Solutions Showcase: part 2 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
Looker Studio: Facebook Ads Dashboard
A Looker Studio dashboard rolling up Facebook ad spend, revenue, ROAS and profit margin across a 9-month window.
Section: Looker Studio
01. Project Overview
This dashboard is part of a larger multi-channel paid media reporting setup. It provides a dedicated view of Facebook advertising performance, allowing marketing and finance teams to review campaign-related spending, revenue, and performance indicators in one place.
Paid Media Reporting
Part of a larger multi-channel Looker Studio report, this page rolls up spend, revenue and profit for Facebook campaigns specifically, alongside a daily revenue-vs-spend trend.
- $3.94M: Facebook spend (9 mo.)
- $3.99M: Facebook revenue
- 1.01: Facebook ROAS
- 27,184: Orders
The dashboard runs on Looker Studio so paid media and finance read from the same live numbers instead of a separate export from Meta.
02. The Challenge
Facebook advertising performance involves several interconnected metrics. Reviewing spend, revenue, purchases, orders, ROAS, and profit margin separately makes it harder to understand overall performance across a reporting period.
A consolidated dashboard helps make these indicators easier to review and compare.
03. The Solution
A dedicated Facebook Ads overview was created in Looker Studio, combining key financial and performance metrics with a revenue-versus-spend trend chart.
The dashboard includes:
- Spend and Revenue: Compare advertising costs with reported revenue.
- Profit and Profit Margin: Review the displayed profitability metrics.
- ROAS: Monitor return on advertising spend.
- Purchases and Orders: Track the conversion and order-volume figures shown in the report.
- CPP: Review cost per purchase.
- Hook Rate: Monitor the displayed creative-engagement indicator.
- Date Filtering: Review performance across a selected period.
04. Dashboard Overview
The dashboard presents high-level KPIs at the top and a revenue-versus-spend chart below. This makes it easier to scan the main figures and observe how spending and revenue move over time.
Image: Facebook performance overview across a 9-month window: spend, revenue, ROAS and profit margin alongside a daily revenue-vs-spend trend.
Dashboard highlights:
- Facebook spend: $3.94M
- Facebook revenue: $3.99M
- ROAS: 1.01
- Orders: 27,184
- Profit: -$1.03M
- Profit margin: 1.21%
These figures are reproduced from the supplied dashboard screenshot. The displayed profit and profit-margin figures may require reconciliation before being used for financial decisions.
05. Technology and Integration
- Looker Studio: Dashboard visualisation and reporting.
- Meta Ads: Facebook advertising performance data.
The report provides a dedicated Facebook performance view within the wider multi-channel reporting environment.
06. Outcome
The dashboard brings Facebook advertising and financial indicators into one reporting interface. It supports performance reviews by making spend, revenue, order volume, and ROAS easier to compare without relying solely on separate platform views or manual exports.
Page · Plain text
Power BI: One Live View of a Multi-Site Clinic Network
A governed Power BI model unifying scheduling, EHR, billing and finance across four systems into two role-based dashboards refreshed every morning.
Section: Power BI
Power BI Case Study · Healthcare
Multi-site clinic network: scheduling, EHR, billing & finance unified · 6-week engagement
- 128,400: Appointments / yr
- 86.4%: Provider utilisation
- 7.8%: No-show rate
- 32 days: Days in AR
Reports that used to take days across sites now land by 6am, and we act on them the same morning.
The network ran on four disconnected systems: scheduling, the EHR, billing/claims and finance. Leadership could never see patient flow, provider utilisation and revenue-cycle health in the same place, and each site’s monthly report was rebuilt by hand. I consolidated all four into one governed Power BI model behind two role-based dashboards, refreshed automatically every morning, turning days of manual reporting into a screen the team reads with their coffee.
What Was Leaking
- Siloed systems: Scheduling, EHR, billing and finance never lined up, so no-shows, utilisation and collections couldn’t be seen together.
- Manual per-site reporting: Every site’s pack was rebuilt by hand (weeks behind by the time it landed, and easy to get wrong).
- Invisible revenue leakage: Denials, AR aging and slow collections weren’t tracked in one place, so cash slipped through unnoticed.
Dashboard One: Patient Flow & Utilisation
Appointments vs utilisation, department mix, top sites, a day-by-hour utilisation heat map and capacity gauge.
Image: Patient Flow & Utilisation: Executive Overview
- Utilisation heatmap: Spots under-used clinic slots by day and hour at a glance.
- Sites & departments: Ranks volume and no-shows together, site by site.
- Volume vs utilisation: Pairs appointment growth with the utilisation trend.
- Capacity gauge: Tracks attainment against the plan, currently 96%.
Dashboard Two: Revenue Cycle & Claims
Billed vs collection rate, a claims funnel, AR aging buckets and net revenue by payer.
Image: Revenue Cycle & Claims
- Claims funnel: Shows where submissions fall out before they’re paid.
- AR aging: Flags the £84K stuck in 90+ days for chase-up.
- Billed vs collected: Tracks the collection rate month over month.
- Payer mix: Splits net revenue across NHS, insurers and self-pay.
