Solutions Showcase: part 3 of 7
The complete text of the site in 7 parts. Parts:
Part 1 has the contents list of every section and case study.
Case studies in full
Automated Transcription Workflow Between Box and Rev.com
Automating audio and video transcription submissions, transcript delivery, and file tracking using Zapier.
Section: Zapier Automations
Overview
Audio and video files stored in Box previously required manual retrieval, transcription submission, order tracking, and document storage. Two connected Zapier workflows now submit eligible files to Rev.com, track pending orders, and deliver completed transcripts back to their corresponding Box folders.
The Problem
Teams handling recordings in Box need to submit files for transcription and keep track of each request until the transcript is ready. Manually retrieving files, creating transcription orders, checking their status, and uploading completed documents involves repetitive work. It can also become difficult to keep the original recording, transcription order, and completed document connected to the correct client folder.
How It Works
- Detect New Files: A Box webhook triggers the workflow when a new file is received.
- Filter Media Files: Zapier checks the file extension and allows supported formats such as WAV, MP4, MP3, OGG, and M4A.
- Retrieve the File: Webhooks obtain Box API access, and Code by Zapier generates the source file's download link.
- Submit for Transcription: The download link is sent to Rev.com to create an automated transcription order.
- Save Order Details: Zapier Tables stores the order ID, client reference, pending status, and folder information.
- Log Source Information: Google Sheets records the original filename, Box file ID, parent folder ID, and download link.
- Check Pending Orders: A second workflow runs daily at 9 PM and retrieves pending records from Zapier Tables.
- Verify Transcription Status: The workflow checks each order through the Rev.com API and identifies orders marked Complete or Delivered.
- Retrieve the Transcript: The automation locates the transcript attachment and prepares a Word document filename.
- Deliver the Document: The completed transcript is uploaded to its associated Box folder. Conditional paths handle orders that are not ready or have been canceled.
Results & Metrics
The two workflows separate transcription submission from transcript delivery, so the initial file-processing workflow does not need to wait for Rev.com to finish the transcription.Pending orders are tracked in Zapier Tables, while Google Sheets maintains source-file details. Once a transcript is marked Complete or Delivered, the automation retrieves the Word document and places it in the associated Box folder.
Tech Stack
| Tool | Role in the Workflow |
|---|
| Zapier | Coordinates both automations, scheduling, filters, loops, and conditional paths. |
| Box | Stores the original media files and receives completed transcripts. |
| Rev.com API | Handles transcription submissions, order-status checks, and transcript retrieval. |
| Webhooks | Communicate with the Box API for authentication and file access. |
| Code by Zapier | Generates download links, extracts order IDs, checks status, and prepares filenames. |
| Zapier Tables | Stores pending transcription orders and related references. |
| Google Sheets | Maintains source-file details and download-link records. |
The team can continue using its existing Box, Rev.com, and Google Sheets setup without moving to a new document-management platform.
Where This Pattern Applies
This solution is not limited to transcription services. The same approach can be used wherever incoming files need to be processed by an external service and returned to the correct record or folder.
Example — Legal Services: Audio recordings of client interviews can be submitted for transcription, tracked until completion, and returned to the relevant case folder in document storage.
Other applications include:
- Healthcare: Process consultation recordings and store completed transcripts.
- Recruitment: Transcribe interviews and attach documents to candidate records.
- Insurance: Process recorded client statements and organize transcripts with claim files.
- Education: Transcribe lectures and store documents by course or session.
- Customer Support: Process recorded calls and attach transcripts to support records.
The general pattern is to detect an incoming file, submit it for processing, track its status, retrieve the completed output, and return it to the correct destination. The external service, matching rules, and storage platform change according to the business process.
Page · Plain text
Automated LoanPro Reporting & Accounts Receivable Monitoring
Automating weekly client forecasting and overdue-account reporting with Zapier, LoanPro, Calendly, and Microsoft Outlook.
Section: Zapier Automations
Overview
Preparing weekly client forecasts and monitoring overdue loan accounts previously required information to be collected and reviewed across multiple systems. The solution uses Zapier to retrieve calendar and LoanPro data, apply business rules, calculate relevant figures, and deliver structured reports through Microsoft Outlook.
The Problem
Financial reporting requires teams to review calendar events, match clients with loan records, and identify overdue balances. These details are spread across different systems, making manual reporting repetitive and difficult to maintain. Smaller outstanding balances can also be overlooked when accounts are reviewed individually. A consistent process was needed to organize client forecasts and highlight qualifying overdue accounts.
How It Works
- Start Scheduled Reporting: Zapier triggers the reporting automations according to their weekly schedules.
- Retrieve Calendar Information: Microsoft Outlook provides calendar events, while Calendly supplies additional scheduled event information.
- Process Meeting Details: JavaScript extracts client information, processes event dates, and prepares records for matching.
- Match Client Records: The workflow searches LoanPro for corresponding customer records using available names and email addresses.
- Retrieve Loan Information: The LoanPro API provides customer, loan, and account details, including outstanding balances and days past due.
- Apply Reporting Rules: JavaScript evaluates client and loan information against configured qualification conditions.
- Group Smaller Balances: Individual amounts below $500 are combined by client, and clients reaching the $500 threshold are included in the report.
- Calculate Report Figures: The automation calculates flagged entries, total amounts due, and principal balances, and sorts the results by days past due.
- Generate Reports: The processed information is formatted into structured HTML reports containing summary figures and relevant account details.
- Deliver Reports: Microsoft Outlook sends the generated reports to the configured recipients.
Results & Metrics
The reporting solution provides visibility into upcoming client engagements and overdue loan accounts through structured email reports.
The available report show:
| Metric | Observed Result |
|---|
| Upcoming items in firm forecast | 4 |
| Active loan accounts reviewed | 280 |
| Flagged receivable entries | 151 |
| Total amount due | $352,715.29 |
| Total principal balance | $220,674.10 |
Note: These figures reflect the current report data and may change from day to day as new calendar events and loan account information are updated.
Tech Stack
| Tool | Role in the Workflow |
|---|
| Zapier | Coordinates scheduled automation and connects the different processing steps. |
| LoanPro API | Retrieves customer, loan, and account information. |
| Calendly API | Provides scheduled event information for client forecasting. |
| Microsoft Outlook | Retrieves calendar events and delivers generated reports by email. |
| JavaScript | Processes API responses, matches records, calculates balances, applies reporting rules, and generates HTML reports. |
The team can continue using its existing calendar, loan-management, and email applications without changing its day-to-day tools.
Where This Pattern Applies
This solution is not limited to financial reporting. The same approach can help businesses collect information from different systems, match records, apply business rules, and deliver scheduled reports.
Example — Insurance: An automation can retrieve policy and claims data, identify overdue payments, group balances by customer, and prepare a weekly outstanding-payment report.
Other applications include:
- Banking: Monitor overdue loan payments and customer balances.
- Healthcare: Prepare scheduled patient-account and payment reports.
- Legal Services: Match client appointments with case records and generate summaries.
- Property Management: Identify overdue rent and prepare tenant payment reports.
- Sales Operations: Combine scheduled meetings with customer records and prepare pipeline reports.
The general pattern is to retrieve information from connected systems, match records, apply qualification rules, calculate relevant figures, and deliver structured reports. The data sources, business rules, and reporting format change according to the business process.
Page · Plain text
Automated NetSuite to ShipStation Order Processing
Automation that sends eligible NetSuite sales orders to ShipStation, prepares shipping details, and updates order status automatically.
Section: Make Automations
Overview
This solution connects NetSuite with ShipStation through Make. It identifies eligible sales orders, prepares their customer, address, item, and shipping details, creates the corresponding orders in ShipStation, and updates NetSuite to record processing.
The Problem
Sales orders are managed in NetSuite, while shipment preparation takes place in ShipStation. Transferring order details between the two systems requires staff to enter customer information, billing and shipping addresses, line items, quantities, prices, and shipping services.
This repetitive work takes time and creates opportunities for incorrect item details, shipping selections, or incomplete order records. Teams also need a reliable way to identify which orders and line items have already been processed.
How It Works
The solution uses a Make scenario to handle the order-processing workflow.
- Monitor sales orders. Make watches a configured NetSuite saved search for sales orders that have been modified.
- Check order eligibility. The workflow checks whether the order is marked to be sent to ShipStation and has not already been marked as created there.
- Retrieve order details. It fetches the complete sales order, including customer information, billing and shipping addresses, dates, totals, and line items.
- Prepare order information. The workflow collects the order details and processes its line items, including item names, descriptions, quantities, and prices.
