Weekly AI News Digest with Perplexity AI and Gmail Newsletter
Overview This automated workflow delivers a weekly digest of the most important AI news directly to your inbox. Every Monday at 9 AM, it uses Perplexity AI to research the latest developments and organizes them into four key categories: New Technology, Trending Topics, Top Stories, and AI Security. The workflow then formats this information into a beautifully designed HTML email with summaries, significance explanations, and source links. What It Does Automatically searches for the latest AI news using Perplexity AI Categorizes content into four focused areas most relevant to AI enthusiasts and professionals Generates comprehensive summaries explaining why each story matters Creates a professional HTML email with styled sections and clickable links Sends weekly on Monday at 9 AM (customizable schedule) Includes error handling with fallback content if news parsing fails Setup Instructions Import the Workflow Copy the JSON code and import it into your n8n instance The workflow will appear as “Daily AI News Summary” Configure Perplexity API Sign up for a Perplexity API account at perplexity.ai Create new credentials in n8n: Type: “OpenAI” Name: “perplexity-credentials” API Key: Your Perplexity API key Base URL: https://api.perplexity.ai Set Up Email Credentials Configure SMTP credentials in n8n: Name: “email-credentials” Add your email provider’s SMTP settings Test the connection to ensure emails can be sent Customize Email Settings Open the “Send Email Summary” node Update the toEmail field with your email address Modify the fromEmail if needed (must match your SMTP credentials) Optional Customizations Change Schedule: Modify the “Daily Trigger” node to run at your preferred time Adjust Categories: Edit the Perplexity prompt to focus on different AI topics or change the theme altogether Modify Styling: Update the HTML template in the “Format Email Content” node Test and Activate Run a test execution to ensure everything works correctly Activate the workflow to start receiving daily AI news summaries Requirements n8n instance (cloud or self-hosted) Perplexity API account and key SMTP email access (Gmail, Outlook, etc.)
By Derek SchatzCreate 2 XML files: with and without XML attributes
This workflow demonstrates two ways of exporting data from SQL to XML. First, several random records are received from the MySQL database. Then, in the upper part of the workflow, the structure of an XML is defined in the Set node. After that, the ItemLists node combines all items into an array. This allows an XML node to create a simple XML file. The lower part of the workflow shows how to create an XML with attributes. It is almost identical except that a $ (dollar sign) JSON key is used to define XML attributes. Finally, both files are saved locally.
By n8n TeamParse natural language dates with OpenAI GPT-4o for smart scheduling
This n8n workflow demonstrates how to transform natural language date and time expressions into structured data with 96%+ accuracy. Parse complex expressions like "early next July", "2 weeks after project launch", or "end of Q3" into precise datetime objects with confidence scoring, timezone intelligence, and business rules validation for any automation workflow. Good to know Achieves 96%+ accuracy on complex natural language date expressions At time of writing, this is the most advanced open-source date parser available Includes AI learning that improves over time with user corrections Supports 6 languages with auto-detection (English, Spanish, French, German, Italian, Portuguese) Sub-millisecond response times with intelligent caching Enterprise-grade with business intelligence and timezone handling How it works Natural Language Input: Receives date expressions via webhook, form, email, or chat AI-Powered Parsing: Your world-class date parser processes the text through: 50+ custom rule patterns for complex expressions Multi-language auto-detection and smart translation Confidence scoring (0.0-1.0) for AI decision-making Ambiguity detection with helpful suggestions Business Intelligence: Applies enterprise rules automatically: Holiday calendar awareness (US + International) Working hours validation and warnings Business day auto-adjustment Timezone normalization (IANA format) Smart Scheduling: Creates calendar events with: Structured datetime objects (start/end times) Confidence metadata for workflow decisions Alternative interpretations for ambiguous inputs Rich context for follow-up actions Integration Ready: Outputs connect seamlessly to: Google Calendar, Outlook, Apple Calendar CRM systems (HubSpot, Salesforce) Project management tools (Notion, Asana) Communication platforms (Slack, Teams) How to use The webhook trigger receives natural language date requests from any source Replace the MCP server URL with your deployed date parser endpoint Configure timezone preferences for your organization Customize business rules (working hours, holidays) in the parser settings Connect calendar integration nodes for automatic event creation Add notification workflows for scheduling confirmations Use Cases Meeting Scheduling: "Schedule our quarterly review for early Q3" Project Management: "Set deadline 2 weeks after product launch" Event Planning: "Book venue for the weekend before Labor Day" Personal Assistant: "Remind me about dentist appointment next Tuesday morning" International Teams: "Team standup tomorrow morning" (auto-timezone conversion) Seasonal Planning: "Launch campaign in late spring 2025" Requirements Natural Language Date Parser MCP server (provided code) Webhook endpoint or form trigger