How It’s Built
| Stage | What We Built | Tools |
|---|
| Sources | 4 systems: Scheduling · EHR · Billing · GL | REST / API / file connectors |
| Clean | Key standardisation | Power Query |
| Model | Star schema, shared date table, DAX | Power BI model + DAX |
| Secure | RLS by site, per-site access | RLS roles |
| Deliver | 06:00 refresh via gateway & service | Power BI Service + gateway |
The Impact
After six weeks
- +5.0pts: Provider utilisation
- −2.1pts: No-show rate
- −6 days: Days in AR
- 3 days → 0: Manual reporting
With utilisation and no-shows visible by site and hour, the network reallocated clinic slots and tightened reminders, lifting utilisation five points while trimming no-shows, and replacing days of manual work with an automatic 6am refresh reconciled to the ledger.
Page · Plain text
LoanPro MCP Server: AI-Powered Financial Data Access & Account Analysis
Connecting AI assistants to LoanPro through a secure Model Context Protocol server for customer lookups, loan data retrieval, and past-due account triage.
Section: AI Agents
Overview
Accessing customer and loan information in LoanPro previously required users to search records and review account details manually. A custom MCP server now connects AI assistants such as Claude with LoanPro, allowing users to retrieve financial information and review accounts through conversational requests.
The Problem
Loan and customer information is stored inside LoanPro, while users want to access and understand it through conversational AI. Manually searching for customers, opening loan profiles, and reviewing transactions and balances makes account reviews repetitive. Identifying past-due accounts that meet specific balance thresholds also requires retrieving and filtering records. An integration layer was needed to connect AI assistants with LoanPro through controlled API operations.
How It Works
- Submit a Request: A user asks Claude to find a customer or review a loan account.
- Connect Through MCP: The AI client connects to the Go-based MCP server using SSE or stdio.
- Select a Tool: The assistant selects an available tool, such as
search_customers, and provides the required arguments. - Process the Request: The server prepares the corresponding LoanPro API operation.
- Retrieve Financial Data: The server requests customer, loan, transaction, or balance information from LoanPro.
- Normalize the Response: Go processes the returned JSON data and handles inconsistent identifier formats.
- Apply Review Logic: Available tools and predefined prompts support customer reviews and past-due account filtering.
- Return Results: The processed information is sent back to the AI assistant for a readable response or account summary.
Architecture flow:
Tech Stack
| Tool | Purpose |
|---|
| Go | MCP server and request processing. |
| MCP | Connects AI assistants with LoanPro tools. |
| LoanPro API | Retrieves customer and financial records. |
| Claude | Conversational AI interface. |
| Docker | Containerized deployment. |
The team can continue using LoanPro while accessing its selected capabilities through a compatible AI assistant.
Where This Pattern Applies
This solution is not limited to loan management. The same approach can connect AI assistants with business platforms through APIs.
Example — Insurance: An AI assistant can retrieve policyholder records, access claim information, and prepare summaries for review.
Other applications include:
- Banking: Customer accounts and transaction reviews.
- Healthcare: Authorized patient record retrieval.
- Legal Services: Client and case information searches.
- Property Management: Tenant records and payment reviews.
- Customer Support: Customer profiles and support history.
The general pattern is to connect an AI assistant to a business API through a dedicated server, expose specific tools, retrieve relevant data, and return structured results. The API, available tools, and business rules change according to the platform.
Page · Plain text
AI-Powered Facebook Content Generation Engine
An automated content generation system that transforms viral social media posts into original, branded creatives for more than 100 Facebook pages using n8n, Airtable, and AI agents.
Section: n8n Automations
Overview
This solution makes it easier to create and manage content for more than 100 Facebook pages. Airtable is used as the main workspace, while n8n handles the automation. The system collects source content, rewrites captions, recreates images, and adds branding for each page. Virtual assistants can then review the content and schedule it through Post Planner.
The Problem
Managing content for many Facebook pages takes a lot of time and effort. Virtual assistants have to find trending posts, rewrite captions, recreate images, and add the correct branding for each page. Doing all of this manually makes the process slow and difficult to manage. A single system was needed to bring these tasks together and make content creation easier.
How It Works
- Submit Source Content: Virtual assistants add a link to a trending post, meme, or news item in Airtable.
- Collect Source Content: n8n retrieves the content and related information from the submitted link.
- Rewrite Captions: AI agents rewrite the original captions to create fresh versions.
- Recreate Images: AI tools process the original images and create new versions.
- Add Page Branding: The system applies the correct templates, logos, and branding for each Facebook page.
- Save the Final Content: The generated captions and images are saved in Airtable for review.
- Schedule Posts: Virtual assistants review the completed content and schedule it through Post Planner.
Result
The system brings content collection, AI content creation, and page branding together in one workflow.
- Supports content management for more than 100 Facebook pages.
- Reduces the manual work involved in writing captions and creating images.
- Produces branded content ready for review and scheduling.
- Gives virtual assistants one place to manage their daily content tasks.
- Uses separate n8n workflows to handle different content-generation tasks.
Tech Stack
- n8n: Automates the workflow and manages content processing.
- Airtable: Provides a workspace for submitting source links and reviewing generated content.
- AI Agents: Rewrite captions and help create new images.
- Post Planner: Used to schedule completed posts.
