Workflow Templates

This n8n workflow is the data ingestion pipeline for the "RAG System V2" chatbot. It automatically monitors a specific Google Drive folder for new files, processes them based on their type, and inserts their content into a Supabase vector database to make it searchable for the RAG agent. Key Features & Workflow: Google Drive Trigger: The workflow starts automatically when a new file is created in a designated folder (named "DOCUMENTS" in this template). Smart File Handling: A Switch node routes the file based on its MIME type (e.g., PDF, Excel, Google Doc, Word Doc) for correct processing. Multi-Format Extraction: PDF: Text is extracted directly using the Extract PDF Text node. Google Docs: Files are downloaded and converted to plain text (text/plain) and processed by the Extract from Text File node. Excel: Data is extracted, aggregated, and concatenated into a single text block for embedding. Word (.doc/.docx): Word files are automatically converted into Google Docs format using an HTTP Request. This newly created Google Doc will then trigger the entire workflow again, ensuring it's processed correctly. Chunking & Metadata Enrichment: The extracted text is split into manageable chunks using the Recursive Character Text Splitter (set to 2000-character chunks). The Enhanced Default Data Loader then enriches these chunks with crucial metadata from the original file, such as file_name, creator, and created_at. Vectorization & Storage: Finally, the workflow uses OpenAI Embeddings to create vector representations of the text chunks and inserts them into the Supabase Vector Store.

How to use the provided n8n workflow (step‑by‑step), what matters, what it’s good for, and costs per run. What this workflow does (in simple terms) 1) You write (or speak) your idea in Telegram. 2) The workflow builds two short prompts: Image prompt → generates one thumbnail via KIE.ai – Nano Banana (Gemini 2.5 Flash Image). Video prompt → starts a Veo‑3 (KIE.ai) video job using the thumbnail as init image. 3) You receive the thumbnail first, then the short video back in Telegram once rendering completes. Typical output: 1 PNG thumbnail + 1 short MP4 video (e.g., 8–12 s, 9:16). Why this is useful Rapid ideation**: Turn a quick text/voice idea into a ready‑to‑post thumbnail + matching short video. Consistent look: The video uses the thumbnail as **init image, keeping colors, objects and mood consistent. One chat = full pipeline**: Everything happens directly inside Telegram—no context switches. Agency‑ready**: Collect ideas from clients/team chats, and deliver outputs quickly. What you need before importing 1) KIE.ai account & API key Sign up/in at KIE.ai, go to Dashboard → API / Keys. Copy your KIE_API_KEY (keep it private). 2) Telegram Bot (BotFather) In Telegram, open @BotFather → command /newbot. Choose a name and a unique username (must end with bot). Copy your Bot Token (keep it private). 3) Your Telegram Chat ID (browser method) Send any message to your bot so you have a active chat Open Telegram web and the chat with the bot Find the chatid in the URL Import & minimal configuration (n8n) 1) Import the provided workflow JSON in n8n. 2) Create Credentials: Telegram API: paste your Bot Token. HTTP (KIE.ai): usually you’ll pass Authorization: Bearer {{ $env.KIE_API_KEY }} directly in the HTTP Request node headers, or make a generic HTTP credential that injects the header. 3) Replace hardcoded values in the template: Chat ID: use an Expression like {{$json.message.chat.id}} from the Telegram Trigger (prefer dynamic over hardcoded IDs). Authorization headers: never in query params—always in Headers. Content‑Type spelling: Content-Type (no typos). ` How to run it (basic flow) 1) Start the workflow (activate trigger). 2) Send a message to your bot, e.g. glass hourglass on a black mirror floor, minimal, elegant 3) The bot replies with the thumbnail (PNG), then the Veo‑3 video (MP4). If you send a voice message, the flow will download & transcribe it first, then proceed as above. Pricing (rule of thumb) Image (Nano Banana via KIE.ai):* ~ *$0.02–$0.04** per image (plan‑dependent). Video (Veo‑3 via KIE.ai):** Fast: $0.40 per 8 seconds ($0.05/s) Quality: $2.00 per 8 seconds ($0.25/s) Typical run (1 image + 8 s Fast video) ≈ $0.42–$0.44. > These are indicative values. Check your KIE.ai dashboard for the latest pricing/quotas. Why KIE.ai over the “classic” Google API? Cheaper in practice** for short video clips and image gen in this pipeline. One vendor** for both image & video (same auth, similar responses) = less integration hassle. Quick start**: Playground/tasks/status endpoints are n8n‑friendly for polling workflows. Security & reliability tips Never hardcode* API keys or Chat IDs into nodes—use *Credentials* or *Environment variables**. Add IF + error paths after each HTTP node: If status != 200 → Send friendly Telegram message (“Please try again”) + log to admin. If you use callback URLs for video completion, ensure the URL is publicly reachable (n8n Webhook URL). Otherwise, stick to polling. For rate limits, add a Wait node and limit concurrency in workflow settings. Keep aspect & duration consistent across prompt + API calls to avoid unexpected crops. Advanced: voice input (optional) The template supports voice via a Switch → Download → Transcribe (Whisper/OpenAI). Ensure your OpenAI credential is set and your n8n instance can fetch the audio file from Telegram. Example prompt patterns (keep it short & generic) Thumbnail prompt**: “Minimal, elegant, surreal [OBJECT], clean composition, 9:16” Video prompt**: “Cinematic [OBJECT]. slow camera move, elegant reflections, minimal & surreal mood, 9:16, 8–12s.” You can later replace the simple prompt builder with a dedicated LLM step or a fixed style guide for your brand. Final notes This template focuses on a solid, reliable pipeline first. You can always refine prompts later. Start with Veo‑3 Fast to keep iteration costs low; switch to Quality for final renders. Consider saving outputs (S3/Drive) and logging prompts/URLs to a sheet for audit & analytics. Questions or custom requests? 📩 suliemansaid.business@gmail.com

