by Sona Labs
Automatically analyzes your Google Ads performance every Monday and sends a comprehensive report to your inbox with AI-powered insights, week-over-week comparisons, and prioritized recommendations to optimize your campaigns. How it works Step 1: Schedule Weekly Analysis Triggers automatically every Monday at midnight Can be customized to your preferred schedule Initiates the entire data collection and analysis process Step 2: Collect Performance Data Fetches last 7 days of Google Ads data via API Retrieves previous 7 days of data (days 8-14) for comparison Extracts key metrics including impressions, clicks, cost, conversions, CTR, and CPA Calculates and summarizes performance for each week Identifies top performers, problem campaigns, and efficiency trends Merges data to create comprehensive week-over-week comparison Step 3: AI-Powered Analysis Aggregates all performance data into a single view Sends data to AI Analyst powered by GPT-5.1 AI analyzes trends, identifies insights, and spots anomalies Diagnoses root causes of performance changes Generates actionable, prioritized recommendations based on business impact Calculates efficiency metrics and budget optimization opportunities Step 4: Deliver Insights Report Formats analysis into a professional HTML report Emails comprehensive insights directly to your inbox Includes executive summary, week-over-week comparison tables, and color-coded metrics Provides high/medium/low priority action items Ready for immediate action and strategy adjustments What you'll get The workflow delivers a comprehensive weekly analysis with: Performance Metrics**: Impressions, clicks, CTR, conversions, cost, CPA, and efficiency trends Week-over-Week Comparison**: Side-by-side analysis with percentage changes and visual indicators Top Performers Analysis**: Detailed breakdown of your best-performing campaigns Issues & Performance Risks**: Identification of campaigns with high spend but zero conversions, declining CTR, or rising CPA AI-Generated Insights**: Intelligent pattern recognition and trend analysis with root cause diagnosis Actionable Recommendations**: Prioritized action items (high/medium/low) with expected impact and risk levels Budget Efficiency Analysis**: Spend allocation recommendations and wasted spend identification Campaign Intelligence**: Clear understanding of what's working and what needs attention Data Confidence Assessment**: Commentary on sample size adequacy and metric reliability Automated Delivery**: Weekly HTML report sent directly to your email without manual effort Why use this Save time on reporting**: Eliminate 2-3 hours of manual weekly analysis and report creation Never miss insights**: AI catches trends and patterns humans might overlook Consistent monitoring**: Automated weekly reviews ensure you stay on top of performance Data-driven decisions**: Make strategic adjustments based on comprehensive analysis with clear priorities Early problem detection**: Spot performance issues and wasted spend before they impact your budget Optimize continuously**: Regular insights enable ongoing campaign refinement Focus on strategy**: Spend less time analyzing data, more time implementing improvements Scalable intelligence**: Works whether you manage 1 campaign or 100 Executive-ready reports**: Professional HTML format suitable for sharing with stakeholders Setup instructions Before you start, you'll need: Google Ads Account & API Access Go to your Google Ads account at https://ads.google.com Find your Customer ID (XXX-XXX-XXXX format in top-right corner) Get a Developer Token from Google Ads API Center Enable API access for your account OpenAI API Key (for GPT-5.1 AI analysis) Sign up at https://platform.openai.com Navigate to API keys section and create a new key Ensure you have access to GPT-5.1 model Gmail Account (for receiving reports) OAuth2 authentication will be used No app password needed Configuration steps: Replace Google Ads Customer ID: Open both "Get Last Week Data" and "Get Previous Week Data" HTTP Request nodes In the URL field, replace [Customer ID] with your actual Customer ID (format: XXX-XXX-XXXX) Add Developer Token: In both HTTP Request nodes, add your Google Ads Developer Token to the header parameters Connect Google Ads OAuth2: In both HTTP Request nodes, authenticate with your Google Ads credentials Select your ad account Connect OpenAI credentials: In the "OpenAI Chat Model" node, add your OpenAI API key Verify GPT-5.1 model is selected Configure email delivery: In the "Email Report to User" node, connect your Gmail OAuth2 credentials Update the recipient email address (default: lee@sonalabs.com) Customize subject line if desired Set your schedule (optional): In the "Weekly Trigger" node, configure your preferred day and time Default is Monday at midnight Test the workflow: Click "Execute Workflow" to run manually Verify data pulls correctly from Google Ads Check that AI analysis provides meaningful insights Confirm email report arrives formatted correctly Customize analysis focus (optional): Open the "AI Analyst" node Adjust the prompt to prioritize specific metrics or goals for your business Modify thresholds for "problem campaigns" in the calculation nodes Activate automation: Enable the workflow to run automatically every Monday Monitor the first few reports to ensure accuracy Note: The workflow analyzes the last 7 days vs. the previous 7 days, giving you rolling two-week comparisons every Monday. Adjust the date ranges in the HTTP Request nodes if you need different time periods.