- Facebook Pages: The platforms where the content is published.
Where This Pattern Applies
This approach can help any organization that manages content for multiple social media accounts.
- Digital Marketing Agencies: Create and manage content for different clients.
- Media Companies: Turn trending topics into new social media content.
- Social Media Teams: Make daily content creation faster and easier.
- Content Publishers: Manage content production across multiple pages.
- Brand Networks: Keep branding consistent across different social media accounts.
The same approach can be used to collect content, create new versions with AI, add the right branding, and prepare posts for publishing from one central workspace.
Page · Plain text
Weekly Marketing Performance Tracker (Google Sheets)
A Google Sheets weekly tracker that brings Google Analytics traffic and Klaviyo email and SMS performance into one view.
Section: Dashboards & Reporting
1. Project Overview
This project brings acquisition and retention metrics together in a centralized Google Sheets tracker. Marketing teams can review website traffic, customer acquisition, email and SMS sales, and subscriber growth without switching between separate platforms.
Category: Dashboards & Reporting
Tools: Google Sheets, Google Analytics, Klaviyo
2. The Challenge
Marketing performance data was spread across different platforms, making it harder to compare acquisition and retention results in one place.
- Fragmented reporting: Website traffic and email/SMS performance were tracked separately.
- Limited visibility: Reviewing performance across channels required switching between tools.
- Manual comparison: Comparing results across weeks and months required a consolidated reporting view.
3. The Solution
A centralized Google Sheets tracker organizes Google Analytics and Klaviyo metrics into weekly and monthly dashboards.
The tracker includes:
- Website traffic: Total traffic, new users, new customers, and engagement time.
- Acquisition channels: Organic search, organic social, paid search, paid social, direct, and other traffic sources.
- Email performance: Email sales, placed orders, campaigns, flows, and subscriber counts.
- SMS performance: SMS sales, subscriber totals, and new subscribers.
- Historical comparison: Weekly and monthly views for comparing performance over time.
4. How It Works
The tracker brings data from both platforms into one reporting view, where the team can compare acquisition and retention metrics over time.
Workflow
Google Analytics + Klaviyo → Consolidated Google Sheets Tracker → Weekly & Monthly Dashboards → Marketing Performance Review
5. Dashboard Highlights
Weekly Dashboard
The weekly dashboard displays traffic sources alongside Klaviyo email and SMS performance. Teams can review weekly changes in website acquisition, sales, and subscriber growth.
Monthly Dashboard
The monthly dashboard provides a broader reporting view for reviewing performance trends over a longer period.
Image: Weekly dashboard tracking Google Analytics traffic by source alongside Klaviyo email and SMS sales and subscriber counts.
6. Business Value
- Centralized reporting: Acquisition and retention metrics are available in one spreadsheet.
- Cross-channel visibility: Website traffic can be reviewed alongside email and SMS results.
- Historical comparison: Weekly and monthly views support trend analysis.
- Simplified reporting: Teams can review key marketing metrics without manually assembling separate platform reports.
7. Final Outcome
The Weekly Marketing Performance Tracker provides a single reporting view for Google Analytics traffic and Klaviyo email and SMS performance. By organizing these metrics into weekly and monthly dashboards, it makes cross-channel performance easier to review and compare.
Technology Stack: Google Sheets, Google Analytics, Klaviyo
Page · Plain text
AI Task Delegator: Slack to Monday.com
Automating the conversion of Slack requests into structured and assigned Monday.com tasks.
Section: Make Automations
1. Overview
This automation connects Slack with Monday.com to convert qualifying messages into structured tasks. An AI agent extracts task details from the original Slack message, while configured mappings determine the appropriate Monday.com board and task owner. The workflow also creates explicitly listed subtasks and sends a confirmation back to Slack.
2. The Problem
Teams often share work requests through Slack, but important action items can get buried in conversations. Manually converting these requests into Monday.com tasks requires reviewing messages, extracting details, selecting the correct board, and assigning owners. This repetitive process takes time and can result in inconsistent task information or missed action items.
3. How It Works
- Capture Slack Event: The workflow detects qualifying Slack messages or reactions through a configured event trigger.
- Retrieve Original Message: It retrieves the complete Slack message to provide context for AI processing.
- Extract Task Information: The AI agent generates a task title and description and identifies mentioned Slack user IDs and explicitly listed subtasks.
- Retrieve User Details: The workflow uses extracted Slack IDs to retrieve the corresponding user information where required.
- Determine Board and Owner: Configured user and channel mappings identify the appropriate Monday.com board, group where applicable, and task owner.
- Create Monday.com Task: The workflow creates the main task using the extracted title and adds its description and original Slack message context.
- Create Subtasks: If the request contains explicitly listed subtasks, the workflow iterates through them and creates them under the main task.
- Send Slack Confirmation: After task creation, the workflow sends a confirmation in the original Slack conversation with a link to the Monday.com task.
4. The Result
The automation connects Slack requests directly with Monday.com task management. It reduces manual task entry, structures incoming requests, applies configured board and owner mappings, and preserves the original conversation context. It also supports automatic subtask creation and sends confirmation through Slack.