📜 Detailed n8n Workflow Description Main Flow The workflow operates through a three-step process that handles incoming chat messages with intelligent tool orchestration: Message Trigger: The When chat message received node triggers whenever a user message arrives and passes it directly to the Knowledge Agent for processing. Agent Orchestration: The Knowledge Agent serves as the central orchestrator, registering a comprehensive toolkit of capabilities: LLM Processing: Uses Anthropic Chat Model with the claude-sonnet-4-20250514 model to craft final responses Memory Management: Implements Postgres Chat Memory to save and recall conversation context across sessions Reasoning Engine: Incorporates a Think tool to force internal chain-of-thought processing before taking any action Semantic Search: Leverages General knowledge vector store with OpenAI embeddings (1536-dimensional) and Cohere reranking for intelligent content retrieval Structured Queries: Provides structured data Postgres tool for executing queries on relational database tables Drive Integration: Includes search about any doc in google drive functionality to locate specific file IDs File Processing: Connects to Read File From GDrive sub-workflow for fetching and processing various file formats External Intelligence: Offers Message a model in Perplexity for accessing up-to-the-minute web information when internal knowledge proves insufficient Response Generation: After invoking the Think process, the agent intelligently selects appropriate tools based on the query, integrates results from multiple sources, and returns a comprehensive Markdown-formatted answer to the user. Persistent Context Management The workflow maintains conversation continuity through Postgres Chat Memory, which automatically logs every user-agent exchange. This ensures long-term context retention without requiring manual intervention, allowing for sophisticated multi-turn conversations that build upon previous interactions. Semantic Retrieval Pipeline The semantic search system operates through a sophisticated two-stage process: Embedding Generation**: Embeddings OpenAI converts textual content into high-dimensional vector representations Relevance Reranking**: Reranker Cohere reorders search hits to prioritize the most contextually relevant results Knowledge Integration**: Processed results feed into the General knowledge vector store, providing the agent with relevant internal knowledge snippets for enhanced response accuracy Google Drive File Processing The file reading capability handles multiple formats through a structured sub-workflow: Workflow Initiation: The agent calls Read File From GDrive with the selected fileId parameter Sub-workflow Activation: When Executed by Another Workflow node activates the dedicated file processing sub-workflow Operation Validation: Operation node confirms the request type is readFile File Retrieval: Download File1 node retrieves the binary file data from Google Drive Format-Specific Processing: FileType node branches processing based on MIME type: PDF Files: Route through Extract from PDF → Get PDF Response to extract plain text content CSV Files: Process via Extract from CSV → Get CSV Response to obtain comma-delimited text data Image Files: Analyze using Analyse Image with GPT-4o-mini to generate visual descriptions Audio/Video Files: Transcribe using Transcribe Audio with Whisper for text transcript generation Content Integration: The extracted text content returns to Knowledge Agent, which seamlessly weaves it into the final response External Search Capability When internal knowledge sources prove insufficient, the workflow can access current public information through Message a model in Perplexity, ensuring responses remain accurate and up-to-date with the latest available information. Design Highlights The workflow architecture incorporates several key design principles that enhance reliability and reusability: Forced Reasoning**: The mandatory Think step significantly reduces hallucinations and prevents tool misuse by requiring deliberate consideration before action Template Flexibility: The design is intentionally generic—organizations can replace **[your company] placeholders with their specific company name and integrate their own credentials for immediate deployment Documentation Integration**: Sticky notes throughout the canvas serve as inline documentation for workflow creators and maintainers, providing context without affecting runtime performance System Benefits With this comprehensive architecture, the assistant delivers powerful capabilities including long-term memory retention, semantic knowledge retrieval, multi-format file processing, and contextually rich responses tailored specifically for users at [your company]. The system balances sophisticated AI capabilities with practical business requirements, creating a robust foundation for enterprise-grade conversational AI deployment.