- Format item data. OpenAI converts the NetSuite line-item data into the structure required by the ShipStation API.
- Identify the shipping service. The workflow reads the shipping method from the order items and maps it to the corresponding ShipStation service code. If no method is available, it uses the configured Ground default.
- Create the ShipStation order. An HTTP request sends the prepared customer, address, item, payment, tax, and shipping information to ShipStation.
- Update NetSuite records. After the order-creation step succeeds, the workflow updates the NetSuite sales order and marks the relevant line items as processed.
The Result
The automation connects order entry with shipment preparation, reducing the need to manually transfer sales order information between NetSuite and ShipStation. It prepares item and shipping details, creates ShipStation orders, and records processing status back in NetSuite. This helps reduce repetitive data entry and keeps order-processing records aligned across both systems.
Daily Automation
| Metric | Observed Output |
|---|
| Emails processed | 7/day (average) |
| Successful runs | 96/day |
| Run frequency | 15 minutes |
| Success rate | 100% |
| Execution time | 1.5 seconds |
Note:Metrics are based on the observed execution history and may vary depending on order activity and processing time.
Tech Stack
- Make: Runs the automation and coordinates order processing, routing, data preparation, and conditional operations.
- NetSuite: Provides sales orders, customer details, addresses, item information, and shipping data.
- ShipStation: Receives and manages sales orders for shipment processing.
The solution works with the existing NetSuite and ShipStation setup, without requiring teams to replace their systems or learn a new order-management platform.
Where This Pattern Applies
This approach connects order records with downstream fulfilment activities, ensuring that information is transferred, processed, and tracked automatically.
Imagine a wholesale business receiving customer orders through its ERP system. The automation collects the order details, formats product and shipping information, sends the order to its fulfilment platform, and updates the original record once processing is complete.
The same pattern can be adapted to:
- E-commerce: Transfer online orders into shipping and fulfilment platforms.
- Wholesale: Process bulk customer orders and prepare shipment records.
- Manufacturing: Send production orders to operational and dispatch systems.
- Retail: Coordinate store orders with warehouse fulfilment.
- Logistics: Transfer shipment details between order and transport systems.
- Healthcare Supply: Coordinate medical supply orders with distribution systems.
The reusable pattern remains the same: monitor incoming orders, validate eligibility, prepare structured data, send it to the fulfilment platform, and update the original system to reflect processing.
Page · Plain text
From Manual Filing to Automatic Document Intake
Automation that turns incoming documents into filed, logged, and findable records, without anyone watching an inbox.
Section: Zapier Automations
Overview
Documents used to arrive, sit in an inbox, and wait for someone to notice them, open them, and put them where they belonged. Now they file themselves correctly, every time, with a record left behind.
The Problem
A document lands in someone’s inbox, and for a while, nobody knows it is there. Maybe it is the filing that should have gone out yesterday. Maybe it is the one that got missed last month, found only after a client called asking where it went. Every day comes down to one person checking an inbox, guessing what matters, and hoping nothing slips through. One missed email is the difference between on time and in real trouble.
How It Works
The automation sits where the person used to sit, watching the inbox, and runs through the same checks in the same order, without getting tired or distracted partway through:
- Watch for the right emails. It recognizes incoming filings by sender and subject, and ignores everything else.
- Confirm there’s actually something attached. No attachment, no work to do. It moves on instead of acting on an empty notification.
- Pull out what matters. The case number, the subject, and the attachment itself are lifted out of the email automatically.
- Log it immediately. Before anything else happens, the document is recorded in a running sheet, so there’s a timestamped record that it arrived, even before it’s filed.
- Check for duplicates. It looks up whether this exact document has already been filed, so the same thing doesn’t get added twice.
- Find the right home. It looks up the matching folder by case number. If that folder doesn’t exist, nothing gets misfiled into the wrong place.
- File it, and say so. The document is uploaded, and the log is updated to say whether it was newly added or already existed.
- Catch failures out loud. If any step fails, that failure is written into the log instead of disappearing silently, so nothing goes missing without someone knowing.
The Result
Nobody checks the inbox to find out whether a new filing came in. It is simply already in the right folder by the time anyone looks. The running log answers “did we get this?” on sight instead of requiring a search. Duplicate filings are caught automatically rather than relying on someone to notice a repeat. And when something does fail, it shows up in the log as a visible flag instead of quietly vanishing.
Tech Stack
- Microsoft Outlook: where the pleading emails arrive, sorted into a dedicated folder the automation watches.
- Zapier: runs the whole process in the background, handling each attachment separately when several pleadings come in one email.
- Google Sheets: the running log, with a row for every pleading showing its case number, file name, time received, and whether it was filed.
- Box.com: where each pleading lands, inside the folder that matches its case number.
Where This Pattern Applies
This isn’t really a story about legal filings. Picture the same automation watching a different inbox for a different business.
A supplier emails an order confirmation. The automation checks it has an attachment, pulls out the purchase order number instead of a case number, logs the confirmation the moment it lands, checks whether it’s already been recorded, finds the folder for that purchase order, and files it, flagging anything that doesn’t match a known order instead of losing track of it.
Swap “purchase order number” for whatever identifier matters in your world, and the same shape shows up everywhere:
- Insurance: claims, policy documents, adjuster reports
- Sales & legal: signed contracts, NDAs, pleadings, compliance acknowledgments
- HR & recruiting: onboarding paperwork, offer letters, background checks
- Finance & accounting: vendor invoices, receipts, expense reports, reconciliations
- Healthcare: patient intake forms, lab results, referral letters
- Real estate: leases, inspection reports, closing documents
- Logistics & supply chain: shipping confirmations, customs paperwork, delivery receipts
- Customer support: ticket attachments, warranty claims, return requests
- Government & permitting: applications, licenses, inspection filings
- Education: student applications, transcripts, enrollment forms
The shape never changes: watch, verify, extract, log, match the destination, file, confirm. What changes is only which number you’re matching against. Whatever industry it sits in, the win is the same. Nobody has to be the one remembering to check.
Page · Plain text
Support Email to ClickUp Ticket Automation
An automated support workflow that turns incoming customer emails into correctly routed ClickUp tickets, adds replies to existing tickets, and prevents duplicate tickets using n8n.
Section: n8n Automations, AI Agents for Ecommerce, ClickUp Setups
Overview
This solution automates support email handling for RefureTech. When a customer sends an email to the shared Gmail inbox, n8n reads the message, identifies the client using their email domain, and sends it to the correct ClickUp support list. If the client is unknown, the email goes to a default triage list. If the conversation already has a ticket, the new email is added as a comment instead. Attachments and previous messages are also included, giving the support team the full conversation in one place.
The business problem
Support requests arrived through a shared email inbox and had to be added to ClickUp manually. This took time and created a risk of assigning emails to the wrong client, missing attachments, or creating duplicate tickets. ClickUp also has its own email feature that handles customer replies, so a basic email-to-ticket automation could create duplicate tickets or process its own confirmation emails repeatedly.
The solution
A single n8n workflow polls the support inbox every minute. It looks up the client list stored in ClickUp, matches the sender by domain, checks four different ways whether the conversation already has a ticket or is already managed by ClickUp, and only then creates a ticket or comment. It uses plain, explainable rules in code nodes rather than an AI model, so every decision can be traced to a header, a subject line or a ClickUp field. Wherever a step could fail, the workflow prefers a duplicate ticket over a lost customer email.
How It Works
- Receive Support Emails: The Gmail Trigger checks the shared inbox every minute and retrieves new messages, including their attachments.
- Identify the Client: n8n checks the sender's email domain against the client information stored in ClickUp. Each client has a domain, folder ID, and support list ID.
- Check for Existing Tickets: The workflow searches for existing tickets using Gmail thread IDs and ClickUp email thread IDs. It also checks the full email conversation to identify related messages.
- Decide Where the Email Goes: The workflow uses routing rules to determine whether the email is a new request, a reply to an existing ticket, an unknown client request, or a message that should be skipped.
- Create a Ticket or Add a Comment: New requests are added to the correct client's support list. Emails from unknown clients go to the default triage list, while replies to existing tickets are added as comments.
- Upload Attachments: Email attachments are downloaded and uploaded to the related ClickUp ticket. Earlier messages in the conversation are also included where available.
- Prevent Duplicate Processing: The workflow skips ClickUp confirmation emails, messages already managed by ClickUp, and automatic replies such as out-of-office messages.
- Mark Emails as Processed: Successfully handled emails receive a
Ticketed label in Gmail. For new tickets, the workflow also waits two minutes and saves ClickUp's confirmation email thread ID for future matching.