by Tony Adijah
Who is this for? This workflow is built for founders, sales teams, solopreneurs, and agencies who want to automate outbound sales without expensive tools. Perfect for anyone doing cold email outreach who wants AI-powered personalization at scale. What it does The workflow runs three automated flows: Flow 1 — New Lead Processing (8 AM weekdays): Reads new leads from Google Sheets Scrapes the lead's website to build a research dossier AI scores each lead (0–100) on company fit, role fit, timing signals, and engagement potential For leads scoring 40+, AI generates 3 personalized cold emails with different angles Sends Email 1 immediately and saves all 3 emails to the sheet Low-fit leads are marked as skipped Flow 2 — Follow-up Engine (every 2 hours weekdays): Checks for leads that need follow-ups Sends Email 2 after 3 days, Email 3 after 7 days Automatically marks sequence as complete after Email 3 Skips leads that have already replied Flow 3 — Reply Detection (every 2 hours weekdays): Searches Gmail for replies from active leads Filters out your own sent emails to avoid false positives When a reply is found, marks the lead as "replied" and stops the sequence Sends a Telegram alert with the reply preview Setup steps Google Sheets — Create a spreadsheet with columns: Lead Name, Email, Company, Website, Role/Title, Status, Reply Date, Reply Subject, Reply Snippet, and email tracking columns (see sticky notes in the workflow for full list) Gmail OAuth2 — Connect your Gmail account for sending emails and searching replies Ollama — Install locally and pull your preferred model (e.g., ollama pull mistral). You can also swap for OpenAI or Anthropic Telegram Bot — Create via @BotFather, get your bot token and chat ID AI Lead Scorer prompt — Edit the system prompt with your product, ICP, and scoring criteria AI Email Writer prompt — Edit with your name, company, value prop, and one specific result Sender name — Update the sender name in the Extract Emails code node (line 12) and Find Follow-ups code node (line 9) Gmail address — Set your sending Gmail address in the Filter Active Leads code node (line 10) and Check Reply Results code node (line 10) Test — Add a test lead with status "new", run the research flow manually, verify emails generate correctly, then enable all schedules Requirements Self-hosted n8n (uses Ollama nodes) Ollama running locally with at least one model installed Google Sheets OAuth2 credentials Gmail OAuth2 credentials Telegram Bot credentials How to customize Adjust the scoring threshold (default 40) in the Extract Score node to be more or less selective Change follow-up timing (default 3 and 7 days) in the Find Follow-ups code node Modify cron schedules on any trigger to match your timezone and preferences Swap Ollama for OpenAI or Anthropic by replacing the LLM nodes Add a LinkedIn enrichment step before the dossier builder for richer research Customize email tone and sign-off in the AI Email Writer system prompt
by Oneclick AI Squad
Automatically converts your daily WhatsApp messages and photos from travels into beautifully structured travel stories, saved as documents in Google Drive. How it works Receive WhatsApp Updates - Webhook captures messages, photos, and locations from your travel day Validate & Aggregate Content - JavaScript organizes messages by day, extracts metadata, validates media Fetch Previous Entries - Retrieves existing journal from Google Drive for context and continuity Prepare AI Context - JavaScript builds comprehensive prompt with photos, messages, locations, and timeline Claude AI Story Generation - Transforms raw messages into narrative travel journal with insights Parse & Format Story - JavaScript structures the output into readable document format Wait for Finalization - Brief pause to ensure all processing completes Save to Google Drive - Creates or updates your travel journal document Send Confirmation - WhatsApp notification with preview of generated story Respond to Webhook - Returns success confirmation Setup Steps Import workflow into n8n Configure credentials: Anthropic API - Claude AI for story generation Google Drive - Document storage and retrieval WhatsApp Business API or Twilio WhatsApp - Message integration Create a Google Drive folder for your travel journals Set up WhatsApp webhook integration: Point WhatsApp webhook to: https://your-n8n-instance.com/webhook/travel-journal Configure to send: messages, media, locations Update the "Fetch Previous Journal" node with your Drive folder ID Activate the workflow Sample WhatsApp Input Messages throughout the day: 09:30 AM: "Just arrived in Kyoto! The train station architecture is stunning 🚄" 11:45 AM: "Fushimi Inari shrine - thousands of orange torii gates going up the mountain" 📸 Photo: Torii gates pathway 02:15 PM: "Tried okonomiyaki for lunch. Amazing! The chef made it right in front of us" 📸 Photo: Okonomiyaki cooking 05:30 PM: "Gion district at sunset. Spotted two geishas!" 📍 Location: Gion, Kyoto, Japan 08:45 PM: "Dinner at an izakaya. Made friends with locals who taught us drinking games 😄" Generated Journal Output Day 3: Kyoto - Ancient Temples and Modern Connections The day began with anticipation as the shinkansen pulled into Kyoto Station at 9:30 AM. The station itself was an architectural marvel—a blend of traditional Japanese aesthetics and contemporary design that set the tone for what would be an unforgettable day. By mid-morning, I found myself at Fushimi Inari Taisha, one of Kyoto's most iconic sites. The seemingly endless tunnel of vermillion torii gates created a mesmerizing pathway up Mount Inari. Each gate, donated by individuals and businesses, bore inscriptions in black kanji. The experience was both spiritual and surreal—the way light filtered through the gates, creating dancing shadows on the stone path... [Full narrative continues with integrated photos, locations, and emotional insights] Features Smart Aggregation** - Groups messages by day, even across time zones Photo Integration** - Embeds images inline with contextual descriptions Location Awareness** - Maps locations and adds geographical context Narrative Style** - Converts casual messages into polished travel prose Emotional Intelligence** - Captures mood and significance beyond literal text Timeline Coherence** - Maintains chronological flow and story arc Automatic Continuity** - Links to previous days for multi-day trip journals Format Flexibility** - Outputs as Google Docs with proper formatting Privacy & Data Messages are processed in real-time and not stored long-term Photos are referenced but can be embedded or linked based on preference Journal documents are private in your Google Drive No message content is retained after journal generation
by Cheng Siong Chin
How It Works This workflow automates end-to-end audio translation with quality assurance for content creators, educators, and international teams managing multilingual content. It solves the challenge of translating audio into multiple languages while ensuring accuracy and maintaining organized delivery. The system receives audio files via webhook, splits them into target languages (Arabic, French, Spanish, Chinese, Hindi), and processes each through NVIDIA's Parakeet TDT translation model. OpenAI validates translation quality, and results are enhanced with comprehensive metadata. Successfully translated files are uploaded to Google Drive with organized naming, combined into a summary spreadsheet, and delivered via email notification. Failed translations trigger quality alerts, ensuring reliable output while minimizing manual oversight and reducing translation turnaround time from hours to minutes. Setup Steps Configure NVIDIA API credentials in the "Generate Audio with ElevenLabs" Add OpenAI API key for quality evaluation in the "OpenAI Chat Model" node Set up Google Drive OAuth connection and specify target folder ID for uploads Configure Gmail SMTP credentials for notification delivery Update webhook URL in source applications to trigger workflow Customize target languages in "Split Languages" node if needed Prerequisites Active accounts: NVIDIA (build.nvidia.com), OpenAI, Google Drive, Gmail. API credentials for all services. Use Cases International podcast distribution, e-learning course localization Customization Modify target languages in Split node, adjust quality thresholds in OpenAI evaluation Benefits Reduces translation time by 90%, eliminates manual quality checks through automated validation Here are clear, professional subheadings for each What / Why pair. They’re concise, action-oriented, and fit well in technical workflow documentation.