Summary: This n8n workflow addresses the manual and cumbersome process of exporting handwritten notes from Kindle devices, such as the Kindle Scribe. It is designed to automate the extraction of the note's PDF download link from an email and subsequently save the file to your Google Drive. The Problem Kindle devices that support handwritten notes (e.g., Kindle Scribe) allow users to export a notebook as a PDF file. However, there is no centralized repository or automated export function. The current process requires the user to: Manually request an export for each file on the device. Receive an auto-generated email containing a temporary, unique download URL (rather than the attachment itself). This manual process represents a significant vendor lock-in challenge and a poor user experience. How This Workflow Solves It This template automates the following steps: Email Ingestion: Monitors your Gmail account for the specific export email from Amazon. Link Extraction: Utilizes an LLM service (like DeepSeek, or any other suitable large language model) to accurately parse the email content and extract the unique PDF download URL. PDF Retrieval & Storage: Executes a request to the extracted URL to download the PDF file and then uploads it directly to your Google Drive. Prerequisites To implement and run this workflow, you will need: Kindle Device: A Kindle model that supports handwritten notes and PDF export (e.g., Kindle Scribe). Gmail Account: The account configured on your Kindle device to receive the export emails. LLM Account: Access to an LLM API (e.g., DeepSeek, OpenAI, etc.) to perform the necessary text extraction. Google Drive Credentials: Configured n8n credentials for your Google Drive account. This workflow is designed for easy and quick setup, providing a reliable, automated solution for backing up your valuable handwritten notes.

This n8n workflow ensures data freshness in the RAG system by handling modifications to existing files. It complements the "Document Ingestion" workflow by triggering whenever a file in the monitored Google Drive folder is updated. This "delete-then-re-insert" process ensures the RAG agent always has access to the most current version of your documents. Key Features & Workflow: Update Trigger: The workflow activates using the File Updated trigger for the same Google Drive folder ("DOCUMENTS"). Duplicate Run Prevention: An If node cleverly filters out immediate "update" events that are triggered by the "Upload Doc" workflow's Word-to-Google-Doc conversion, preventing unecessary duplicate runs. Delete Old Entries: Once a genuine update is detected, the workflow's first action is to find and delete all existing vector chunks associated with that file_id from the Supabase "documents" table. Smart Versioning: It then retrieves the old version number from the deleted metadata and uses an OpenAI node (Set Version) to intelligently increment it (e.g., "v1" becomes "v2"). Re-Ingestion Pipeline: The updated file is then processed through the exact same logic as the "Upload Doc" workflow: It is routed by a Switch node based on its MIME type (PDF, Google Doc, Excel, etc.). Text is extracted, chunked, and embedded. The Enhanced Default Data Loader enriches these new chunks with metadata, including the new, incremented version number. Insert New Entries: Finally, the newly processed and versioned chunks are inserted back into the Supabase Vector Store.