The Result
The automation successfully manages incoming support emails, creates and routes ClickUp tickets, and adds replies to existing tickets. It also preserves attachments and email history while preventing duplicate tickets and unnecessary processing.
Automation Performance
| Metric | Result |
|---|
| Successful workflow executions | 11 |
| Successful execution rate | 100% |
| Failed executions | 0 |
| Total n8n nodes | 38 |
Tech Stack
- n8n: Manages the automation, email processing, routing rules, and duplicate checks.
- Gmail: Receives support emails, retrieves message threads and attachments, and labels processed messages.
- ClickUp: Stores client information, creates support tickets, adds comments, and manages attachments.
- JavaScript: Handles client matching, email validation, routing decisions, and duplicate checks.
- ClickUp API: Supports searches and operations that connect the workflow with ClickUp records.
Where This Pattern Applies
The same approach can be used by organizations that manage customer requests through shared email inboxes.
- IT Support Teams: Convert incoming technical support emails into tickets.
- Customer Service Teams: Route customer requests to the correct team or department.
- Managed Service Providers: Organize support requests across multiple clients.
- SaaS Companies: Track customer issues and follow-up conversations in one system.
- Operations Teams: Turn shared inbox requests into assigned and trackable tasks.
The general approach is to monitor a shared inbox, identify the customer, check for existing conversations, and automatically create or update the right ticket while keeping the full email history and attachments.
Page · Plain text
Automated NetSuite Billing and Shipment Processing
Automation that extracts invoice and shipment details from incoming emails, matches them with NetSuite records, and prepares shipment notifications.
Section: Make Automations
Overview
This solution connects Microsoft Outlook, OCR.space, OpenAI, and NetSuite through Make. It processes incoming billing emails and PDF attachments, extracts purchase order numbers, tracking IDs, and vendor information, matches the information with NetSuite transactions, and prepares shipment-related email notifications. It also sends an alert when OCR processing encounters an error.
The Problem
Billing teams manually review incoming emails, download invoices and shipment documents, extract key details, and match them with NetSuite records. This repetitive process takes time and increases the risk of missing information or incorrect transaction matching.
How It Works
The solution uses a Make scenario to process incoming billing emails and their attachments.
- Monitor Billing Emails. Microsoft Outlook watches the configured billing inbox for incoming messages.
- Apply Email Conditions. The workflow checks sender and subject details to determine which messages should proceed.
- Retrieve Attachments. It lists the available attachments and downloads the relevant files.
- Filter PDF Documents. PDF attachments proceed through the document-processing route, with a short delay before extraction.
- Extract Document Text. OCR.space processes the PDF and returns its extracted text.
- Handle OCR Errors. If the OCR request encounters an error, the workflow sends an email alert to the configured recipient.
- Prepare Extraction Inputs. The email preview and extracted PDF text are stored for further processing.
- Extract Purchase Order and Tracking Details. OpenAI identifies purchase order numbers and tracking IDs from the available email and document content.
- Identify Vendor Information. A separate OpenAI step extracts vendor details, and the returned information is parsed into structured fields.
- Search NetSuite Transactions. The workflow searches NetSuite for records matching the extracted information and retrieves the relevant transaction details.
- Prepare Item Information. Related transaction items are collected and processed into a structured list for the notification.
- Prepare Shipment Emails. The workflow combines the retrieved transaction, item, and shipment information to prepare the relevant email.
- Send Notifications. Microsoft Outlook sends the shipment-related email using the prepared information.
The Result
The automation connects incoming billing documents with the corresponding NetSuite records and shipment notifications. Instead of manually reviewing every email, downloading documents, extracting details, and searching transactions, the workflow handles these steps automatically. It also provides an email alert when OCR processing fails, helping the team identify document-processing issues.
| Metric | Result |
|---|
| Total executions | 164 |
| Successful executions | 158 |
| Success rate | ~95% |
| Average execution time | 17.15 seconds |
Note:Metrics are based on the available execution logs and may vary depending on email volume, attachment processing, and document complexity.
Tech Stack
Make: Coordinates the complete workflow, including email routing, attachment processing, data extraction, transaction matching, and error handling.
Microsoft Outlook: Monitors the billing inbox, retrieves email attachments, and sends shipment notifications and OCR error alerts.
OCR.space API: Extracts readable text from PDF attachments for further processing.
OpenAI: Extracts purchase order numbers, tracking IDs, and vendor information from email and document content.
NetSuite: Provides transaction and item records used to match extracted billing and shipment information.
JavaScript: Supports custom data processing and prepares structured item information for email notifications.
The team can continue using Outlook and NetSuite without replacing its existing email or business management systems.
Where This Pattern Applies
This is not limited to billing and shipment processing. Imagine an e-commerce business receiving supplier invoices, delivery documents, and tracking information through email. The automation extracts the relevant details, finds matching order records, and prepares the next notification without requiring someone to process every document manually.
The same approach can be adapted to:
- E-commerce: Order and shipment document processing
- Logistics: Delivery documents and tracking details
- Finance: Invoice and purchase order processing
- Procurement: Supplier document management
- Distribution: Shipment records and customer notifications
- Healthcare Supply: Medical supply invoices and delivery documentation
The reusable pattern remains the same: receive documents, extract information, identify relevant details, match existing records, and trigger the next action. What changes is the document type, the system being searched, and the action that follows.
Page · Plain text
Power BI: Turning Five Booking Systems Into One Revenue Engine
A governed Power BI model and two dashboards that replaced three days of manual owner-statement assembly with an automated daily refresh for a short-term rental portfolio.
Section: Power BI
Power BI Case Study
BnB Heaven: short-term rental & boutique B&B management · 6-week engagement
- 5 → 1: Systems unified
- ~90%: Less reporting effort
- Daily: Automated 06:00 refresh
- 6 wks: Concept to live rollout
BnB Heaven manages a portfolio of short-term rentals and boutique B&Bs across the UK. Bookings arrived from Airbnb, Booking.com, Vrbo and their own direct site; cleaning and turnovers lived in the ops tool; finance sat in the accounting system. Owner statements and the monthly board pack took three days to assemble by hand. This case study shows how we consolidated everything into one governed Power BI model with two dashboards, cutting reporting effort by roughly 90% and giving the team occupancy, rate and channel-profitability numbers they finally trust.
The Challenge
Before the project, 'how are we doing?' was a surprisingly hard question to answer. Three problems came up in every conversation with the team.
- Bookings scattered across platforms: Revenue lived in Airbnb, Booking.com, Vrbo and the direct site, with turnovers in the PMS and money in accounting. Nobody could see occupancy, nightly rate and net revenue in one place without exporting several files first.
- Owner statements ate three days a month: A manager rebuilt every owner statement and the board pack by hand (copy, paste, reconcile, repeat). By the time they were ready the numbers were weeks old, and one slip meant redoing the lot.
- No shared version of the truth: Channel profitability after platform fees was invisible. It wasn’t clear which channels actually paid off once commissions were taken out, so pricing and listing decisions were made on gut feel.
The Approach
Rather than bolt a chart onto each platform, we built one properly modelled layer underneath a small number of focused dashboards. Four phases over six weeks:
- Discovery & metric definitions (week 1): Workshops to agree exactly what occupancy, ADR, RevPAR and net-of-fees revenue mean (one signed-off definition each, so the model has a single source of truth).
- Connect & clean with Power Query (weeks 2–3): ETL into all five sources, standardised property and channel keys, and consistent handling of platform fees, refunds and cancellations so figures reconcile to the accounts.
- Star-schema model & DAX (weeks 3–4): A clean fact-and-dimension model with a shared date table, reusable DAX measures (occupancy, ADR, RevPAR, YoY, target) and row-level security so each owner sees only their own properties.
- Dashboards, refresh & handover (weeks 5–6): Two role-based dashboards, an on-premises gateway for the automated 06:00 refresh, plus training and a short written guide so the team can extend the model themselves.
The Solution
Executive overview
The board-level view answers leadership’s core questions on one screen: where revenue comes from, how occupancy and rate are trending, which properties and channels pull their weight, and whether the year is on target.
Image: Revenue & Occupancy: the executive overview page, live in Power BI Desktop, with KPIs, revenue trend, channel mix, property and location breakdowns and target attainment.
Operations & guests
The operations view is a daily working screen for the wider team: booking volume against occupancy, manager contribution, the direct-site booking funnel and guest satisfaction by location.
Image: Operations & Guest Experience: bookings vs occupancy, manager revenue, booking funnel and 5-star reviews by location.
- Cumulative revenue vs operating cost shows the margin gap at a glance.