by Cheng Siong Chin
How It Works Scheduled processes retrieve customer feedback from multiple channels. The system performs sentiment analysis to classify tone, then uses OpenAI models to extract themes, topics, and urgency indicators. All processed results are stored in a centralized database for trend tracking. Automated rules identify high-risk or negative sentiment items and trigger alerts to the relevant teams. Dashboards and workflow automation then visualize insights and support follow-up actions. Setup Instructions Data Sources: Connect social media APIs, survey tools, and customer support platforms. AI Analysis: Configure the OpenAI API with sentiment and theme-extraction prompts. Database: Set up a feedback storage schema in your utility database. Alerts: Configure email notifications and CRM triggers for priority issues. Dashboards: Link your analytics and reporting tools for real-time insights. Prerequisites Social media/survey API credentials; OpenAI API key; database access; CRM system credentials; email notification setup Use Cases Customer sentiment tracking; product feedback aggregation; support ticket prioritization; brand monitoring; trend identification Customization Adjust sentiment thresholds; add new feedback sources; modify categorization rules Benefits Reduces analysis time 85%; captures actionable insights; enables rapid response to issues
by DIGITAL BIZ TECH
AI-Powered Timesheet → Invoice Automation (Gmail + OCR + AI + Google Sheets + QuickBooks) > Note: This workflow uses sticky notes extensively to document each logical section of the automation. Sticky notes are mandatory and already included to explain OCR, AI parsing, folder logic, duplicate handling, and QuickBooks steps. This workflow automates the full lifecycle of timesheet-based invoicing — from emailed timesheets to structured Google Sheets records and finalized invoices in QuickBooks Online. It is designed for real-world billing scenarios, including split weeks across months, zero-hour months, duplicate prevention, and first-week-of-year edge cases. What This Workflow Does Listens to Gmail for timesheet emails with attachments Splits and processes each attachment independently Extracts text using OCR (no hardcoded API keys) Uses AI to parse month-wise billable hours Correctly splits weeks spanning multiple months Looks up Customer and PO details from Google Sheets Organizes files in Client → Employee → Year folders in Google Drive Reuses existing invoice sheets or creates new ones Prevents duplicate invoice rows Automatically finds or creates customers in QuickBooks Creates invoices in QuickBooks using validated data High-Level Workflow Stages Gmail Intake and Attachment Loop OCR Text Extraction AI-Based Timesheet Parsing Month Normalization and Validation Customer & PO Lookup Drive Folder Discovery and Creation Invoice Sheet Reuse or Creation Duplicate and Edge-Case Handling Append Invoice Rows to Google Sheets Create / Update Customers in QuickBooks Create Invoices in QuickBooks Each of these stages is clearly documented with sticky notes inside the workflow canvas. Quick Setup Instructions Import the workflow JSON into your n8n instance Configure credentials for: Gmail Google Drive Google Sheets OpenAI or Google Gemini QuickBooks Online Verify the OCR HTTP node: Default URL: https://universal-file-to-text-extractor.vercel.app/extract No hardcoded API keys are used Configure Get Customer Info From PO Sheet: Spreadsheet ID Sheet name and column mappings Ensure the Client Invoices root folder exists in Google Drive Send a test timesheet email Execute the workflow once manually Activate the workflow Who This Workflow Is For Agencies and consultancies billing from emailed timesheets Finance and operations teams using Google Workspace + QuickBooks Staffing firms with monthly or bi-weekly contractor billing Teams that want a fully auditable, zero-manual invoice process Requirements n8n instance Gmail account receiving timesheet emails Google Drive and Google Sheets OpenAI or Google Gemini API OCR API endpoint (configurable) QuickBooks Online account Customer PO Google Sheet containing: Email Customer Name Company Name Customer Account Number PO Number Item Folder Name Invoice range Due Date Calculation How It Works (Detailed) 1. Email Intake and Attachment Loop Gmail Trigger polls for timesheet emails Attachments are split so each file is processed independently Sticky notes explain the intake and loop logic 2. OCR Extraction Each attachment is sent to the OCR API PDFs and images are converted to plain text OCR logic is documented via sticky notes 3. AI Timesheet Parsing (Month-Wise) AI extracts data only from BILLABLE HOURS sections Outputs strict JSON: Employee Name Client Name Month Year Week Start Date Week End Date Total Billable Hours Special handling included: Split weeks across months Zero-hour months still included No guessed or inferred dates 4. Month Normalization and Validation AI output is normalized into a month array Each month is processed independently Invalid or zero-hour entries are skipped 5. Customer and PO Lookup Sender email is matched in the PO sheet Retrieved values drive: Folder structure Invoice logic Due date calculation 6. Google Drive Folder Structure The workflow enforces a strict hierarchy: Client Invoices └── Client └── Employee └── Year Missing folders are created automatically. 