Execution Metrics
| Metric | Result |
|---|
| Total Executions | 4,856 |
| Successful Executions | 4,826 |
| Failed Executions | 16 |
| Success Rate | 99.4% |
| Average Execution Time | 0.63 seconds |
Metrics are based on the available execution logs and may vary depending on message volume, task complexity, and the number of subtasks processed.
5. Tech Stack
Make: Coordinates the automation, processes Slack events, manages AI extraction, handles routing, and creates Monday.com tasks and subtasks.
Slack: Provides the triggering messages or reactions, original conversation context, user information, and task confirmations.
OpenAI: Uses GPT-4.1 mini and GPT-4.1 nano to extract and structure task information from Slack messages.
Monday.com: Receives the structured tasks, mapped owners, and explicitly listed subtasks.
6. Where This Pattern Applies
This automation pattern can be applied wherever teams receive work requests through communication platforms and need to organize them in task-management systems. Examples include internal operations, customer support, marketing coordination, project management, and administrative task tracking.
Page · Plain text
Contract Intake Tool
AI-Powered Contract Validation, Human Review, Automated Google Drive Filing, Folder Organization, Missing-Term Detection & Document Tracking.
Section: Custom SaaS Platforms
Overview
The Contract Intake Tool is a web app that uses Claude AI to extract key terms from supplier contracts, flags missing information for human review, and automatically files approved contracts into the correct Google Drive folders. It also maintains a record of all filing activities..
Business Problem
Supplier contracts such as hotel, venue, and bus services) Were reviewed and filed manually, making the process time-consuming. Important terms like cancellation clauses, fees, and tax rates could be missed, and contracts sometimes ended up in the wrong Google Drive folders, making them difficult to find later for billing or disputes.
Proposed Solution
Supplier contracts (hotel, venue, bus) were being reviewed and filed by hand. That was slow, and important terms (cancellation clauses, fees, tax rates) could get missed, and contracts sometimes ended up in the wrong Drive folder, making them hard to find later for billing or disputes.
Goal
- ut the manual review time per contract
- Make sure required terms are never silently missed
- File every contract into the exact right folder, every time, with no human guesswork
- Keep a record of who filed what, and when
How It Works
1. Scan
User uploads the PDF and picks a category (Hotel / Venue / Buses / Other). The text is extracted from the PDF and sent to Claude (Anthropic’s AI), which pulls out the specific terms that category requires, e.g. for Hotel: room rate, attrition clause, cancellation terms, tax rate. Each term comes back marked Found or Not Found.
2. Review
Anything Not Found must be manually checked and ticked off by a person before the contract can be filed. The tool never files something incomplete without a human saying it’s okay.
Image: The review screen after a scan: each key term (group name, number of rooms, rate, attrition, cancellation, additional fees and tax rate) with the text found in the contract and a Found status, plus a File button. The group name and company name are blurred.
3. File
Using the contract’s group name (e.g. “State University - Alpha Chapter”) and date, the tool works out the correct folder path, Year → Season → University → Chapter → Category, and uploads the PDF there automatically. It only creates the last two folder levels itself; everything above that must already exist in Drive. Every filing is logged (who, what, where).
Image: The Google Drive folder tree the contracts are filed into: Formal Contracts, then the year, then (inside 2027) a season folder, Spring 2027, and a group folder. One folder name and its owner are blurred.
Key Features
- AI-Powered Term Extraction: Extracts required contract terms using Claude AI.
- Missing Term Review: Flags missing information (Not Found) for manual review before filing.
- Automated Google Drive Filing: Files contracts into the correct folder based on group name, date, and category.
- Filing Activity Log: Records who filed the contract, what was filed, where it was stored, and when.
- Category-Based Checks: Checks contract terms according to the selected category (Hotel / Venue / Buses / Other).
What It’s Built With
Next.js (web framework) + TypeScript, Google Drive API, Claude for the AI extraction, Postgres for the log. PDF text extraction is done with a JavaScript library.
Page · Plain text
AI-Powered Meta Ads Reporting
An AI reporting system that pulls Meta Ads data, flags underperforming ads in real time, and recommends budget and creative changes.
Section: AI Agents, AI Agents for Ecommerce
AI-Powered Meta Ads Reporting
Automating Meta Ads performance reporting, identifying underperforming campaigns, and generating AI-driven optimization recommendations.
Project Overview
This system is designed to collect Facebook and Instagram campaign data, analyze performance using AI, and recommend changes to budgets, targeting, and creatives. It aims to help marketers make faster, data-driven decisions while reducing manual reporting work.
Platforms: Meta Ads, Instagram
01. The Problem
Manual campaign analysis required marketers to collect data across campaigns and ad sets, identify underperforming ads, and decide when to adjust budgets or creatives. This process was time-consuming and made timely optimization difficult as campaigns scaled.
02. The Solution
An AI-powered reporting system designed to automate data collection, analyze campaign performance, flag potential issues, and provide actionable recommendations for improving campaign results.
03. Key Features
- Automated Data Collection: Collect campaign-, ad set-, and ad-level metrics.
- AI Performance Analysis: Identify trends, anomalies, and underperforming ads.
- Budget Recommendations: Suggest budget reallocations based on performance.