- Channel donut exposes reliance on commission-heavy platforms vs direct.
- Top-property table ranks by revenue with live YoY growth flags.
- Gauge tracks progress against the £4.55M annual target (106%).
Under the Hood
| Layer | What We Built | Tools |
|---|
| Sources | Airbnb, Booking.com, Vrbo, direct site, PMS / channel manager, accounting | REST / API / file connectors |
| Ingest & clean | Dedupe, key standardisation, fee / refund / cancellation handling | Power Query (M) |
| Model | Star schema, shared date table, reusable measures | Power BI model + DAX |
| Governance | Row-level security by owner / manager, documented definitions | RLS roles |
| Delivery | Two role-based dashboards, automated daily refresh | Power BI Service + gateway |
The Results
- +5.6pts: Occupancy rate
- +0.14: Guest rating
- 3 days → 0: Manual reporting
- 106%: Of annual target
| Measure | Before | After |
|---|
| Owner statements & board pack | ~3 days, manual | Automatic, ready by 06:00 |
| Data freshness | ~3 weeks old | Refreshed daily |
| Channel profit (net of fees) | Invisible | Live, per channel |
| Sources reconciled | Manually, error-prone | Reconciled to accounts automatically |
With channel profitability visible net of platform fees, BnB Heaven leaned into direct bookings and trimmed commission-heavy inventory, finishing the year 6% ahead of target.
Page · Plain text
Automated P&L & Sales Tracker for Ecommerce (Google Sheets)
A single Google Sheets template that turns raw sales, COGS and marketing cost data into live real-vs-estimated profit numbers for any date range.
Section: Dashboards & Reporting
Project Overview
This project delivers an automated profit and loss (P&L) tracking solution for an ecommerce business. It consolidates sales, real COGS, marketing costs, and other expenses into a single spreadsheet-based reporting system.
The tracker calculates real and estimated profit automatically, allowing the team to review financial performance across different date ranges without rebuilding reports manually.
The Challenge
Ecommerce financial data can be spread across sales records, product costs, marketing expenses, and other operational costs. Combining these figures manually makes it harder to maintain an up-to-date view of profitability.
The main challenges included:
- Fragmented financial data: Sales, COGS, marketing spend, and other expenses needed to be considered together.
- Manual reporting: Profit and loss figures required repetitive calculations and reporting work.
- Limited visibility: Understanding real profit, estimated profit, and profit margins across different periods required a consolidated view.
- Date-range comparisons: Reviewing daily, monthly, and longer-term performance required flexible reporting.
The Solution
A reusable Google Sheets template was developed to bring the relevant financial figures into one reporting system and calculate profitability automatically.
The solution provides:
- Automated P&L calculations: Combines sales, COGS, marketing costs, and other expenses to calculate profit metrics.
- Real vs. estimated profit: Makes both measures available for financial review.
- Flexible date-range reporting: Allows the team to review performance for selected periods.
- Daily performance tracking: Presents sales, profit, and expense metrics for day-to-day monitoring.
- Monthly and rolling analysis: Supports longer-term performance reviews and expense breakdowns.
- Reusable template: The same template can be applied to different brands, with totals recalculated for the relevant data.
Key Dashboard Features
Finance & Sales Reporting
An automated profit & loss tracker built in Google Sheets for an ecommerce business. Pulling sales, real COGS, marketing spend and other expenses into one model, it calculates real vs. estimated profit automatically for any date range instead of being rebuilt by hand every month.
- $1.18M: Total sales (period)
- $54.6K: Total real profit
- 4.61%: Real profit margin
- $587K: Total marketing cost
Image: Monthly sales and profit dashboard: total sales, real/estimated profit, margins and marketing cost calculated automatically from raw order data.
Image: The same template applied to a different brand: totals, COGS and marketing cost recalculated instantly for any date range.
Daily and 30-day views
A daily dashboard view surfaces total and trailing-30-day sales, profit and expense metrics side by side, so the team can catch a bad week before it becomes a bad month.
Image: Daily dashboard: total and last-30-days sales, profit and expense metrics side by side for fast day-to-day monitoring.
Rolling breakdowns
A rolling 12-month view breaks total profit down into COGS, marketing cost, other expenses and disputes won, so the team can see exactly where margin is being gained or lost.
Image: Last-12-months pie chart breaking total profit down into COGS, marketing cost, other expenses and disputes won.
Built as a single Google Sheets template so finance reads live profit numbers for any date range without exporting from five different tools first.
Workflow
The workflow consolidates the available financial inputs, calculates the relevant profit and margin metrics, and presents the results through reporting views for different periods.
Technology Used
Google Sheets is the core platform used to organize the financial data, calculate P&L metrics, and display the dashboards.
The solution uses a reusable spreadsheet structure to support financial reporting across date ranges and brands.
Results and Business Value
The tracker brings key ecommerce financial metrics into one place and reduces the need to rebuild reports manually.
- Centralized financial visibility: Sales, profit, margins, COGS, and marketing costs can be reviewed together.
- Reduced manual reporting: Calculations and dashboard views are organized within a reusable template.
- Flexible analysis: The team can review performance across daily, monthly, and rolling periods.
- Consistent reporting: Different brands can use the same reporting structure.
- Improved financial oversight: Real and estimated profit figures help the team review financial performance.
Final Outcome
The Automated P&L & Sales Tracker provides an organized, reusable Google Sheets solution for ecommerce financial reporting. By bringing sales, costs, and profitability metrics into one place, it makes financial performance easier to review across selected date ranges and supports more consistent reporting for ecommerce operations.
Page · Plain text
AI Voice Agents for Lead Qualification and Customer Support
An AI voice automation system for Pine Street Code that instantly qualifies new leads, handles customer calls, and connects callers with human representatives when needed.
Section: n8n Automations, AI Agents
Overview
Pine Street Code wanted to improve lead response times and ensure customer calls were handled even when the team was unavailable. We developed two AI voice agents using ElevenLabs and n8n. Hazel automatically contacts new Meta leads within seconds, asks qualifying questions, and gathers project details. The second agent handles incoming customer calls when the team cannot answer. Both agents integrate with Thrive CRM and Slack for lead tracking and team notifications. A customer-facing application also allows the client to review call recordings and request improvements.
The Problem
Pine Street Code needed a way to respond to new Meta leads immediately and avoid losing potential customers to competitors. It also needed reliable coverage for incoming calls when staff were unavailable, without changing its existing business phone numbers.
How It Works
- Capture New Leads: When a prospect submits a Meta lead form, the n8n workflow receives the lead information and initiates the automated calling process.
- Immediate AI Follow-Up: Hazel, the AI lead qualification agent, contacts the prospect within approximately 5–10 seconds of form submission.
- Qualify Prospects: Hazel asks predefined qualifying questions, gathers project requirements, and captures relevant lead details using configured conditions and conversation instructions.
- Apply Conversation Guardrails: Hazel avoids making pricing commitments, disclosing sensitive business information, or making decisions reserved for human representatives.
- Notify the Team: Lead qualification details are sent to Slack so the team can review new opportunities and follow up when human involvement is needed.
- Track Leads in the CRM: The n8n workflows connect with the client's Thrive CRM, maintaining lead information and tracking progress through the pipeline until the opportunity is closed.
- Route Existing Business Calls: The second AI voice agent handles incoming calls through the business's existing phone numbers, allowing Pine Street Code to retain its established numbers.
- Activate Customer Support Agent: When an incoming call rings three times without being answered by the team, the call is routed to the AI customer support agent.
- Handle Customer Inquiries: The support agent responds to customer questions while following strict instructions that prevent unauthorized pricing commitments, disclosure of internal processes, or sharing sensitive business information.
- Provide Call Review: A customer-facing application allows the business to listen to recorded conversations and flag specific calls or interactions for changes and improvements.
Result
The solution connects lead acquisition, AI-powered qualification, customer support, and CRM tracking into one automated system.
- Faster lead response: Hazel initiates calls approximately 5–10 seconds after form submission.
- Automated qualification: Prospects are contacted and asked predefined questions to capture project requirements.
- Human-controlled decisions: Pricing and other sensitive commitments remain under human control.
- Improved call coverage: Incoming calls can be handled by the support agent when the business team does not answer after three rings.
- Centralized lead tracking: Lead progress is maintained in Thrive CRM through the final pipeline stage.
- Client visibility: The customer-facing application provides access to call recordings and a way to flag interactions for review.
Tech Stack
- ElevenLabs: Powers the AI voice agents, conversation handling, and voice interactions.
- n8n: Orchestrates lead processing, calling workflows, conditional logic, CRM updates, and notifications.