7. Invoice Sheet Naming and Search Sheet names are generated using: Employee Name Month Year Existing sheets are reused when found Supports monthly and 15-day billing cycles 8. Duplicate Prevention and Edge Cases Duplicate invoice rows are detected and skipped January first-week edge case is handled explicitly Safe re-runs are supported 9. Google Sheets Invoice Rows Each appended row includes: Customer Account Number Invoice Date Due Date PO Number Item Name Quantity (Total Hours) Period description 10. QuickBooks Integration Searches for existing customers in QuickBooks Creates customers automatically if missing Creates invoices using: Customer reference Item Quantity Invoice date Due date All QuickBooks logic is documented with sticky notes. How To Customize Swap AI model (OpenAI ↔ Gemini) Extend prompts to extract: Project Cost center Approval status Add tax codes, currency, or unit pricing Modify folder naming rules Insert approval steps before invoice creation Common Use Cases Monthly contractor invoicing Agency billing across multiple clients Finance automation with audit-ready records Eliminating manual timesheet-to-invoice work Troubleshooting | Issue | Likely Cause | |------|-------------| | No invoices created | Gmail filter mismatch or email already read | | OCR output empty | Unsupported file or OCR endpoint issue | | Wrong month split | Review AI prompt and month logic | | Duplicate rows | Duplicate detection conditions | | Invoice missing in QuickBooks | Customer or item configuration issue | Notes on Community Guidelines Sticky notes are used throughout the workflow No hardcoded API keys are present Markdown is used (no HTML tags) This workflow is original and not copied Need Help or Customization? Digital Biz Tech can help tailor this workflow to your business. We offer free setup support, including credential configuration and deployment. Contact: rajeet.nair@digitalbiz.tech Website: https://www.digitalbiz.tech LinkedIn: https://www.linkedin.com/company/digital-biz-tech/ You can also DM us on LinkedIn for any help. You can also DM us on LinkedIn.
by Milo Bravo
Event Registration + Auto-Enrichment Intelligence Who is this for? Event organizers, conference planners, and marketing teams fighting registration drop-off who want 4-field forms with LinkedIn-level attendee intelligence. What problem is this workflow solving? Multi-page forms kill conversions: 80-90% drop-off on page 2 No attendee insights post-reg Manual enrichment wastes hours Abandoned carts = lost revenue This captures 4 fields but enriches 15+ data points automatically. What this workflow does 3 Webhook Intelligence Suite: POST /event-registration**: 4-field form → enrichment → HubSpot POST /reg-beacon**: Abandoned cart tracking pixel POST /validate-promo**: AJAX promo code validation Requires 2 sub-workflows: 1) Abandoned Cart Recovery 2) Participant Re-engager Enrichment Waterfall: Clearbit → LinkedIn (Proxycurl) → Google+AI → Full profile Outputs: HubSpot contacts with company/role/title Data Tables: enriched_profiles / reg_analytics Slack alerts + email confirmations Setup (12 minutes) Data Tables**: enriched_profiles, reg_analytics, promo_codes HubSpot**: API key + custom properties APIs**: Clearbit, Proxycurl, SerpAPI, Gemini Host**: reg-page/index.html (update webhook URLs) SMTP/Slack**: Notifications Fully configurable, no code changes needed. How to customize to your needs Forms**: Swap HTML for Typeform/Webflow Enrichment**: Add Apollo/Hunter for emails CRM**: HubSpot → Salesforce → Airtable Promos**: Tiered discounts / early-bird Companion**: Abandoned Cart + Re-engager templates ROI: 3x registration completion** (4 fields vs 12+) 65% enriched profiles** (company/role/title) 20% revenue recovery** (abandoned carts) Need help customizing?: Contact me for consulting and support: LinkedIn / Message Keywords: event registration, attendee enrichment, abandoned cart recovery, conference automation, HubSpot
by Incrementors
Description Submit your video topic, target audience, video length, and tone of voice using a simple form and two sequential AI agents do the rest. The first writes a complete structured video script with hook, three content sections, conclusion, and call to action. The second generates the full SEO metadata package: an optimized title, three alternative titles, a full YouTube description with hashtags, 15 tags, and timestamped chapters. Everything arrives in one clean Gmail email ready to record and upload. Built for YouTube creators, video marketers, and SEO agencies who want a complete production-ready video package in minutes instead of hours. What This Workflow Does Writes a full structured video script** — GPT-4o-mini produces a complete spoken script with hook, introduction, three named content sections with examples and tips, conclusion, and call to action Generates an optimized YouTube title** — Produces a main title under 60 characters with the primary keyword, plus three alternative titles at curiosity, number, and question angles Creates a full YouTube description** — Writes a description under 250 words with a keyword-rich hook, learning points, call to action, and relevant hashtags Produces 15 mixed tags** — Generates a balanced mix of short and long keywords all relevant to the topic and channel niche Builds timestamped chapters** — Creates chapters spaced evenly across your video length starting at 0:00, ready to paste directly into YouTube Delivers everything in one Gmail** — Script, title options, tags, chapters, and