Calendar integration (Google Calendar, Outlook, etc.) Optional: Slack/Teams for notifications Optional: Database for learning pattern storage Customizing this workflow Multi-language Support: Enable auto-detection for global teams Business Rules: Configure company holidays and working hours Learning System: Enable AI learning from user corrections Integration Depth: Connect to your existing calendar and CRM systems Confidence Thresholds: Set minimum confidence levels for auto-scheduling Ambiguity Handling: Route unclear dates to human review or clarification requests Sample Input/Output Input Examples: "early next July" "2 weeks after Thanksgiving" "next Wednesday evening" "Q3 2025" "mañana por la mañana" (Spanish) "first thing Monday" Rich Output: json { "parsed": [{ "start": "2025-07-01T00:00:00Z", "end": "2025-07-10T23:59:59Z", "timezone": "America/New_York" }], "confidence": 0.95, "method": "custom_rules", "business_insights": [{ "type": "business_warning", "message": "Selected date range includes July 4th holiday" }], "predictions": [{ "type": "time_preference", "suggestion": "You usually schedule meetings at 10 AM" }], "ambiguities": [], "alternatives": [{ "interpretation": "Early July 2026", "confidence": 0.15 }], "performance": { "cache_hit": true, "response_time": "0.8ms" } } Why This Workflow is Unique World-Class Accuracy: 96%+ success rate on complex expressions AI Learning: Improves over time with user feedback Global Ready: Multi-language and timezone intelligence Business Smart: Enterprise rules and holiday awareness Performance Optimized: Sub-millisecond cached responses Context Aware: Provides confidence scores and alternatives for AI decision-making Transform your scheduling workflows from rigid form inputs to natural, conversational date requests that your users will love!
By JaredCoAutomatic email classification with Gmail and Claude AI
How It Works 1.Gmail Trigger Continuously monitors your Gmail inbox for new messages. Captures the email’s subject, body, and metadata. Sends the extracted content to the Email Content Classifier. 2.Email Content Classification The Email Content Classifier analyzes the email content using natural language processing. Compares the message against predefined Gmail labels: Ads Work Personal Financial Other (fallback label) Users can add or rename categories to match their specific needs. Uses context, tone, and keywords to determine the most accurate label. 3.Applying Gmail Labels Sends the classification result to the corresponding Gmail label node. Automatically applies the matching Gmail label in your inbox. If the classifier cannot confidently match the message, the Other label is used as a fallback. Setup Steps Connect Gmail Accounts Connect your Gmail account in the Gmail Trigger and in each Gmail label node. Configure the Email Content Classifier Map the incoming Gmail message body to inputText. Ensure the classifier node has access to a language model credential (Anthropic or other). Test the Workflow Send a few sample emails to yourself to confirm that labels are correctly applied. Tweak Categories if Needed Adjust category names in the classifier node to match your Gmail labels exactly. Customization Add or rename categories in the classifier to reflect your specific email types. Create corresponding Gmail label nodes for each new category. Expand or modify categories as your workflow evolves to improve organization and efficiency. Use Cases Automatic inbox organization and sorting. Separation of work, personal, financial, and promotional emails. Improved productivity by making important emails easier to locate. Custom categorization for specialized workflows. Troubleshooting Tips Emails not being labeled → check API permissions and message ID references. Wrong label assigned → update classifier examples or refine category descriptions. Classifier not returning a category → confirm fallback category “Other” is configured. Workflow not triggering → reconnect Gmail Trigger authentication and ensure the workflow is active.
By Ayis Saliaris FasseasAutomatically optimize AI prompts with OpenAI using OPRO & DSPy methodology
This workflow implements cutting-edge concepts from Google DeepMind's OPRO (Optimization by PROmpting) and Stanford's DSPy to automatically refine AI prompts. It iteratively generates, evaluates, and optimizes responses against a ground truth, allowing you to "compile" your prompts for maximum accuracy. Why this is powerful Instead of manually tweaking prompts (trial and error), this workflow treats prompt engineering as an optimization problem: OPRO-style Optimization: The "Optimizer" LLM analyzes past performance scores and reasons to mathematically deduce a better prompt. DSPy-style Logic: It separates the "Logic" (Workflow) from the "Parameters" (Prompts), allowing the system to self-correct until it matches the Ground Truth. How it works Define: Set your initial prompt and a test case with the expected answer (Ground Truth). Generate: The workflow generates a response using the current prompt. Evaluate: An AI Evaluator scores the response (0-100) based on accuracy and format. Optimize: If the score is low, the Optimizer AI analyzes the failure and rewrites the prompt. Loop: The process repeats until the score reaches 95/100 or the loop limit is hit. Setup steps Configure OpenAI: Ensure you have an OpenAI credential set up in the OpenAI Chat Model node. Customize: Open the Define Initial Prompt & Test Data node and set your initialprompt, testinput, and ground_truth. Run: Execute the workflow and check the Manage Loop & State node output for the optimized prompt.
By Shun Nakayama