- Meta Lead Forms: Provides incoming prospect information from advertising campaigns.
- Thrive CRM: Tracks leads and their progress through the sales pipeline.
- Slack: Delivers lead qualification notifications to the business team.
- Customer-Facing Application: Allows clients to listen to calls and flag interactions for changes.
- Telephony Integration: Routes incoming business calls to the AI customer support agent while retaining existing phone numbers.
Where This Pattern Applies
The same approach can be adapted for businesses that need faster lead response and reliable phone support.
- Home Services: Contact new inquiries immediately and qualify project requirements.
- Real Estate: Follow up with property inquiries and identify serious prospects.
- Marketing Agencies: Qualify advertising leads and notify sales teams about opportunities.
- Healthcare: Handle routine appointment inquiries and route calls when staff are unavailable.
- Professional Services: Capture new client requirements and manage incoming service inquiries.
- Customer Support Teams: Provide automated call coverage outside busy periods.
The general pattern combines immediate AI-powered lead follow-up, structured qualification, automated customer call handling, and human oversight to help businesses respond faster and manage more conversations efficiently.
Page · Plain text
A Private AI Research Desk for Traders
A self-hosted AI research platform that searches a trader's private documents and videos, provides source citations, reads chart information, and runs trading strategy backtests.
Section: Custom SaaS Platforms
Overview
This project delivers a private AI assistant for an active trader working with ICT trading concepts. It combines document and video search, AI-powered answers, chart analysis, and a Python backtesting engine in one platform. The system runs on the client's own VPS, keeping their data, infrastructure, and operating costs under their control.
The Problem
The client's trading knowledge was spread across hundreds of hours of mentorship videos, PDFs, Pine Script references, and price-data spreadsheets. Finding specific explanations required manually searching through documents and videos, while testing strategies meant writing code from scratch.
General-purpose AI assistants were not reliable enough because they could mix outside information with the client's material or provide incorrect chart prices with confidence. The client needed a private system that could provide source-backed answers and perform real backtests using their own data.
How It Works
- Private AI Chat: Open WebUI provides a secure chat interface, with Caddy handling HTTPS and LiteLLM connecting the AI models.
- Document Processing: The FastAPI and Haystack services extract content from uploaded documents, divide it into searchable sections, generate embeddings, and store them in Qdrant.
- Video Processing: Videos are downloaded, transcribed, and analyzed using keyframes, OCR, and visual descriptions. The extracted information is indexed so users can search for specific explanations and chart moments.
- Intelligent Retrieval: The platform combines keyword and semantic search, reranks results, and filters out low-confidence matches. A query planner also rewrites natural-language questions into clearer search queries.
- Source-Based Answers: The AI answers using retrieved client materials and provides document-page or video-timestamp citations. Uncertain chart prices are marked rather than presented as confirmed values.
- Trading Backtesting: An isolated Python environment runs strategy backtests, parameter sweeps, indicators, ICT pattern detection, performance metrics, and chart exports.
- Administration and Monitoring: A Streamlit dashboard manages uploads, video processing, storage, costs, and restoration. Phoenix tracing and encrypted backups support monitoring and recovery.
The Result
The platform provides the client with a private workspace to search trading knowledge, review source materials, and test strategies. It also supports a shared knowledge base across different user accounts, allowing authorized users to access relevant documents and videos. By connecting AI-powered research with an isolated backtesting environment, the system keeps the client's data and infrastructure under their control.
Tech Stack
- Open WebUI: Provides the private AI chat interface.
- LiteLLM: Connects and manages AI models, including Gemini Flash.
- FastAPI and Haystack: Handle document processing, retrieval, and RAG services.
- Qdrant: Stores document and video embeddings for search.
- PostgreSQL: Stores application state and related data.
- Apache Tika: Extracts content from documents.
- Voyage AI: Provides embeddings and reranking.
- Groq ASR: Supports speech-to-text processing.
- OCR and Vision Models: Extract and describe information from video frames and charts.
- Python: Runs the trading backtesting engine and analysis tools.
- Streamlit: Provides the administration dashboard.
- Docker Compose and Caddy: Manage self-hosted services and HTTPS.
- Phoenix / OpenTelemetry: Support tracing and monitoring.
- restic and rclone: Handle encrypted backups and storage transfers.
Where This Pattern Applies
- Trading Firms: Search internal research, trading strategies, and market education materials.
- Investment Research Teams: Retrieve information from private reports, documents, and recorded discussions.
- Financial Educators: Make large libraries of training videos and learning materials searchable.
- Quantitative Analysts: Combine AI-assisted research with automated backtesting and strategy evaluation.
- Agriculture: Help farmers and agricultural organizations search farming guides, crop research, soil reports, weather records, and agricultural training materials.
- Healthcare: Help medical research teams retrieve information from clinical studies, medical documents, and educational resources.
- Education: Make institutional learning materials, lectures, research papers, and training content searchable.
- Manufacturing: Provide AI-powered access to equipment manuals, maintenance records, technical documentation, and operational procedures.
- Research Organizations: Build private AI assistants grounded in internal documents and datasets.
This pattern can be applied across industries wherever organizations have large collections of private information. By combining a shared knowledge base, AI-powered search, source-backed answers, and specialized analysis tools, organizations can turn their existing data into a searchable and useful research assistant while keeping control of their infrastructure.
Page · Plain text
ClickUp Structure: Taraki Staffing Company
Detailed ClickUp workspace structure for a staffing company’s operations.
Section: ClickUp Setups
01. Project Overview
This project organizes Taraki Staffing Company's operations into a structured ClickUp workspace. The workspace centralizes recruitment activities, client accounts, staffing requests, compliance tracking, onboarding, and performance reviews.
The setup uses dedicated folders, lists, custom fields, and automation rules to help teams manage tasks consistently and track work throughout the staffing lifecycle.
02. The Challenge
Staffing companies coordinate multiple interconnected processes, from publishing job openings and screening candidates to managing client requirements and onboarding placements.
Without a structured workspace, teams can face challenges such as:
- Recruitment tracking: Keeping job postings, candidate screening, interviews, and offers organized.
- Client coordination: Managing client accounts, staffing requests, and contract reviews.
- Compliance management: Tracking required checks and resolving outstanding compliance issues.
- Employee onboarding: Coordinating documentation, training, and onboarding tasks.
- Performance monitoring: Scheduling employee reviews and following up on client feedback.
03. The Solution
A dedicated ClickUp workspace structure was designed around five operational areas:
Recruitment
Manages job openings and the candidate journey from initial screening through interview scheduling and offer management.
Client Management
Centralizes client account information, staffing requests, service agreements, and account review activities.
Compliance and Onboarding
Tracks placement compliance requirements, employee documentation, training schedules, and onboarding progress.
Performance Management
Organizes employee performance reviews, feedback, improvement plans, and client satisfaction follow-ups.
04. Workspace Structure
Main Folder: Taraki Staffing Operations
A. Recruitment
- Job Postings: Tracks job ID, role title, department, status, posting date, location, salary range, and job description.
- Candidate Screening: Records candidate details, screening outcomes, resumes, and screening notes.
- Interview Scheduling: Manages interview dates, interviewers, formats, notes, and follow-up requirements.
- Offer Management: Tracks offer dates, acceptance status, start dates, salary, benefits, and offer details.
B. Client Management
- Client Accounts: Stores company details, contacts, service-level agreements, account managers, and review dates.
- Project Requests: Tracks staffing requirements, urgency, fulfillment status, and expected completion dates.
C. Compliance and Onboarding
- Compliance Tracking: Records placement IDs, compliance checklists, verification dates, outstanding issues, and resolution status.
- Employee Onboarding: Manages onboarding dates, required documents, training schedules, completion status, and assigned mentors.
D. Performance Management
- Employee Reviews: Tracks review periods, performance scores, feedback, improvement plans, and reviewers.
- Client Feedback: Records feedback dates, satisfaction levels, comments, and follow-up actions.
05. Automation and Workflow Rules
ClickUp automation rules support the processes defined within each list.
- Recruitment: Notify the team when jobs are posted, send alerts when statuses change, remind recruiters about overdue vacancies, and initiate onboarding tasks after offer acceptance.
- Client Management: Schedule quarterly account reviews, remind account managers about contract renewals, and flag urgent staffing requests.
- Compliance and Onboarding: Create compliance tasks for new placements, flag unresolved issues, and notify teams when onboarding remains incomplete.
- Performance Management: Remind reviewers about pending assessments, schedule future reviews, and create follow-up tasks based on employee or client feedback.