description all arrive in a single clearly sectioned plain-text email Setup Requirements Tools Needed n8n instance (self-hosted or cloud) OpenAI account with GPT-4o-mini API access Gmail account (the account you want to receive the content package) Credentials Required OpenAI API key (used in 4. OpenAI — Script Model GPT-4o-mini and 7. OpenAI — SEO Model GPT-4o-mini) Gmail OAuth2 > ⚠️ OpenAI API key appears in 2 steps — connect it in both 4. OpenAI — Script Model GPT-4o-mini and 7. OpenAI — SEO Model GPT-4o-mini Estimated Setup Time: 10–15 minutes Step-by-Step Setup Import the workflow — Open n8n → Workflows → Import from JSON → paste the workflow JSON → click Import Fill in Config Values — Open node 2. Set — Config Values → replace all three placeholders: | Field | What to enter | |---|---| | PASTE_YOUR_EMAIL_HERE | The email address where the content package should be sent | | PASTE_YOUR_NAME_HERE | Your name for the email greeting and sign-off | | PASTE_YOUR_CHANNEL_NICHE_HERE | Your channel's topic area (e.g. personal injury law, SaaS marketing, medical aesthetics) — GPT uses this to personalize both the script and metadata | Connect OpenAI for the script step — Open node 4. OpenAI — Script Model GPT-4o-mini → click the credential dropdown → add your OpenAI API key → test the connection Connect OpenAI for the SEO step — Open node 7. OpenAI — SEO Model GPT-4o-mini → click the credential dropdown → select the same OpenAI API credential → confirm it is connected Connect Gmail — Open node 10. Gmail — Send Content Package → click the credential dropdown → add Gmail OAuth2 → sign in with the Gmail account where you want to receive packages → authorize access Activate the workflow — Toggle the workflow to Active → copy the Form URL from node 1. Form — YouTube Content Request → open it in a browser to submit your first video How It Works (Step by Step) Step 1 — Form: YouTube Content Request You open the form URL in a browser and fill in five fields: the video topic, target audience, video length (e.g. "8 minutes"), tone of voice (optional, defaults to "educational and engaging"), and your name. Submitting the form starts the workflow immediately. Step 2 — Set: Config Values Your email, sender name, channel niche, and all five form inputs are stored here. Today's date is auto-generated for the email subject. Tone of voice defaults to "educational and engaging" if left blank on the form. Step 3 — AI Agent: Write Video Script GPT-4o-mini receives the video topic, target audience, video length, tone of voice, and channel niche. It writes a complete spoken video script in plain English with no bullet points or markdown. The structure is fixed: a 30-second hook with 3–4 punchy sentences, a short introduction paragraph, three named content sections each with 2–3 paragraphs, a conclusion summarizing the three key takeaways, and a 2-sentence call to action asking viewers to like, subscribe, and comment. Step 4 — OpenAI: Script Model GPT-4o-mini This is the language model powering the script writing step. It runs at temperature 0.7 for creative, natural-sounding spoken language and is capped at 2,000 tokens to accommodate a full-length video script. Step 5 — Set: Save Script and Config The completed script is saved from the previous step's output. All nine config values — email, name, niche, topic, audience, length, and today's date — are explicitly re-carried forward here so the SEO agent has full context. This bridge step is necessary because n8n agents pass their output to the next step, not the full context from earlier in the workflow. Step 6 — AI Agent: Generate SEO Package GPT-4o-mini receives the video topic, target audience, channel niche, and video length. It returns five structured fields: a main YouTube title under 60 characters, an array of three alternative titles (one curiosity angle, one number angle, one question angle each under 60 characters), a full description under 250 words with keyword hook, learning points, call to action, and hashtags, an array of 15 keyword tags mixing short and long tail terms, and an array of timestamped chapter objects spaced evenly across the video length starting at 0:00. Step 7 — OpenAI: SEO Model GPT-4o-mini This is the language model powering the SEO metadata step. It runs at temperature 0.3 for precise, consistent output — lower than the script step because metadata needs to be accurate and structured, not creative. Step 8 — Parser: Structured SEO Output This step enforces the exact five-field schema GPT-4o-mini must return for the SEO package. It validates that title, alternativeTitles, description, tags, and chapters are all present and correctly typed before the email is assembled. Step 9 — Code: Build Email The SEO output and the saved script are combined into one complete plain-text email. The email is organized into clearly labeled sections: topic summary header, main title and three alternative titles, all 15 tags as a comma-separated list, chapters as timestamp-title pairs, the full description, and the complete video script. The email subject is automatically set to "YouTube Content Package — [main title] — [today's date]". Step 10 — Gmail: Send Content Package The complete email is sent to your configured email address with no attribution footer. One email contains everything needed to record, upload, and optimize the video. Key Features ✅ Two specialized AI agents in sequence — Script writing and SEO metadata are handled by