- Creative Insights: Recommend potential creative improvements.
- Audience Optimization: Suggest targeting adjustments.
- Real-Time Alerts: Flag deviations from defined performance benchmarks.
- Natural Language Interaction: Allow users to request campaign insights and changes using natural language.
- Performance Tracking: Monitor metrics such as CTR, CPA, ROAS, conversions, spend, and impressions.
04. System Workflow
05. System Architecture
Phase 1 — Data Collection and Normalization
Collect campaign metrics, including impressions, clicks, CTR, conversions, ROAS, CPA, spend, and budget utilization, then prepare the data for analysis.
Phase 2 — AI-Powered Analysis
Analyze performance data to detect trends, anomalies, low ROAS, and CTR below defined benchmarks.
Phase 3 — Optimization Recommendations
Generate suggestions for budget allocation, audience targeting, and creative improvements, prioritized by their potential impact on KPIs.
Phase 4 — Reporting and Alerts
Present performance metrics in dashboards and notify users when defined KPI thresholds are breached.
Phase 5 — AI-Assisted Campaign Management
Allow users to request campaign changes through natural language, with validation and tracking of adjustments and their subsequent KPI impact.
06. Reported Results
The original case study reports the following outcomes after automation:
- Reporting time reduced from 6–8 hours to under 1 hour per week.
- 90% of underperforming ads flagged in real time.
- Campaign response time reduced from 1–2 days to under 1 hour.
- Reported ROAS improvement of 15–25%.
- Approximately 7 hours saved per marketer each week.
- Campaign management scaled from 10 to 50+ ad sets without additional staff.
- Human errors in campaign adjustments reduced by approximately 90%.
These figures are reported in the supplied case study and have not been independently verified.
07. Final Outcome
The system aims to replace repetitive manual analysis with automated reporting, AI-generated insights, performance alerts, and optimization recommendations, allowing marketers to focus more on campaign strategy and testing.
Page · Plain text
Supplement Operations Dashboard
A centralized analytics dashboard for monitoring orders, inventory levels, shipping performance, unit economics, and stock alerts.
Section: Looker Studio
Overview
Managing supplement operations requires visibility into orders, inventory, shipping, product costs, and stock alerts. This project brings these areas together in an interactive Google Looker Studio dashboard, allowing users to review operational information, apply filters, and monitor different business activities from one interface.
The Problem
Operational information is often spread across separate reports and spreadsheets. Reviewing order statuses, checking stock availability, comparing regional shipping costs, and identifying inventory warnings can require repeated manual filtering and switching between data views.
A centralized dashboard was needed to organize these areas and make operational information easier to access, compare, and review.
How It Works
- Access the Dashboard: Users open the dashboard and navigate through the sidebar to the required operational section.
- Review Orders: The Order Management section displays product details, quantities, order statuses, expected delivery dates, and tracking information.
- Monitor Inventory: Users review available stock, days and weeks of supply, regions, and critical or warning indicators.
- Check Inventory Forecasts: The forecasting view presents current stock alongside average demand over 14 and 30 days and replenishment recommendation fields.
- Analyze Shipping: The Shipping Analytics section compares regional shipping costs and average bottles per order.
- Review Unit Economics: Users examine product prices, stock in hand, expiry dates, and cost of goods sold (COGS).
- Monitor Alerts: The Alerts section presents alert distribution and recent shipment-related notifications.
- Filter and Investigate: Available search fields, product filters, region selectors, and status filters help users narrow the information and identify records requiring attention.
Result
The dashboard provides a single interface for reviewing six operational areas: Overview, Order Management, Inventory, Shipping Analytics, Unit Economics, and Alerts.Users can move between dedicated reporting views, compare regional and product-level information, review inventory conditions, and identify shipment-related alerts without switching between separate reporting interfaces.
| Metric | Observed Output |
|---|
| Items tracked daily | 170 |
| Alert channels | 2 (Email + Slack) |
| Source platforms | 3 (Amazon, Shopify + Google Sheets) |
| Alert levels | 2 |
Tech Stack
Google Looker Studio: Dashboard interface, interactive filters, data tables, charts, and operational reporting.
Where This Pattern Applies
The same dashboard approach can be used by businesses that need to monitor several operational areas through one reporting interface.
- E-commerce: Track orders, inventory, shipping, and product performance.
- Retail: Monitor stock availability, replenishment needs, and sales operations.
- Warehousing: Review inventory levels, stock movements, and fulfillment activity.
- Logistics: Compare regional shipping costs and delivery performance.
- Manufacturing: Monitor material availability, product costs, and operational indicators.
- Distribution: Review order status, regional inventory, and shipment alerts.
The general pattern is to organize information from different operational areas into dedicated dashboard views, provide relevant filters and indicators, and make important records easier to review.
Page · Plain text
Production Linux Server Audit and Repair for a Data Subscription Site
An audit of the single Ubuntu server behind a financial-data subscription site, a fix for its silently failed social-posting pipeline, and a documented setup so it can be maintained safely.
Section: Python Automation
Project Overview
A financial-data subscription site ran its Python backend, data pipelines, scheduled jobs, publishing automation, and social-posting pipeline on a single Ubuntu VPS. The project focused on auditing the server, repairing a silently failed social-posting pipeline, and documenting the setup for safer maintenance.