These rules are designed to reduce repetitive coordination and make task ownership and progress easier to track.
06. End-to-End Workflow
This workflow connects the major stages of staffing operations, from the initial client requirement through placement, onboarding, and ongoing performance management.
07. Key ClickUp Features
- Custom Fields: Capture structured information specific to each operational process.
- Dedicated Lists: Separate recruitment, client management, compliance, onboarding, and performance activities.
- Status Tracking: Make task progress and outstanding work visible.
- Automation Rules: Trigger reminders, notifications, and follow-up tasks based on configured conditions.
- Centralized Workspace: Keep staffing operations organized within one ClickUp structure.
08. Expected Business Value
The workspace is designed to support:
- Better visibility into recruitment and staffing requests.
- More consistent candidate and placement tracking.
- Improved coordination between recruitment and account management.
- Clearer oversight of compliance and onboarding requirements.
- More organized employee reviews and client feedback.
- Less repetitive manual follow-up through configured automation rules.
09. Conclusion
The Taraki Staffing Company ClickUp setup provides a structured foundation for managing staffing operations in one workspace. By combining dedicated lists, custom fields, status tracking, and automation rules, the system helps teams coordinate recruitment, client relationships, compliance, onboarding, and performance management more consistently.
Page · Plain text
Paid List vs. Rooming List
Compare payment and rooming records, identify discrepancies, and keep group travel organized with confidence through faster, smarter, and more accurate data reconciliation.
Section: Custom SaaS Platforms
Project Overview
The Paid List vs. Rooming List is a web application designed for a group travel company to compare payment records with room assignments. It identifies missing guests, unpaid balances, and similar-looking names, helping staff detect discrepancies quickly and maintain accurate travel records. Users can upload CSV files exported from Google Sheets and receive categorized comparison results without manually checking hundreds of rows.
Business Problem
The group travel company managed payment records and room assignments in separate Google Sheets, making it difficult to keep both lists consistent. Staff had to manually check hundreds of rows to identify guests who had paid but were missing from the rooming list, guests assigned to rooms without payment records, and names with slight spelling differences. This process was time-consuming, error-prone, and made it harder to identify discrepancies quickly.
Proposed Solution
The solution is a web application that compares the Paid List and Rooming List using uploaded CSV files exported from Google Sheets. It automatically matches guest names, verifies payment status, and categorizes results into three groups: Matched, Paid List Issues, and Rooming List Issues. It also highlights similar-looking names to help staff identify possible spelling differences and avoid overlooking guests. Each results table can be sorted and downloaded separately as a CSV file, making the reconciliation process faster and more reliable.
End-to-End Workflow
Image: Figure: Workflow Overview
How It Works
1. CSV Upload and Parsing: Staff upload the Paid List and Rooming List as CSV files exported from Google Sheets. The system handles differences in file formats, including header rows, optional row-number columns, and variations in payment column names.
2. Rooming List Processing: Rooming List rows are converted into individual guest records, including multiple occupants assigned to the same room.
3. Guest Name Matching: The system compares names using case-insensitive exact matching. If an exact match is not found, it checks for similar names based on shared surnames, minor spelling differences, or possible nicknames.
4. Discrepancy Detection: The application identifies guests missing from either list, flags payment statuses that are not marked “Paid in Full,” and highlights potential name matches for further review.
5. Categorized Results: Results are displayed in three separate tables: Matched, Paid List Issues, and Rooming List Issues. Red highlights indicate discrepancies, while yellow highlights indicate possible similar-name matches.
6. Review and Export: Staff can sort the results and download each table as a separate CSV file for further review and record-keeping.
Results Categories
Product Experience
The application provides a simple, browser-based interface that allows staff to upload CSV files, compare guest records, and review discrepancies in organized tables. Results are separated into three categories
so users can quickly identify records that need attention. The tables support sorting and individual CSV downloads, making it easier to investigate issues and share results with the team.
Image: The upload screen: a staff member adds the Rooming List and Paid List CSVs exported from the group’s Google Sheet and clicks Compare.
Image: The results summary and the Paid List issues. Red rows are real discrepancies and yellow rows are similar-name warnings. Names, amounts, room and confirmation numbers are blurred for privacy.
Image: The Rooming List issues: people on the rooming list who are not on the paid list. Names and booking numbers are blurred for privacy.
Image: The matched list: people who paid in full and are on the rooming list, with no action needed. Names, amounts and booking numbers are blurred for privacy.
Technology Stack
| Technology | Purpose |
|---|
| TypeScript | Core application logic and type-safe data processing |
| Node.js | Runs the backend using a plain HTTP server without a web framework |
| HTML, CSS & Vanilla JavaScript | Provides the browser interface, interactive result tables, sorting, and CSV downloads |
| Google Sheets & CSV | Source of the Paid List and Rooming List data, uploaded as CSV files |
| Railway | Cloud deployment and application hosting |
Data Handling & Limitations
The application processes uploaded CSV files in real time and returns comparison results directly in the browser. It is stateless, meaning uploaded data is not saved to disk. Each comparison runs independently, and users can download the Matched, Paid List Issues, and Rooming List Issues tables as separate CSV files.
Limitations: The accuracy of the results depends on the quality and consistency of the uploaded data. Similar-name detection helps identify potential matches but may require manual verification. Staff should review flagged discrepancies before making changes to payment records or room assignments.
Closing Summary
The Paid List vs. Rooming List application simplifies group travel reconciliation by automatically comparing payment records with room assignments. Through exact name matching, similar-name detection, payment status validation, and categorized discrepancy reports, it helps staff identify issues faster and reduce manual checking. Built with TypeScript, Node.js, and a lightweight web interface, the tool provides a practical and efficient way to maintain accurate guest records and support smoother group travel operations.
Page · Plain text
Automated Order-to-Task Management and Asana Synchronization
Automation that turns sales orders into Asana tasks, with deadlines and project updates handled automatically.
Section: Make Automations
Overview
This solution connects NetSuite sales orders with Asana, automating task creation, deadline tracking, and project organization. It keeps order information and operational tasks aligned, reduces repetitive manual updates, and helps teams stay organized.
The Problem
Sales orders live in NetSuite, but the work needed to fulfil them is managed in Asana. Moving information between the two systems means manually creating tasks, transferring order details, checking deadlines, and keeping project sections organized.
Tasks can be duplicated, important order details can be missed, and statuses can fall out of date. When several projects are involved, keeping everything aligned becomes another job in itself.
How It Works
The solution uses three connected Make scenarios, each handling a different part of the operational workflow.
- Receive sales order information. A custom webhook receives sales order data originating from NetSuite and starts the automation.
- Process the order items. The workflow iterates through the line items and separates regular Asana items from TM Engraving items, sending each through its configured processing route.
- Prepare structured task details. It combines item names, descriptions, quantities, engraving notes, and shipping methods where available.
- Check for existing tasks. Before creating anything, the automation searches Asana using the sales order number and purchase order number.
- Create or update the task. If no matching task exists, a new one is created. If a matching task already exists, its notes are updated instead of creating a duplicate.
- Monitor deadlines and statuses. A second scenario retrieves active tasks from two configured Asana projects and evaluates their due dates, current sections, and existing status fields.
- Update only when necessary. Conditional rules calculate the appropriate status based on configured date and section conditions. The automation updates the custom field only when a change is required and skips unnecessary updates
- Organize tasks through events. A third scenario listens for Asana webhook events, identifies the associated task and project, determines the appropriate destination section, and moves the task using the Asana API..
The Result
The integrated automation manages the complete workflow between NetSuite, Asana, and Ashore. It automatically creates and updates Asana tasks from eligible sales orders, checks deadlines, updates task statuses, and organizes tasks into the appropriate project sections based on Ashore updates. This reduces manual task management, improves project organization, and keeps information synchronized across all three platforms.
Daily Automation Output
| Metric | Combined Result |
|---|
| Successful workflow executions | 65 per day |
| Successful execution rate | 100% of displayed runs |
| Average execution time | 1.66 seconds |
| Tasks created | 4 |
| Existing tasks updated | 2 |
| Scheduled deadline checks | 24 per day |
Note:Metrics are based on the observed day and may vary depending on daily sales order volume, task updates, and incoming Ashore events.
Daily Automation Activity
Tech Stack
- Make: Runs all three automation scenarios and coordinates the workflow logic, routers, filters, iterators, and conditional operations.
- NetSuite: Supplies sales order information, customer details, and order line items.
- Asana: Manages operational tasks, project sections, due dates, notes, and custom status fields.
- Asana API: Handles task searches, creation, updates, status changes, and section assignments.