separate GPT instances with different temperatures so each task is optimized independently ✅ Script temperature tuned for creativity — The script agent runs at 0.7 so the language sounds natural and spoken, not robotic or like a list ✅ SEO metadata temperature tuned for precision — The metadata agent runs at 0.3 so titles stay under 60 characters, chapters start at 0:00, and tag arrays are clean ✅ Channel niche personalizes both outputs — Your niche is passed to both agents so the script examples and the SEO keywords stay relevant to your actual audience ✅ Structured output enforced for metadata — A schema parser validates all five SEO fields before the email is built — no broken or incomplete packages ✅ Chapters spaced to your video length — The chapters step reads your submitted video length and distributes timestamps evenly so chapters actually match the content structure ✅ Single email with every deliverable — Script, titles, tags, chapters, and description all arrive in one email with clear section headers — ready to copy-paste into your recording notes and YouTube upload form ✅ Tone defaults to educational if blank — Leaving the Tone of Voice field empty on the form triggers a sensible default instead of failing the workflow Customisation Options Change the script structure — In node 3. AI Agent — Write Video Script, edit the structure instructions to add or remove sections — for example replace "Section 3 — common mistake" with "Section 3 — case study example" to change the content format for your channel style. Add a Google Docs save alongside the Gmail — After node 9. Code — Build Email, add a Google Docs step that creates a new document with the email body — giving you a permanent editable copy in Drive alongside the email delivery. Generate a shorter script for YouTube Shorts — Add a second form field option for "Short format (under 60 seconds)" and branch after step 2 — if the video length is under 60 seconds, route to a shorter prompt in the AI Agent that writes just a hook and one main point. Send the package to a Slack channel — After node 10. Gmail — Send Content Package, add a Slack step that posts the main title, first alternative title, and today's date to a #youtube-content channel so your team sees new packages without checking email. Increase script length for longer videos — In node 4. OpenAI — Script Model GPT-4o-mini, raise maxTokens from 2000 to 3000 to allow GPT to write a more detailed script for 15–20 minute videos — useful for in-depth tutorial formats. Troubleshooting Form submission not starting the workflow: Confirm the workflow is Active — inactive workflows do not receive form submissions Copy the Form URL fresh from node 1. Form — YouTube Content Request after activating — URLs copied before activation will not work Make sure Video Topic, Target Audience, and Video Length are all filled in — these three fields are required Script agent not generating content: Confirm the OpenAI API key is connected in node 4. OpenAI — Script Model GPT-4o-mini and your account has available credits Check the execution log of node 3. AI Agent — Write Video Script for the raw GPT response If maxTokens is too low for your video length, the script may be cut off — increase from 2000 to 2500 in node 4 SEO package missing fields or failing schema validation: Confirm the OpenAI API key is connected in node 7. OpenAI — SEO Model GPT-4o-mini — this is a separate credential connection from node 4 Check the execution log of node 6. AI Agent — Generate SEO Package for the raw GPT response — the schema parser in node 8. Parser — Structured SEO Output will flag which fields are missing or wrong format If chapters are empty, the video length you submitted may be ambiguous — use a clear format like "8 minutes" or "10 minutes" Gmail not sending the package: Confirm the Gmail OAuth2 credential in node 10. Gmail — Send Content Package is connected and authorized Check that PASTE_YOUR_EMAIL_HERE in node 2. Set — Config Values is replaced with your actual email address Check your spam or promotions folder on the first send — automated Gmail OAuth2 emails sometimes land there Email arriving with missing sections or garbled content: Check the execution log of node 9. Code — Build Email — if seoOutput is null the step throws an error Confirm node 5. Set — Save Script and Config successfully carried the videoScript field forward — check its output in the execution log to confirm the script text is present before the SEO agent runs Support Need help setting this up or want a custom version built for your team or agency? 📧 Email: info@incrementors.com 🌐 Website: https://www.incrementors.com/
by Cheng Siong Chin