Technology: Python, Flask, SQLite, systemd, cron, Nginx, Gunicorn, Cloudflare Tunnel, Stripe, WordPress, Brevo
01. The Problem
The server supported several interconnected services and automated workflows. The social-posting pipeline had silently stopped working, and the client needed a server audit, a repair, and a clear maintenance roadmap.
02. What Was Done
- Audited systemd units, cron jobs, logs, Nginx, Gunicorn, the SQLite database, and the backup job.
- Prepared a plain-English client report with a health score and prioritized fixes.
- Repaired the social-posting pipeline with two targeted changes and stabilized its scheduling.
- Set up a Git mirror of
/opt and added a CLAUDE.md file documenting the architecture to support safer maintenance with Claude Code.
03. How the System Runs
- Nightly pipeline — 20:00 ET: Ingests OHLC data, runs scanners, builds JSON outputs, backs up the database to Google Drive using rclone, builds the newsletter and blog post, publishes through the WordPress REST API, and sends the daily email through Brevo.
- Live pipeline — 15:45 ET: Runs
live_pipeline.py for real-time signals and options pricing. - Always-on API: Runs the Gunicorn-hosted Flask API on port 5500 behind Nginx and Cloudflare Tunnel.
- Content engine: Scheduled through cron at 08:15, 08:45, every 15 minutes during market hours, and 21:00 to render PNG/MP4 content cards and post to Instagram, X, and TikTok.
04. Workflow
Nightly Data Pipeline
Scheduled systemd Timer → nightly_pipeline.sh → Ingest OHLC Data → Run Scanners → Build JSON → Back Up Database to Google Drive → Build Newsletter and Blog Post → Publish via WordPress REST API → Send Daily Email via Brevo
Live Data Pipeline
Scheduled systemd Timer → live_pipeline.py → Real-Time Signals and Options Pricing
API Service
Flask API → Gunicorn on Port 5500 → Nginx → Cloudflare Tunnel
Social Content Pipeline
Cron Schedule → Content Engine → Render PNG/MP4 Cards → Publish to Instagram, X, and TikTok
20:00 ET systemd timer → nightly_pipeline.sh
ingest OHLC → run scanners → build JSON → DB backup to Drive (rclone)
→ build newsletter + blog post (publish via WP REST API)
→ send daily email (Brevo)
15:45 ET systemd timer → live_pipeline.py (real-time signals + options pricing)
always systemd service → gunicorn Flask API :5500 behind nginx + Cloudflare Tunnel
cron 08:15 / 08:45 / every 15 min market hours / 21:00 → content engine renders PNG/MP4 cards and posts to IG / X / TikTok
05. Technology and Integrations
Python, Flask, SQLite, systemd, cron, Bash, Nginx, Gunicorn, Cloudflare Tunnel, rclone, JWT authentication, Stripe, WordPress REST API, Brevo, and the Post for Me API.
06. Outcome
The server was audited, the failed social-posting pipeline was repaired, scheduling was stabilized, and the architecture was documented to support safer ongoing maintenance.
Page · Plain text
Automated Meeting Transcription and Case Management
Automating Webex meeting transcript retrieval, case matching, document storage, and record tracking using Zapier.
Section: Zapier Automations
Overview
Meeting transcripts previously required manual handling, from retrieving recordings and identifying the correct client case to storing documents and updating tracking records. The Zapier automation connects these steps, using Calendly matching or AI-assisted case identification to route transcripts into the appropriate Box folders and update Google Sheets.
The Problem
Teams handling Webex meetings need to retrieve transcripts, identify the correct client or case, and store documents in the right folders. When these tasks are handled manually, transcripts can be difficult to match with the correct records, and tracking sheets may not stay up to date. Managing different meeting sources also adds repetitive work and increases the chance of misplaced or untracked documents.
How It Works
- Capture Meeting Information: A webhook starts the workflow when meeting-related data is received.
- Retrieve Meeting Details: Webex provides meeting information and participant details.
- Check Transcript Availability: Filters check whether the meeting meets the required transcription conditions.
- Format Meeting Data: Meeting dates and times are prepared for further processing.
- Match the Meeting: Zapier routes the meeting through either Calendly matching or AI-assisted case identification.
- Identify the Case Folder: The workflow locates the corresponding folder in Box.
- Process the Transcript: The transcript is retrieved and uploaded to the appropriate Box folder.
- Update Records: Google Sheets records the meeting and processing information.
Results
The automation brings transcript retrieval, case matching, document storage, and tracking into one coordinated workflow. It provides two matching paths for handling meetings and helps keep transcript files and associated case records organized across connected applications.
Tech Stack
| Tool | Role in the Workflow |
|---|
| Zapier | Connects applications and manages filters, loops, and workflow paths. |
| Webex | Provides meeting details, participant information, and transcript access. |
| Calendly | Supplies event information for meeting matching. |
| AI by Zapier | Assists in identifying case numbers from client records. |
| Microsoft Excel | Provides case-related information through CSV data. |
| Box | Stores transcripts in the relevant folders. |
| Google Sheets | Maintains meeting and processing records. |
The team can continue using its existing applications without needing to move its meeting records or document storage to a new platform.