AI Carousel Caption & Template Editor Workflow Overview This workflow is a caption-only carousel text generator built in n8n. It turns any raw LinkedIn post or text input into 3 short, slide-ready title + subtext captions and renders those captions onto image templates. Output is a single aggregated response with markdown image embeds and download links. Workflow Structure Input:** Chat UI trigger accepts text and optional template selection. Core AI:** Agent cleans input and returns structured JSON with 3 caption pairs. Template Rendering:** Edit Image nodes render title and subtext on chosen templates. Storage:** Rendered images uploaded to S3. Aggregate Output:** Aggregate node builds final markdown response with embeds and download links. Chat Trigger (Frontend) Trigger:** When chat message received UI accepts plain text post. allowFileUploads optional for template images. SessionId preserved for context. AI Agent (Core) Node name:** AI Agent Model:** Mistral Cloud Chat Model (mistral-small-latest) Behavior:** Clean input (remove stray formatting like \n and ** but keep emojis). Produce exactly one JSON object with fields: postclean, title1, subtext1, title2, subtext2, title3, subtext3. Titles must be short (max 5 words). Subtext 1 or 2 short sentences, max 7 words per line if possible. Agent must return valid JSON to be parsed by the Structured Output Parser. Structured Output Parser Node name:** Structured Output Parser Validates agent JSON and prevents downstream errors. If parsing fails, stop and surface error. Normalize Title Nodes Nodes:** normalize title,name 1, normalize title,name 2, normalize title,name 3 (and optional 4) Map parsed output into node fields: title, subtext, safeName (safe filename for exports). Template Images Source:** Google Drive template PNGs (download via Google Drive nodes) or provided upload. Keep templates high resolution and consistent aspect ratio. Edit Image Nodes (Render Captions) Nodes:** Edit Image 1, Edit Image2, Edit Image3, Edit Image3 (or Edit Image3/Edit Image4 as available) MultiStep operations render: Title text (font, size, position) Subtext (font, size, position) This is where caption text is added to the template. Upload to S3 Nodes:** S3 Upload rendered images to bucketname using safeName filenames. Confirm public access or use signed URLs. Get S3 URLs and Aggregate Nodes:** get s3 url image 1, get s3 url image 2, get s3 url image 3, get s3 url image 4 Merge + Aggregate:** Merge1 and Aggregate collect image items. Output Format:** output format builds a single markdown message: Inline image embeds `` Download links per image. Integrations Used | Service | Purpose | Credential | |---------|---------|-----------| | Mistral Cloud | AI agent model | Mistral account | | Google Drive | Template image storage | Google Drive account | | S3 | Store rendered images and serve links | Supabase account | | n8n Core | Flow control, parsing, image editing | Native | Agent System Prompt Summary > You are a data formatter and banner caption creator. Clean the user input (remove stray newlines and markup but keep emojis). Return a single JSON object with postclean, title1/subtext1, title2/subtext2, title3/subtext3. Titles must be short (max 5 words). Subtext should be 1 to 2 short sentences, useful and value adding. Respond only with JSON. Key Features Caption only output: 3 short slide-ready caption pairs. Structured JSON output enforced by a parser for reliability. Renders captions onto image templates using Edit Image nodes. Uploads images to S3 and returns markdown embeds plus download links. Template editable: swap Google Drive background templates or upload your own. Zero guess formatting: agent must produce parseable JSON to avoid downstream failures. Summary A compact n8n workflow that converts raw LinkedIn text into a caption-only carousel with rendered images. It enforces tight caption rules, validates AI JSON, places captions on templates, uploads images, and returns a single ready-to-post markdown payload. Need Help or More Workflows? We can wire this into your account, replace templates, or customize fonts, positions, and export options. We can help you set it up for free — from connecting credentials to deploying it live. Contact: shilpa.raju@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.

