio data to assess investment risk
- Automated Geopolitical Intelligence Reports - Generate daily/weekly PDF reports from breaking news data
- Conflict Escalation Tracker - Track score trends over time to detect escalating tensions
- Supply Chain Risk Alerting - Focus on trade/sanctions news affecting global supply chains
📧 Support & Feedback
For questions, issues, or feature requests:
- GitHub: n8n-geopolitics-breaking-news-alert Repository
- n8n Community Forum: Tag @devdutta
- Email: devjothi@gmail.com
📄 License
MIT License - Free to use, modify, and distribute
⭐ If you find this workflow useful, please share your feedback and star the workflow!
Filter Breaking Geopolitical News with AI Scoring & Telegram Alerts
This n8n workflow automates the process of identifying and alerting on breaking geopolitical news. It fetches news from an RSS feed, uses an AI agent to score the severity of each news item, and then sends alerts to Telegram for highly impactful news.
What it does
- Schedules Execution: The workflow runs on a predefined schedule to regularly check for new news.
- Fetches RSS Feed: It retrieves the latest articles from a specified RSS news feed.
- Applies AI Scoring: Each news article is passed to an AI Agent (powered by an OpenAI Chat Model) which evaluates its content and assigns a "breaking score" based on geopolitical impact.
- Parses AI Output: The AI's response is structured and parsed to extract the breaking score and any relevant summary.
- Filters by Score: The workflow then uses an 'If' condition to filter news items. Only articles with a breaking score above a certain threshold (e.g., 7 out of 10) proceed.
- Sends Telegram Alerts: For news items that meet the breaking score criteria, a formatted alert message is sent to a specified Telegram chat.
Prerequisites/Requirements
- n8n Instance: A running n8n instance.
- RSS Feed URL: The URL of an RSS news feed you want to monitor (e.g., a geopolitical news feed).
- OpenAI API Key: An API key for OpenAI to power the AI Agent and Chat Model. This needs to be configured as an n8n credential.
- Telegram Bot Token: A Telegram Bot token to send messages. This needs to be configured as an n8n credential.
- Telegram Chat ID: The chat ID where the alerts should be sent (can be a user, group, or channel ID).
Setup/Usage
- Import the Workflow:
- Download the provided JSON file.
- In your n8n instance, go to "Workflows" and click "New".
- Click the "Import from JSON" button and paste the workflow JSON or upload the file.
- Configure Credentials:
- OpenAI: Set up an OpenAI credential in n8n with your API key. Select this credential in the "OpenAI Chat Model" node.
- Telegram: Set up a Telegram credential in n8n with your Bot Token. Select this credential in the "Telegram" node.
- Customize Nodes:
- Schedule Trigger (Node 839): Adjust the schedule to your desired frequency for checking news (e.g., every 15 minutes, hourly).
- RSS Read (Node 37): Update the "URL" field to your preferred geopolitical news RSS feed.
- AI Agent (Node 1119): Review and adjust the prompt for the AI agent to refine how it scores news. Ensure it clearly instructs the AI to provide a "breaking score" (e.g., on a scale of 1-10) and a brief summary.
- Structured Output Parser (Node 1179): Verify the schema matches the expected output format from your AI Agent. If you change the AI's output, you'll need to update this schema.
- If (Node 20): Modify the condition to set your desired "breaking score" threshold (e.g.,
{{ $json.breakingScore > 7 }}). - Telegram (Node 49):
- Enter the
Chat IDwhere you want to receive alerts. - Customize the
Textfield to format your alert message using expressions to include details like the news title, summary, breaking score, and URL.
- Enter the
- Activate the Workflow: Once configured, activate the workflow by toggling the "Active" switch in the top right corner of the workflow editor.
The workflow will now run on its schedule, fetch news, score it with AI, and send Telegram alerts for significant geopolitical events.