- Webhooks: Trigger the scenarios when sales order information or supported Asana task events are received.
- Routers, Filters, Iterators, and Variables: Control processing paths, handle line items, evaluate conditions, and determine the appropriate task updates.
Where This Pattern Applies
This solution goes beyond task creation. It keeps sales orders, deadlines, task statuses, and project activities connected, helping teams stay organized across their daily operations.
Imagine a business receiving a new customer order through its CRM. The automation takes the order information, identifies the required work, checks whether a corresponding project task already exists, creates or updates it, assigns the relevant deadline, and keeps its status aligned as work progresses.
The same approach can be adapted to different business operations:
- Sales: Convert new opportunities and closed deals into structured tasks and follow-up activities.
- Manufacturing: Turn production orders into operational tasks with deadlines and progress tracking.
- E-commerce: Coordinate order fulfilment, packaging, and shipping activities.
- Insurance: Convert new claims into investigation and documentation tasks.
- HR & Recruiting: Organize candidate onboarding, interview activities, and employee documentation.
- Finance: Coordinate invoice approvals, payment processing, and reconciliation tasks.
- Logistics: Manage shipment preparation, delivery coordination, and dispatch activities.
- Customer Support: Convert incoming requests into trackable support tasks.
- Project Management: Keep tasks, deadlines, statuses, and project sections synchronized across teams.
- Professional Services: Coordinate client projects, deliverables, and internal assignments.
The underlying pattern remains the same: receive information, process it, check for existing records, create or update tasks, evaluate deadlines, synchronize statuses, and organize work based on events.
Whatever systems a business uses, the objective is the same: keep operational information connected and let automation handle the repetitive coordination.
Page · Plain text
AI-Powered Fashion Campaign Image Generation
An n8n workflow that turns one product photo into AI-generated model images plus eCommerce and lifestyle campaign shots, saved to Google Drive.
Section: n8n Automations, AI Agents, AI Agents for Ecommerce
Project Overview
The AI-Powered Fashion Campaign Image Generation system automates fashion visual production using n8n, Google Gemini, image generation APIs, and Google Drive. Starting with a single uploaded clothing image, the workflow analyzes the garment, develops creative prompts, generates a model image, and uses the original product and generated model as references for additional campaign visuals.
The final images are automatically uploaded to Google Drive, creating a streamlined process for producing consistent fashion and eCommerce assets without manually managing each stage of the creative workflow.
Technologies: n8n · Google Gemini · AI Image Generation APIs · Google Drive
01. The Problem: Manual Image Creation for Fashion Campaigns
Before automation, fashion campaign production required manual coordination across photography, creative direction, and AI image generation.
Common challenges included:
- Time-consuming image conceptualization and generation.
- Specialist prompt engineering for different image types.
- Fragmented workflows for managing product images.
- Delays and inconsistencies across campaign visuals.
Core challenge: Integrate the entire creative production pipeline into one automated system that generates high-quality, consistent fashion campaign images efficiently.
02. The Goal: A Fully Automated Fashion Photoshoot
The goal was to transform a single product photo into a complete set of AI-generated campaign assets through one workflow.
The system:
- Accepts a clothing image through a simple form.
- Analyzes the product and generates a suitable creative prompt.
- Creates a photorealistic model image featuring the product.
- Generates eCommerce studio shots and lifestyle campaign visuals.
- Uses the original clothing and generated model images as references.
- Uploads the resulting assets to Google Drive automatically.
This reduces manual coordination and streamlines creative production from input to final output.
03. The Solution: AI-Powered Fashion Image Generation
The workflow combines n8n automation with AI-powered image analysis, prompt generation, and image creation.
It uses internal workflow logic to develop creative directions, generates a model image from the original product photo, and then creates additional product and lifestyle visuals using both images as references.
All generated assets are organized in Google Drive, making them easier to access and manage.
04. How the System Works
Phase 1: Image Input and Model Creation
- A form trigger receives the uploaded clothing image.
- The image is converted to Base64 for API processing.
- Workflow logic analyzes the garment and develops a creative prompt, including the intended model persona.
- An AI image generation API using Google Gemini creates the fashion model image.
- The generated model image is uploaded to Google Drive.
Phase 2: Prompt Generation and Campaign Image Creation
- The original clothing image and generated model image are used as visual references.
- The workflow creates prompts for eCommerce studio shots and lifestyle scenes.
- AI image generation APIs produce the corresponding campaign visuals.
- Generation results are checked for success.
- Final images are uploaded to Google Drive.
05. Real-World Impact
- Reduced Manual Prompting: Creative direction and prompt generation are handled by the workflow.
- Consistent Brand Visuals: Products receive standardized eCommerce images and lifestyle scenes.
- Faster Production: Multiple stages that previously required manual coordination run automatically.
- Scalable Content Creation: The same workflow can be reused across a product catalog.
- Organized Assets: Generated images are stored in Google Drive with predictable naming conventions.
06. Expected Impact
Time Savings
The workflow is designed to reduce manual creative and prompt-writing time by an estimated 70–90%, depending on the production process and level of review required.
Consistency and Coverage
Standardized prompts help reduce missing image angles, incomplete product coverage, and inconsistent lifestyle visuals.
Faster Content Production
Campaign visuals can potentially be generated on the same day products arrive, helping teams prepare new collections more quickly.
Asset Organization
Generated images are uploaded to Google Drive using predictable naming conventions, such as AI Model and Result #X, making image sets easier to browse.
Creative Efficiency
Reusable creative logic allows teams to produce more variations while reducing dependence on external photoshoots for every campaign asset.
07. Workflow Architecture
- Product Image Upload: Receives the original clothing image.
- Garment Analysis: Extracts visual details to guide image generation.
- Creative Prompt Generation: Defines the model and visual direction.
- AI Model Image: Creates the initial model image using the product reference.
- Campaign Image Generation: Produces studio and lifestyle variations.
- Google Drive: Stores the generated assets for later use.
Image: Fig:n8n automation workflow
08. Final Outcome
The workflow transforms a single clothing image into a collection of AI-generated fashion campaign visuals through an automated process.
- Creative prompting is handled within the workflow.
- Model, eCommerce, and lifestyle images are generated from visual references.
- Multiple stages of image production run automatically.
- Campaign assets are organized in Google Drive.
- Reusable automation supports production across larger product catalogs.
The result: A streamlined fashion content production pipeline that helps brands create campaign-ready visuals faster, with more consistent creative direction and less repetitive manual work.
Page · Plain text
AI-Driven Instagram Video Breakdown: Decode What Makes Viral Content Tick
Automatically fetch and analyze top-performing Instagram videos from popular creators to uncover what makes them stand out.
Section: AI Agents
Project Overview
Understanding why an Instagram Reel performs well requires more than looking at its view count. The opening hook, visual presentation, setting, storytelling, and memorable moments can all provide useful insights for content planning.
This project automates the process of identifying high-performing videos from selected Instagram creators and analyzing their creative elements. The workflow retrieves creator usernames from Airtable, identifies each creator’s most-viewed Reel, collects its details, downloads the video for analysis, and uses AI to generate a structured breakdown.
The resulting insights are saved back to Airtable, creating a searchable reference for reviewing successful content and informing future creative decisions.
01. The Challenge
Content research can become repetitive when teams manually review creators, compare video performance, and document what makes individual Reels engaging.
The main challenges include:
- Finding High-Performing Content: Identifying the strongest-performing Reel for each creator requires reviewing video performance data.
- Manual Video Research: Collecting links, captions, creator names, and view counts takes time when handled individually.
- Understanding Creative Techniques: View counts alone do not explain how a video attracts attention or maintains viewer interest.
- Inconsistent Analysis: Without a consistent framework, different videos may be reviewed using different criteria.
- Scattered Research Notes: Video observations can be difficult to organize and revisit when they are not stored in a structured database.
02. Project Objectives
The workflow was designed to automate video discovery and provide a consistent framework for analyzing creative content.
Its objectives are to:
- Retrieve Instagram creator usernames from Airtable.
- Identify the highest-viewed Reel available for each creator.
- Capture essential video information, including the link, caption, creator name, and view count.
- Download the selected video for closer analysis.
- Use AI to examine the opening hook, overall mood, visual style, and standout moments.
- Store the resulting analysis in Airtable for future reference.
03. The Solution
The solution combines Airtable-based creator tracking, automated video discovery, video downloading, and AI-assisted content analysis in a single workflow.
Rather than requiring a person to research and document every video manually, the workflow processes creator records, selects a top-performing Reel, and organizes its information for analysis.