Where This Pattern Applies
This solution is not limited to meeting management. The same approach can help any team that needs to match incoming documents or records with existing client information.
Example – Insurance: An incoming claim document can be matched with a customer record, stored in the correct claim folder, and logged in a tracking sheet.
Other applications include:
- Legal: Match client documents with case files.
- Healthcare: Organize consultation records and related documents.
- Recruitment: Match candidate documents with applications.
- Financial Services: Route transaction documents to customer records.
- Customer Support: Attach incoming correspondence to support cases.
The general pattern is to capture incoming information, identify its matching record, store the associated document, and update the tracking system. The matching rules and connected applications change according to the business process.
Page · Plain text
AI-Powered RAG Chatbot for The Fast Bite: Seamless Ordering and Query Handling
Create an AI-powered chatbot that helps The Fast Bite( a fast food restaurant) customers with menu queries, placing orders, and providing restaurant details in a fast and friendly manner.
Section: AI Agents
AI-Powered RAG Chatbot for The Fast Bite
An AI-powered chatbot that answers customer questions about menu items, restaurant information, and opening hours using an automatically updated knowledge base.
Project Overview
The Fast Bite chatbot uses Google Gemini and Pinecone to retrieve relevant information and generate helpful responses. Restaurant information is processed from files stored in Google Drive, allowing the chatbot’s knowledge base to be updated when new information is added.
Technology Stack: Google Drive, Google Gemini, Pinecone Vector Store
01. The Challenge
Customers need quick answers about menu items, food options, restaurant hours, and other frequently asked questions. Keeping this information current and responding consistently can require manual effort, especially when menu details or restaurant information change.
02. The Solution
An AI-powered Retrieval-Augmented Generation (RAG) chatbot was developed to process restaurant information, store it in a searchable vector database, and use that knowledge to answer customer questions.
The solution combines:
- Google Drive: Source for menu and restaurant information.
- Google Gemini: Processes information and generates natural-language responses.
- Pinecone: Stores searchable vector representations of the processed content.
- AI Chatbot: Retrieves relevant information and responds to customer queries.
03. How the System Works
Knowledge Base Preparation
When a new file is added to the designated Google Drive folder, the workflow detects the file and downloads it for processing.
Information Processing
Google Gemini helps process the content into information suitable for retrieval. The processed information is then prepared for storage in the vector database.
Vector Storage
Pinecone stores the processed knowledge so the chatbot can search for relevant information when a customer asks a question.
Customer Query Handling
When a customer submits a question, the chatbot retrieves relevant knowledge and uses an AI model to generate a helpful response based on the available information.
Detailed working Flow:
DEMO
04. Workflow
Image: Simple analogy
05. Key Features
- Knowledge Updates: New files can trigger the knowledge-processing workflow.
- Context-Aware Answers: Responses use relevant information retrieved from the knowledge base.
- Menu Assistance: Helps customers find menu details and food options.
- Restaurant Information: Answers common questions, including opening hours, based on available information.
- Centralized Knowledge: Keeps restaurant information available through a searchable vector store.
06. Technology Stack
| Technology | Purpose |
|---|
| Google Drive | Stores source documents and restaurant information |
| Google Gemini | Processes content and generates responses |
| Pinecone Vector Store | Stores and retrieves relevant knowledge |
| AI Chat Interface | Receives customer questions and displays answers |
07. Outcome
The result is a reusable RAG workflow for restaurant customer support that can be maintained by updating the underlying source information.
The Fast Bite chatbot provides a convenient way for customers to ask questions about restaurant information and receive AI-generated answers. By combining Google Drive, Gemini, and Pinecone, the solution connects document updates with knowledge retrieval and conversational responses.
Page · Plain text
Cold Email Copy Generation with Automatic Quality Checks
An AI tool that writes five cold email sequences in spintax format in minutes and checks each one against eight quality rules, rewriting any that fail.
Section: Python Automation
Overview
Cold email copy generation and quality control. Instead of spending hours writing email variations by hand in spintax format and checking each line against banned phrases and formatting rules, teams now get five production-ready email sequences in minutes.
The Problem
Creating cold email variations meant hours of manual work. Writers had to draft email sequences by hand, then apply spintax format line by line, a tedious process where every variation had to be written and formatted separately. Quality control was completely manual: each line had to be checked against banned phrases and banned words, word counts verified, spintax coverage confirmed, and offer rotation rules checked. With no automated checklist, mistakes slipped through before emails went into the sending tool. Creating five email sequences took 5 to 10 hours of work, was error-prone, and depended entirely on someone being available to do it correctly.
What the Automation Does
Image: The team interface: a chat assistant on the left, a button to generate the week’s strategy, and Copy Variations and History at the top.
Step 1: Email sequences are generated
The automation takes the email parameters and requirements, then uses AI to generate five complete cold email sequences in full spintax format, with multiple variations per email step (A/B variants) so testing options are built in.
Step 2: Automatic quality checks run
Every generated copy is automatically checked against eight quality rules: word count, spintax coverage on every line, banned phrases, banned words, offer accuracy, hook uniqueness, offer rotation compliance, and more. If a copy passes all checks, it is flagged as production-ready. If it fails, the system automatically rewrites it (up to three retries) to meet the requirements.