Related Templates
Track competitor SEO keywords with Decodo + GPT-4.1-mini + Google Sheets
This workflow automates competitor keyword research using OpenAI LLM and Decodo for intelligent web scraping. Who this is for SEO specialists, content strategists, and growth marketers who want to automate keyword research and competitive intelligence. Marketing analysts managing multiple clients or websites who need consistent SEO tracking without manual data pulls. Agencies or automation engineers using Google Sheets as an SEO data dashboard for keyword monitoring and reporting. What problem this workflow solves Tracking competitor keywords manually is slow and inconsistent. Most SEO tools provide limited API access or lack contextual keyword analysis. This workflow solves that by: Automatically scraping any competitor’s webpage with Decodo. Using OpenAI GPT-4.1-mini to interpret keyword intent, density, and semantic focus. Storing structured keyword insights directly in Google Sheets for ongoing tracking and trend analysis. What this workflow does Trigger — Manually start the workflow or schedule it to run periodically. Input Setup — Define the website URL and target country (e.g., https://dev.to, france). Data Scraping (Decodo) — Fetch competitor web content and metadata. Keyword Analysis (OpenAI GPT-4.1-mini) Extract primary and secondary keywords. Identify focus topics and semantic entities. Generate a keyword density summary and SEO strength score. Recommend optimization and internal linking opportunities. Data Structuring — Clean and convert GPT output into JSON format. Data Storage (Google Sheets) — Append structured keyword data to a Google Sheet for long-term tracking. Setup Prerequisites If you are new to Decode, please signup on this link visit.decodo.com n8n account with workflow editor access Decodo API credentials OpenAI API key Google Sheets account connected via OAuth2 Make sure to install the Decodo Community node. Create a Google Sheet Add columns for: primarykeywords, seostrengthscore, keyworddensity_summary, etc. Share with your n8n Google account. Connect Credentials Add credentials for: Decodo API credentials - You need to register, login and obtain the Basic Authentication Token via Decodo Dashboard OpenAI API (for GPT-4o-mini) Google Sheets OAuth2 Configure Input Fields Edit the “Set Input Fields” node to set your target site and region. Run the Workflow Click Execute Workflow in n8n. View structured results in your connected Google Sheet. How to customize this workflow Track Multiple Competitors → Use a Google Sheet or CSV list of URLs; loop through them using the Split In Batches node. Add Language Detection → Add a Gemini or GPT node before keyword analysis to detect content language and adjust prompts. Enhance the SEO Report → Expand the GPT prompt to include backlink insights, metadata optimization, or readability checks. Integrate Visualization → Connect your Google Sheet to Looker Studio for SEO performance dashboards. Schedule Auto-Runs → Use the Cron Node to run weekly or monthly for competitor keyword refreshes. Summary This workflow automates competitor keyword research using: Decodo for intelligent web scraping OpenAI GPT-4.1-mini for keyword and SEO analysis Google Sheets for live tracking and reporting It’s a complete AI-powered SEO intelligence pipeline ideal for teams that want actionable insights on keyword gaps, optimization opportunities, and content focus trends, without relying on expensive SEO SaaS tools.