Automated Databricks Data Querying & SQL Insights via Slack with AI Agent & Gemini Node-by-Node Explanation This workflow is divided into three functional phases: Initialization, AI Processing, and Response Delivery. | Node Name | Category | What it does | | :--- | :--- | :--- | | When Slack Message Received | Trigger | Monitors a Slack channel for @mentions. It captures the user's question and the thread ID to keep the conversation organized. | | Set Databricks Config | Configuration | A "helper" node where you hardcode your Databricks warehouse_id and target_table. This makes it easy to update settings in one place. | | Fetch Databricks Schema | Data Retrieval | Sends a DESCRIBE command to the Databricks API. It learns what columns exist (e.g., "price", "date", "store_id") so the AI knows what it can query. | | Parse Table Schema | Data Transformation | Uses JavaScript to clean up the raw Databricks response. it converts complex technical data into a simple list that the AI can easily read. | | SQL Data Analyst Agent | AI Brain | The "manager" of the workflow. It takes the user's question and the table schema, decides which SQL query to write, and interprets the results. | | Gemini Model | LLM Engine | Provides the actual intelligence (using Google Gemini 3.1 Flash). This is what "thinks" and generates the SQL and conversational text. | | Redis Chat Memory | Memory | Stores previous messages in the thread. This allows you to ask follow-up questions (e.g., "Now show me only the top 5") without repeating the whole context. | | Run Primary SQL Query | AI Tool | An HTTP tool given to the Agent. The Agent "calls" this node to actually run the generated SQL on Databricks and get the real data back. | | If Output Valid | Logic Gate | A safety check. It verifies if the Agent successfully produced a message for Slack or if something went wrong during the process. | | Post to Slack Channel | Output (Success) | Sends the final answer (e.g., "The total revenue for Q3 was $4.2M") back to the user in Slack. | | Post Error to Slack | Output (Failure) | If the SQL fails or the AI hits a wall, this node sends an error message to the user so they aren't left waiting. | How the "Agent" Loop Works Unlike a standard linear workflow, the SQL Data Analyst Agent doesn't just move to the next step. It performs a "Reasoning" loop: Observe: "The user wants to know sales for March." Think: "I have a table called 'franchises' with a 'sale_date' column. I should run a SUM query." Act: It triggers the Run Primary SQL Query node. Observe Results: "The query returned 150,000." Final Response: "The total sales for March were 150,000."

This workflow automatically creates daily backups of all n8n workflows and stores them in Google Drive, using the n8n API to export workflows and a scheduled retention policy to keep storage organized. The automation runs in two stages: backup and cleanup. Daily Backup Process A Schedule Trigger runs at a defined time each day. The workflow creates a folder in Google Drive using the current date. It calls the n8n API to retrieve the list of all workflows. Each workflow is processed individually and converted into a .json file. The files are uploaded to the daily backup folder in Google Drive. This ensures that every workflow is safely stored and versioned by date. Automatic Cleanup A second scheduled process maintains storage hygiene: The workflow lists all backup folders in the Google Drive root directory. It checks the folder creation date. Any folder older than the defined retention period (default 15 days) is automatically deleted. This prevents unnecessary storage usage while keeping recent backups easily accessible. Key Features Automated daily workflow backups Uses n8n API to export workflows Files stored in Google Drive Automatic retention cleanup Fully documented with sticky notes inside the workflow Uses secure credentials (no hardcoded API keys) Setup Configuration takes only a few minutes: Connect a Google Drive OAuth credential Define the Google Drive root folder ID for backups Configure n8n API credentials securely Adjust: Backup schedule Retention period (default 15 days) Once configured, the workflow will run automatically, creating daily backups and removing old ones without manual intervention.

Who is this for This template is for investigators, real estate professionals, recruiters, and sales teams who need to skip trace individuals -- finding current addresses, phone numbers, and emails from a name, phone, or email address. It is ideal for anyone who needs to enrich a list of contacts with verified location and contact data at scale. How it works You configure a list of names (or phones/emails) in the setup node. The workflow submits a skip trace job to the ScraperCity People Finder API and captures the run ID. An async polling loop checks the job status every 60 seconds until it returns SUCCEEDED. Once complete, the results are downloaded, parsed from CSV, and written row by row to Google Sheets. How to set up Add your ScraperCity API key as an HTTP Header Auth credential named "ScraperCity API Key". Open the "Configure Search Inputs" node and replace the placeholder names with your target list. Open the "Save Results to Google Sheets" node and set your Google Sheet document ID and sheet name. Click Execute to run. Requirements ScraperCity account with People Finder access (app.scrapercity.com) Google Sheets OAuth2 credential connected to n8n How to customize the workflow Switch the search input from names to phone numbers or emails by editing the JSON body in "Start People Finder Scrape". Increase or decrease max_results in the request body to control how many matches are returned per person. Add a Filter node after CSV parsing to keep only results with a confirmed phone number or address.