The AI analysis focuses on four core areas:
Opening Hook
Examines how the video captures attention in its opening seconds, including the opening scene, action, or message that encourages viewers to keep watching.
Mood and Setting
Reviews the atmosphere of the video, including its background, environment, lighting, and overall energy.
Visual Style
Examines presentation elements such as on-screen text, clothing, framing, and other visible creative choices that contribute to the video's appearance.
Standout Moments
Identifies memorable or attention-grabbing moments that may help explain why viewers continue watching the video.
These observations are organized into a structured output and saved to Airtable alongside the relevant video information.
04. How It Works
- Retrieve Creators: Read Instagram usernames from Airtable.
- Find the Top Reel: Identify the most-viewed available Reel for each creator.
- Collect Video Details: Capture the video link, caption, creator name, and view count.
- Download the Video: Prepare the selected Reel for closer analysis.
- Analyze with AI: Examine the hook, mood, visual style, and standout moments.
- Save the Insights: Write the structured analysis back to Airtable.
Demo:
05. Workflow
06. Key Features
- Automated Creator Research: Uses Airtable as the source for Instagram creator usernames.
- Performance-Based Selection: Focuses on the most-viewed available Reel for each creator.
- Video Metadata Collection: Organizes essential information about each selected video.
- AI-Assisted Creative Analysis: Applies consistent analysis criteria to the selected content.
- Structured Content Breakdown: Separates observations into hook, mood, visual style, and standout moments.
- Centralized Results: Stores video information and analysis in Airtable.
- Scheduled Execution: Supports daily, weekly, or monthly scheduling when configured in the automation platform.
07. Technology Stack
| Technology | Purpose |
|---|
| Instagram | Source of creator videos and Reel content |
| Airtable | Stores creator records, video details, and analysis results |
| Automation Workflow | Coordinates video discovery, downloading, analysis, and data storage |
| AI Analysis | Examines the video's creative and storytelling elements |
Note: The exact AI provider and video-downloading service are not specified in the supplied case study details.
08. Business Benefits
Faster Content Research
Automates repetitive steps involved in finding videos and collecting their key information.
More Consistent Analysis
Uses a common set of creative criteria to review videos, making observations easier to compare.
Organized Creative Intelligence
Keeps video metadata and analysis together in Airtable rather than scattered across separate notes.
Better-Informed Content Planning
Provides a structured reference for exploring hooks, visual presentation, storytelling, and other creative techniques used in high-performing videos.
09. Conclusion
The AI-Driven Instagram Video Breakdown workflow turns video research into a more organized and repeatable process. By combining creator tracking, Reel selection, video downloading, AI-assisted analysis, and Airtable storage, it helps transform individual videos into structured creative insights.
The result is a centralized content research process that makes it easier to review successful Reels, compare creative approaches, and use documented observations to guide future content planning.
Page · Plain text
AI-Powered Shopify Abandoned Cart Recovery System
An always-on automation that detects abandoned Shopify carts and sends personalized, AI-written recovery emails.
Section: n8n Automations, Make Automations, AI Agents, AI Agents for Ecommerce
01. The Problem: Abandoned Carts Were Leaving Revenue on the Table
Before automation, abandoned carts were often handled manually or received no follow-up at all.
- Teams had to check Shopify manually for abandoned checkouts.
- Writing reminder emails took time and effort.
- Follow-ups were inconsistent, and many carts were never contacted.
- Generic emails lacked personalization.
- Delayed reminders reduced the chance of customers completing their purchases.
The Cost of Manual Follow-Ups
For stores handling 40–60 abandoned carts per day:
- Each follow-up took approximately 5–7 minutes.
- Manual work could consume 3–5 hours daily.
- Some stores followed up only once a day or skipped follow-ups entirely.
Without timely reminders, potential sales were lost.
02. Results After Automation
The automated workflow ensures abandoned checkouts receive timely, personalized recovery emails with minimal human intervention.
- 100% recovery-attempt coverage: Every detected abandoned cart receives a recovery attempt.
- 90–95% less manual work: Repetitive follow-up tasks are automated.
- Faster communication: Recovery emails are sent within the configured time window.
- AI personalization: Each email is generated to provide a relevant, friendly reminder.
Time Savings
| Metric | Before Automation | After Automation |
|---|
| Follow-up process | Manual | Automated |
| Time per cart | Approximately 6 minutes | Minimal manual effort |
| Daily workload | Around 3–5 hours | Near-zero routine effort |
| Monthly time savings | — | Approximately 100–120 hours |
Potential Revenue Impact
Using a conservative example of 50 abandoned carts per day, a $50 average cart value, and a 5–8% recovery rate:
- Potential recovered sales: $125–$200 per day.
- Potential recovered sales: Approximately $3,750–$6,000 per 30-day month.
These figures are illustrative estimates, not guaranteed results. Actual performance depends on store traffic, customer behavior, email deliverability, and conversion rates.
03. The Solution: AI-Powered Abandoned Cart Recovery
The system works as an always-on sales assistant that follows up with customers automatically.
It:
- Detects abandoned Shopify checkouts.
- Waits for a configured period before sending a reminder.
- Verifies that the checkout is still abandoned and has not been completed.
- Uses AI to generate a personalized recovery email.
- Sends the email automatically through Gmail or a configured email service.
The workflow operates in the background, reducing repetitive work while keeping follow-ups consistent.
04. How the Automation Works
The workflow connects Shopify, an automation platform, AI, and email delivery.
- Abandoned Checkout Detection: Shopify provides abandoned checkout data.
- Wait and Verify: The automation waits and checks whether the checkout remains abandoned.
- AI Email Generation: OpenAI generates a friendly, personalized recovery message.
- Email Delivery: Gmail or the configured email service sends the message to the customer.
- Scheduled Execution: The workflow runs automatically according to its configured schedule.
Workflow:
No routine manual follow-up is required once the workflow is configured and activated.
05. Business Value
Recover Potential Revenue
Re-engages customers who leave products in their carts and creates another opportunity to complete a purchase.
Reduce Manual Work
Eliminates repetitive checkout monitoring and email-writing tasks.
Improve Customer Experience
Delivers timely reminders with more relevant, personalized messaging.
Ensure Consistent Follow-Ups
Provides a recovery attempt for every detected abandoned checkout that meets the workflow conditions.
Scale With Store Growth
Handles increasing checkout volumes without requiring a proportional increase in manual effort.
06. How to Replicate the System
Use the provided workflow blueprint to configure the automation in Make.com.
Step 1: Import the Blueprint
- Open the attached JSON file: Shopify Abandoned Checkout Recovery with Order Verification (1).json.
- Select and copy the complete JSON content.
- Log in to Make.com and open Scenarios.
- Create a new scenario and choose the blueprint import option.
- Import the JSON, save the scenario, and name it Shopify Abandoned Checkout Recovery with Order Verification.
Step 2: Configure Shopify
- Connect your Shopify account.
- Confirm that the workflow retrieves abandoned checkouts.
- Verify that the checkout status and required customer fields are mapped correctly.
Step 3: Configure the Wait and Verification Logic
- Review the delay before sending the recovery email.
- Verify that the checkout has not been completed.
- Prevent duplicate or unnecessary recovery emails.
Step 4: Configure OpenAI
- Add your OpenAI API key.
- Confirm that the AI generates a relevant, friendly recovery email.
- Check that the email body follows your desired format and tone.
Step 5: Configure Email Delivery
- Reconnect Gmail or your SMTP email service.
- Map the customer's email address dynamically.
- Set the email subject to You left something behind.
- Verify the recipient, subject, and generated email body.
Step 6: Test and Activate
- Run the scenario once.
- Verify that abandoned checkout data is retrieved.
- Confirm that the checkout verification works.
- Check that the AI-generated email is correct.
- Confirm that the recovery email is delivered successfully.
- Activate the scenario and configure an appropriate schedule, such as every 15–60 minutes.
Important: The actual schedule, delay, and verification rules should match your store's requirements and the imported workflow configuration.
07. Final Outcome
The AI-Powered Shopify Abandoned Cart Recovery System transforms abandoned checkouts into automated follow-up opportunities.
By combining Shopify checkout data, workflow automation, AI-generated emails, and automated delivery, the system helps businesses:
- Follow up consistently with abandoned carts.
- Reduce repetitive manual work.
- Deliver timely, personalized reminders.
- Create additional opportunities to recover lost sales.
- Scale their recovery process as the business grows.
The result: A reliable, always-on abandoned cart recovery workflow that supports revenue recovery without increasing routine workload.
Page · Plain text
End of part 3 of 7. Continue with part 4.