By Ranjan DailataGenerate song lyrics and music from text prompts using OpenAI and Fal.ai Minimax
Spark your creativity instantly in any chat—turn a simple prompt like "heartbreak ballad" into original, full-length lyrics and a professional AI-generated music track, all without leaving your conversation. 📋 What This Template Does This chat-triggered workflow harnesses AI to generate detailed, genre-matched song lyrics (at least 600 characters) from user messages, then queues them for music synthesis via Fal.ai's minimax-music model. It polls asynchronously until the track is ready, delivering lyrics and audio URL back in chat. Crafts original, structured lyrics with verses, choruses, and bridges using OpenAI Submits to Fal.ai for melody, instrumentation, and vocals aligned to the style Handles long-running generations with smart looping and status checks Returns complete song package (lyrics + audio link) for seamless sharing 🔧 Prerequisites n8n account (self-hosted or cloud with chat integration enabled) OpenAI account with API access for GPT models Fal.ai account for AI music generation 🔑 Required Credentials OpenAI API Setup Go to platform.openai.com → API keys (sidebar) Click "Create new secret key" → Name it (e.g., "n8n Songwriter") Copy the key and add to n8n as "OpenAI API" credential type Test by sending a simple chat completion request Fal.ai HTTP Header Auth Setup Sign up at fal.ai → Dashboard → API Keys Generate a new API key → Copy it In n8n, create "HTTP Header Auth" credential: Name="Fal.ai", Header Name="Authorization", Header Value="Key [Your API Key]" Test with a simple GET to their queue endpoint (e.g., /status) ⚙️ Configuration Steps Import the workflow JSON into your n8n instance Assign OpenAI API credentials to the "OpenAI Chat Model" node Assign Fal.ai HTTP Header Auth to the "Generate Music Track", "Check Generation Status", and "Fetch Final Result" nodes Activate the workflow—chat trigger will appear in your n8n chat interface Test by messaging: "Create an upbeat pop song about road trips" 🎯 Use Cases Content Creators: YouTubers generating custom jingles for videos on the fly, streamlining production from idea to audio export Educators: Music teachers using chat prompts to create era-specific folk tunes for classroom discussions, fostering interactive learning Gift Personalization: Friends crafting anniversary R&B tracks from shared memories via quick chats, delivering emotional audio surprises Artist Brainstorming: Songwriters prototyping hip-hop beats in real-time during sessions, accelerating collaboration and iteration ⚠️ Troubleshooting Invalid JSON from AI Agent: Ensure the system prompt stresses valid JSON; test the agent standalone with a sample query Music Generation Fails (401/403): Verify Fal.ai API key has minimax-music access; check usage quotas in dashboard Status Polling Loops Indefinitely: Bump wait time to 45-60s for complex tracks; inspect fal.ai queue logs for bottlenecks Lyrics Under 600 Characters: Tweak agent prompt to enforce fuller structures like [V1][C][V2][B][C]; verify output length in executions
By Daniel NkenchoAutomate invoice processing with OCR, GPT-4 & Salesforce opportunity creation
PDF Invoice Extractor (AI) End-to-end pipeline: Watch Drive ➜ Download PDF ➜ OCR text ➜ AI normalize to JSON ➜ Upsert Buyer (Account) ➜ Create Opportunity ➜ Map Products ➜ Create OLI via Composite API ➜ Archive to OneDrive. --- Node by node (what it does & key setup) 1) Google Drive Trigger Purpose: Fire when a new file appears in a specific Google Drive folder. Key settings: Event: fileCreated Folder ID: google drive folder id Polling: everyMinute Creds: googleDriveOAuth2Api Output: Metadata { id, name, ... } for the new file. --- 2) Download File From Google Purpose: Get the file binary for processing and archiving. Key settings: Operation: download File ID: ={{ $json.id }} Creds: googleDriveOAuth2Api Output: Binary (default key: data) and original metadata. --- 3) Extract from File Purpose: Extract text from PDF (OCR as needed) for AI parsing. Key settings: Operation: pdf OCR: enable for scanned PDFs (in options) Output: JSON with OCR text at {{ $json.text }}. --- 4) Message a model (AI JSON Extractor) Purpose: Convert OCR text into strict normalized JSON array (invoice schema). Key settings: Node: @n8n/n8n-nodes-langchain.openAi Model: gpt-4.1 (or