How It Works This workflow automates platform trust and safety operations by deploying a multi-agent AI system that detects abuse signals, investigates behaviour, scores risk, checks policy compliance, and enforces actions automatically. Designed for platform safety teams, content moderation managers, and compliance officers, it eliminates manual triage delays and ensures high-severity violations are actioned immediately. An abuse signal webhook triggers behaviour analysis via OpenAI, classifying signals by severity. A routing node directs cases to a Governance Agent, which orchestrates Investigation, Risk Scoring, and Policy Compliance Checker sub-agents. Enforcement data is prepared, then routed by action type-logging to abuse records, alerting the security team via Slack, sending escalation emails, or triggering auto-enforcement actions based on threshold checks—before all outcomes are logged. Setup Steps Configure Abuse Signal Webhook URL and authenticate incoming POST requests. Add OpenAI API credentials to all OpenAI Model nodes. Connect Google Sheets for abuse records and enforcement action logging. Configure Slack credentials and set security team alert channel. Add Gmail/SMTP credentials to Send Escalation Email node. Prerequisites Slack workspace with bot token Gmail or SMTP credentials Google Sheets for abuse and enforcement logging Use Cases Real-time abuse detection and auto-suspension on social platforms Customization Replace OpenAI with Anthropic Claude or NVIDIA NIM models Benefits Eliminates manual abuse triage with real-time AI signal processing
by Abdullah
Daily Cyber News Digest to Telegram Workflow Created By: Abdullah Dilshad 📧 iamabdullahdishad@gmail.com Stay informed with automated daily summaries. This workflow aggregates cyber news from multiple trusted sources, uses AI to intelligently select and summarize the top 5 most relevant articles, and delivers a clean, concise digest directly to your Telegram chat every morning at 10:00 AM. What This Workflow Does Collects Data: Fetches cybersecurity news from multiple global APIs. Filters Noise: Uses AI to discard irrelevant updates. Summarizes: Generates short, professional summaries (1–2 sentences). Delivers: Automatically sends a formatted digest to Telegram within message length limits. How It Works Schedule Trigger Runs automatically every day at 10:00 AM (customizable). News Collection Fetches articles using the keyword "cyber" from: GNews NewsAPI Data Processing Merges articles from both sources into a single, unified dataset. AI-Powered Selection OpenAI analyzes all fetched articles. Intelligently selects the Top 5 most relevant cybersecurity stories. Smart Summarization Each article is condensed into 1–2 clear sentences. Includes: Publication date, Source name, and Article link. Telegram Delivery Sends a clean, formatted digest to your specified Telegram chat. Ensures the total message length stays under Telegram’s 4096-character limit. Setup Instructions Get API Keys Sign up for free API keys from GNews.io and NewsAPI.org. Connect Accounts Add your Telegram and OpenAI credentials in n8n. Configure Telegram Enter your Telegram Chat ID in the "Send a Text Message" node. Customize the Schedule Change the trigger time if you prefer delivery at a different hour. Customization & Use Cases This workflow is fully reusable and scalable. You can replace the keyword "cyber" to track any topic relevant to your needs. Example Topics: 🤖 Artificial Intelligence (AI) 💰 Cryptocurrency & Blockchain 🚀 Startups & Venture Capital 📱 Consumer Technology 🏭 Industry-specific updates Note: This workflow is designed to be adapted for individual tracking, team updates, or competitor analysis.
by Le Nguyen
How it works Runs every morning at 8:00 using the Schedule Trigger. Sets a stale_days value and queries Salesforce for Opportunities where Stage_Unchanged_Days__c equals that value and the stage is not Closed Won / Closed Lost. For each “stale” Opportunity, loads full deal details and sends them to an OpenAI model. The model uses the query_soql tool to pull recent Notes, the primary Contact, and the Opportunity Owner, then returns a single JSON object with: a personalized follow-up email for the client, a short SMS template, a concise Slack summary for the sales team, and a ready-to-use Task payload for Salesforce. n8n parses that JSON, sends the email via SMTP, posts the Slack message to your chosen channel, and creates a Salesforce Task assigned to the Opportunity Owner so every stalled deal has a clear next step. Setup steps Estimated setup time: ~30–45 minutes if your Salesforce, OpenAI, SMTP and Slack credentials are ready. Create Stage_Unchanged_Days__c on Opportunity (Salesforce) Field Type: Formula (Number, 0 decimal places) Formula: IF( ISBLANK(LastStageChangeDate), TODAY() - DATEVALUE(CreatedDate), TODAY() - DATEVALUE(LastStageChangeDate) ) This field tracks how many days the Opportunity has been in the current stage. Connect credentials in n8n Salesforce OAuth2 for the Salesforce nodes and the query_soql HTTP Tool. OpenAI (or compatible) credential for the “Message a model” node. SMTP credential for the customer email node. Slack credential for the internal notification node. Configure your follow-up rules In Edit Fields (Set), set stale_days to the threshold that defines a stalled deal (e.g. 7, 14, 30). In Perform a query, optionally refine the SOQL (record types, owners, minimum amount, etc.) to match your pipeline. Update the Send Email SMTP Customer node with your real “from” address and tweak the wording if needed. Point Send Message To Internal Team (Slack) to the right channel or user. Test safely Turn off the Schedule Trigger and run the workflow manually with a few test Opportunities. Inspect the AI output in Message a model and Parse JSON to confirm the structure (email, sms, slack, task.api_body). Check that the email and Slack messages look good and that Salesforce Tasks are created, assigned to the right Owner, and linked to the correct Opportunity. Go live Re-enable the Schedule Trigger. Monitor the first few days to confirm that follow-ups, Slack alerts, and Tasks all behave as expected, then let the automation quietly keep your pipeline clean and moving.