How it works This workflow lets you search for leads using FullEnrich's People Search API directly from Monday.com, then auto-fills the results as new items on your board. A Monday.com automation sends a webhook when a new item is created on your "search criteria" board The workflow responds to Monday.com's challenge handshake, then calls FullEnrich's People Search API with the criteria from your Monday.com columns (job title, industry, location, company size, number of results) The search results are split into individual people and each one is created as a new item on your Monday.com "results" board with their name, title, company, domain, LinkedIn URL, and location Set up steps Setup takes about 15 minutes: Monday.com "Search Criteria" board — Create a board with these columns: Job Title (text), Industry (text), Location (text), Company Size (text), Number of Results (number). Note down the column IDs Monday.com "Results" board — Create a board with columns for: First Name, Last Name, Job Title, Company Name, Company Domain, LinkedIn URL, Location. Note down the board ID, group ID, and column IDs Monday.com automation — On your search criteria board, create an automation: When item created → send webhook to the production URL from the "Monday.com Webhook" node FullEnrich — Connect your FullEnrich API credentials Monday.com — Connect your Monday.com API credentials Column mapping — Update the column IDs in the HTTP Request body and in the Monday.com node to match your boards Activate the workflow

Automated multilingual article publishing from RSS feeds to WordPress using ACF Instalations Instructions Youtube Instalation Instructions # Who’s it for This workflow is built for news publishers, media organizations, and content aggregators who need to automatically: pull articles from RSS feeds rewrite them into original text translate them into multiple languages generate a featured image publish everything directly to WordPress. It is ideal for multilingual news portals, editorial teams with limited resources, and businesses that want to automate high-volume content production. How it works The workflow monitors a selected RSS feed at regular intervals and retrieves new article links. It scrapes each article’s HTML and uses AI to extract structured text: title full content and a short summary. The text is then rewritten into an original article tailored to your target audience’s language and country context. Next, the workflow translates the rewritten article into any number of additional languages while preserving the formatting. It also generates a unique AI-based featured image, uploads it to WordPress, assembles multilingual ACF fields, and publishes the final post with the correct metadata. How to set up Insert your RSS feed URL, add your OpenAI and Replicate API keys, configure your WordPress API credential, and ensure the ACF fields on your site match the workflow’s naming structure. Requirements WordPress with REST API enabled ACF WP Plugin installed OpenAI API key Replicate API key Firebase API Key How to customize the workflow Adjust the RSS source, modify the default language and list of translated languages, change the rewriting style or country context, refine the image generation prompt, or remap ACF fields to match your WordPress layout.

📌Who is this for? This workflow is designed for engineering teams, project managers, and IT operations who need consistent visibility into team availability across multiple projects. It’s perfect for organizations that use Odoo for leave management and Redmine for project collaboration, and want to ensure that everyone involved gets timely, automated Slack notifications whenever a team member will be absent the next day. 📌The problem When team members go dark, everything grinds to a halt. You're stuck with: Last-minute meeting reschedules (and frustrated stakeholders) Tasks assigned to people who aren't there No time to redistribute workload Bottlenecks affecting multiple projects 📌How it works Runs daily at 17:15 - Set it and forget it. Executes every afternoon, giving teams time to prepare. Fetches Tomorrow's Approved Leaves from Odoo - Pulls all leave records with tomorrow's start date and "approved" status. Maps Employee & Project Data - Grabs the employee's details and identifies every Redmine project they're assigned to. Finds All Teammates on the Same Projects - Deduplicates across overlapping projects to avoid notification spam. Sends Targeted Slack Notifications - Only notifies people who actually work with the absent member, plus optional manager alerts. 📌Quick setup Before you start, you’ll need: Odoo API key Redmine API key Slack Bot Token (or Incoming Webhook URL) Subflows need to be created within a new flow; the main flow will call these subflows. 📌Results What changes immediately: Zero surprises - teams know absences 24 hours ahead Workload rebalancing happens before the person goes off Managers make proactive decisions, not reactive ones No more wasted Slack messages to irrelevant people This creates a more predictable and transparent workflow across your engineering and project teams. 📌Take it further Ready to supercharge it? Add: Auto-assign backup owners for critical tasks Sync absences to Google Calendar/Outlook Log notifications to a database for auditing Conditional alerts (key roles, high-priority projects only) Daily summary digest of all upcoming absences 📌Need help customizing? Contact me for consulting and support: Linkedin / Website