gpt-4.1-mini) Message role: system (the strict prompt; references {{ $json.text }}) jsonOutput: true Creds: openAiApi Output (per item): $.message.content → the parsed JSON (ensure it’s an array). --- 5) Create or update an account (Salesforce) Purpose: Upsert Buyer as Account using an external ID. Key settings: Resource: account Operation: upsert External Id Field: taxid_c External Id Value: ={{ $json.message.content.buyer.tax_id }} Name: ={{ $json.message.content.buyer.name }} Creds: salesforceOAuth2Api Output: Account record (captures Id) for downstream Opportunity. --- 6) Create an opportunity (Salesforce) Purpose: Create Opportunity linked to the Buyer (Account). Key settings: Resource: opportunity Name: ={{ $('Message a model').item.json.message.content.invoice.code }} Close Date: ={{ $('Message a model').item.json.message.content.invoice.issue_date }} Stage: Closed Won Amount: ={{ $('Message a model').item.json.message.content.summary.grand_total }} AccountId: ={{ $json.id }} (from Upsert Account output) Creds: salesforceOAuth2Api Output: Opportunity Id for OLI creation. --- 7) Build SOQL (Code / JS) Purpose: Collect unique product codes from AI JSON and build a SOQL query for PricebookEntry by Pricebook2Id. Key settings: pricebook2Id (hardcoded in script): e.g., 01sxxxxxxxxxxxxxxx Source lines: $('Message a model').first().json.message.content.products Output: { soql, codes } --- 8) Query PricebookEntries (Salesforce) Purpose: Fetch PricebookEntry.Id for each Product2.ProductCode. Key settings: Resource: search Query: ={{ $json.soql }} Creds: salesforceOAuth2Api Output: Items with Id, Product2.ProductCode (used for mapping). --- 9) Code in JavaScript (Build OLI payloads) Purpose: Join lines with PBE results and Opportunity Id ➜ build OpportunityLineItem payloads. Inputs: OpportunityId: ={{ $('Create an opportunity').first().json.id }} Lines: ={{ $('Message a model').first().json.message.content.products }} PBE rows: from previous node items Output: { body: { allOrNone:false, records:[{ OpportunityLineItem... }] } } Notes: Converts discount_total ➜ per-unit if needed (currently commented for standard pricing). Throws on missing PBE mapping or empty lines. --- 10) Create Opportunity Line Items (HTTP Request) Purpose: Bulk create OLIs via Salesforce Composite API. Key settings: Method: POST URL: https://<your-instance>.my.salesforce.com/services/data/v65.0/composite/sobjects Auth: salesforceOAuth2Api (predefined credential) Body (JSON): ={{ $json.body }} Output: Composite API results (per-record statuses). --- 11) Update File to One Drive Purpose: Archive the original PDF in OneDrive. Key settings: Operation: upload File Name: ={{ $json.name }} Parent Folder ID: onedrive folder id Binary Data: true (from the Download node) Creds: microsoftOneDriveOAuth2Api Output: Uploaded file metadata. --- Data flow (wiring) Google Drive Trigger → Download File From Google Download File From Google → Extract from File → Update File to One Drive Extract from File → Message a model Message a model → Create or update an account Create or update an account → Create an opportunity Create an opportunity → Build SOQL Build SOQL → Query PricebookEntries Query PricebookEntries → Code in JavaScript Code in JavaScript → Create Opportunity Line Items --- Quick setup checklist 🔐 Credentials: Connect Google Drive, OneDrive, Salesforce, OpenAI. 📂 IDs: Drive Folder ID (watch) OneDrive Parent Folder ID (archive) Salesforce Pricebook2Id (in the JS SOQL builder) 🧠 AI Prompt: Use the strict system prompt; jsonOutput = true. 🧾 Field mappings: Buyer tax id/name → Account upsert fields Invoice code/date/amount → Opportunity fields Product name must equal your Product2.ProductCode in SF. ✅ Test: Drop a sample PDF → verify: AI returns array JSON only Account/Opportunity created OLI records created PDF archived to OneDrive --- Notes & best practices If PDFs are scans, enable OCR in Extract from File. If AI returns non-JSON, keep “Return only a JSON array” as the last line of the prompt and keep jsonOutput enabled. Consider adding validation on parsing.warnings to gate Salesforce writes. For discounts/taxes in OLI: Standard OLI fields don’t support per-line discount amounts directly; model them in UnitPrice or custom fields. Replace the Composite API URL with your org’s domain or use the Salesforce node’s Bulk Upsert for simplicity.
By Le Nguyen