by isaWOW
Automatically publish blog content to WordPress with AI-generated branded images, internal linking, and client reporting using Google Sheets, OpenAI, and Gemini What this workflow does This workflow receives written blog content from your content creation automation and handles the complete WordPress publishing process. It adds internal links to your content based on target keywords, generates 3 AI-powered branded images (thumbnail + 2 content images), uploads them to WordPress, inserts them into your article, publishes the complete blog with proper categories, updates tracking sheets, and notifies clients automatically. Perfect for agencies managing multiple client blogs who want to eliminate manual publishing tasks while maintaining brand consistency and SEO optimization. Key features Intelligent internal linking: Automatically analyzes your target keywords and adds up to 3 natural anchor links within the content to improve site SEO and user navigation AI image generation: Creates 3 professional branded images using DALL-E based on your blog topic and brand colors - one thumbnail with overlay text and two supporting content images Automated WordPress publishing: Publishes blogs with proper categories, sets featured images, and handles all WordPress REST API interactions without manual intervention Multi-client management: Processes different projects based on individual client settings including image preferences, brand colors, and reporting requirements Tracking and reporting: Updates Google Sheets with live URLs and publish dates, sends Discord notifications to project managers, and triggers client reporting workflows How it works Receives content from writing automation: Triggered by your blog content creation workflow with title, body content, focus keyword, and client details Fetches project configuration: Loads client-specific settings from Google Sheets including website URL, WordPress API credentials, image creation preferences, and brand guidelines Adds internal links: Retrieves target keywords and URLs from project sheets, filters valid links, and uses Gemini AI to intelligently insert 3 contextual anchor links Generates branded images (if enabled): Uses OpenAI GPT to create detailed image prompts based on blog topic and brand colors, then generates 3 images with DALL-E (thumbnail with text overlay + 2 content images) Uploads to WordPress media library: Processes each image through a loop, uploads to WordPress, stores metadata including URLs and alt text Inserts images into content: Uses Gemini AI to intelligently place images at strategic positions within the article while preserving existing HTML structure and anchor links Publishes to WordPress: Creates the blog post with proper title, content, categories, and sets the thumbnail as featured image via REST API Updates tracking sheets: Records the live blog URL and publish date in Google Sheets for project management Sends notifications: Triggers Discord alerts for project managers and executes the Reporting Manager workflow for client communication via email, Slack, or WhatsApp Setup requirements Tools you'll need: Active n8n instance (self-hosted or n8n Cloud) Google Sheets with OAuth access for project management WordPress site with REST API enabled and proper authentication OpenAI API key (for DALL-E image generation) Google Gemini API key (for content processing) Discord bot (optional, for team notifications) Blog Content Creation workflow (Part 1 - sold separately or built independently) Estimated setup time: 30-40 minutes Configuration steps Add credentials in n8n: Google Sheets OAuth API OpenAI API (for DALL-E image generation) Google Gemini API (for AI content processing) Discord Bot API (for notifications) WordPress credentials (API tokens) Set up Project Central Sheet: Create a master Google Sheet with these columns: Client ID Website URL Blog API (WordPress auth token) GMB Name (business name) Image Creation (Yes/No) Image Instructions (specific image guidelines) Color and Font (brand colors in hex format) Discord Channel ID Project Manager Discord ID On Page Sheet (URL to client's tracking sheet) Project Information Sheet (URL to internal linking keywords sheet) Categories (WordPress category IDs) Update the sheet URL in the "Fetch Project Configuration" node Create client-specific sheets: For each client, maintain two sheets: Sheet 1: TGT Keywords (for internal linking) Keywords column: Target keywords to link Target Pages column: Full URLs to link to Sheet 2: Content Requirement & Posting (for tracking) row_number: Unique identifier Focus Keyword: Target SEO keyword Content Topic: Blog title Publish URLs: Live blog URL (auto-filled) Published Date: Publish date (auto-filled) Configure WordPress authentication: Enable REST API on your WordPress site Generate API authentication tokens Update authorization values in these nodes: "Upload to WordPress Media" "Publish Blog with Featured Image" "Set Thumbnail as Featured Image" "Publish Blog without Images" Connect to Blog Creation workflow: Ensure your Blog Content Creation workflow (Part 1) triggers this workflow The trigger should pass these workflow inputs: Client ID Blog S.NO. (row number) Blog Title Content (HTML formatted) OnPage SEO (tracking sheet URL) Focus Keyword Set up Reporting Manager (optional): Create or connect your client reporting workflow Update the workflow ID in "Trigger Client Reporting Workflow" node This sends automated reports to clients via email, Slack, or WhatsApp Test the workflow: Run your Blog Creation workflow manually with test data Verify images generate correctly with brand colors Check WordPress post publishes with featured image Confirm tracking sheet updates Test Discord notification delivery Use cases Marketing agencies: Manage blog publishing for 10+ clients with different brand guidelines and WordPress sites from a single automation Content teams: Eliminate 2-3 hours of manual work per blog by automating image creation, internal linking, and WordPress publishing SEO specialists: Ensure consistent internal linking and proper category assignment across all published content Freelance writers: Offer end-to-end blog services including branded image creation and WordPress publishing without manual intervention SaaS companies: Maintain consistent blog publishing schedule across multiple product blogs with automated tracking and reporting Customization options Modify image generation: Edit the "Generate Image Prompts with AI" node to change image style, dimensions, or prompt instructions Change DALL-E model or image size in "Generate Image with DALL-E" node Adjust internal linking: Modify the "Add Internal Links to Content" agent prompt to change linking strategy (more/fewer links, different placement rules) Change notification channels: Replace Discord with Slack, email, or webhook notifications Add multiple notification channels in parallel WordPress customization: Add custom fields, tags, or metadata to published posts Integrate with WordPress plugins via REST API extensions Troubleshooting Images not generating: Check OpenAI API key validity and account credits. Verify image prompt node receives content properly. WordPress publish fails: Confirm REST API is enabled, authentication tokens are correct, and site URL is properly formatted with trailing slash. Internal links not appearing: Ensure "TGT Keywords" sheet has valid URLs starting with "http" and filter node is working correctly. Tracking sheet not updating: Verify Google Sheets OAuth connection and that row_number matches between sheets. Discord notification fails: Check Discord bot permissions and channel ID accuracy. Resources n8n documentation WordPress REST API guide OpenAI DALL-E API Google Gemini API Google Sheets API Important notes This workflow is specifically for blog publishing. To use it correctly, you must first have a Blog Content Creation workflow that generates the blog title, content, and required metadata. I have already shared a Blog Writing Automation workflow, which you can use directly for content creation before running this publishing workflow. Make sure the content creation workflow runs before this publishing workflow, as this setup depends on the generated output. Support Need help or custom development? 📧 Email: info@isawow.com 🌐 Website: https://isawow.com/