Step 3: Ready-to-send copies are delivered
The team receives five email sequences with a pass or fail verdict on each. Every copy is either production-ready or clearly flagged as needing manual revision, so there are no surprises or quality issues after the copy goes into the sending tool.
Main Work Flow
Tools and Integrations Used
- Custom code automation (AI-powered email generation and quality control)
- Anthropic Claude (copywriting and analysis)
- Python and FastAPI (backend automation)
- TypeScript, React and Next.js (team interface)
The Result
Teams no longer spend 5 to 10 hours writing and quality-checking email sequences by hand. Five production-ready sequences now generate automatically in minutes. Quality control shifted from a manual checklist to an automated pipeline that catches banned phrases, spintax gaps, word count violations and formatting mistakes instantly. Every copy follows the same proven structure with consistent formatting. What used to take hours of manual writing and QA now happens automatically, freeing the team to focus on strategy and testing instead of production work.
Summary
The tool automates the full cycle from email copy generation to quality-checked delivery. Teams provide their email requirements, the automation generates five complete sequences in spintax format, automatic quality checks verify everything, and production-ready emails are delivered in minutes instead of hours. The team stays in control, since they review and approve the output, while the repetitive writing and quality-checking work is handled automatically.
Page · Plain text
WhatsApp Voice & Business Agent with n8n
An AI-powered WhatsApp assistant that understands voice notes, text messages, and photos, then answers customer questions using product information stored in Supabase.
Section: n8n Automations, AI Agents for WhatsApp
Overview
This project is a WhatsApp business assistant for an online store. Customers can send a voice note, text message, or product photo and receive an answer based on the store’s product database. The system uses n8n to process incoming messages, OpenAI to understand different input types, and Supabase to retrieve product information. When a customer sends a voice note, the assistant can respond with a voice message. Conversation memory also helps maintain context across messages from the same customer.
The business problem
Online stores receive repeated questions about product availability, prices, and delivery. Customers may ask these questions through text, voice notes, or photos, making them difficult for simple chatbots to handle. Manual replies take time, while inaccurate answers about prices or stock can reduce customer trust.
How It Works
- Receive WhatsApp Messages: The WhatsApp Business Cloud API receives customer messages, including text, voice notes, and photos.
- Identify Message Type: n8n checks the incoming message and routes it to the correct processing path.
- Process Voice and Images: OpenAI transcribes voice notes and analyzes product photos. Text messages are passed through directly.
- Prepare the Message: n8n converts each input into a common text format and associates it with the customer's phone number.
- Retrieve Product Information: The AI agent uses the Supabase product database to find relevant information before preparing an answer. Conversation memory helps it maintain context.
- Send the Response: Text messages receive text replies. When the customer sends a voice note, the answer is converted into speech and returned as a WhatsApp voice message.
The Result
The completed workflow brings voice, text, and image-based customer enquiries into one WhatsApp assistant. It retrieves product information from Supabase before answering, supports both text and voice replies, and maintains conversation context for each customer.
Workflow Delivery Metrics
| Metric | Result |
|---|
| n8n nodes after cleanup | 21 |
| Supported input types | 3 |
| Reply formats | 2 |
| AI models used | 4 |
| Main agent workflows | 1 |
| Workflow defects fixed | 2 |
Note: These figures describe the delivered workflow. Live customer response time, answer accuracy, and sales conversion have not yet been measured.
Tech Stack
- n8n: Connects the services and manages the message-processing workflow.
- WhatsApp Business Cloud API: Receives customer messages, downloads media, and sends replies.
- OpenAI: Transcribes voice notes, analyzes images, generates answers, and converts replies into speech.
- Supabase: Stores product information and provides a searchable knowledge source for the AI agent.
- Shopify: Relevant to the planned extension for product and order-related functionality; order lookup and replacement-order creation are not part of the current workflow.
Where This Pattern Applies
- E-commerce Stores: Answer product questions about prices, availability, and product details.
- Retail Businesses: Help customers identify products through photos and ask questions through voice or text.
- Customer Support Teams: Handle common enquiries and pass complex issues to human support.
- Online Service Providers: Provide customers with a WhatsApp-based assistant for frequently asked questions.
This pattern is useful for businesses that receive customer enquiries through WhatsApp and want to automate responses while keeping answers connected to reliable business data.
Page · Plain text
AI Calling Agent with Human Handover and Automatic AI Fallback
An AI-powered phone calling workflow using ElevenLabs and Twilio that allows callers to request a human representative and automatically return to the AI agent when the human does not answer.
Section: AI Agents
Overview
This solution is designed to connect an ElevenLabs AI voice agent with Twilio to manage incoming calls and human handovers. When a caller requests to speak with a person, the AI agent initiates a transfer to a designated human number. If the human answers, the caller is connected. If the call is not answered within the configured timeout, Twilio returns the caller to the AI agent so the conversation can continue.
The Problem
An AI calling agent needs to support more than automated conversations. Callers may sometimes need assistance from a human representative, and the transfer process should not leave them disconnected if the representative is unavailable.
A reliable call-handling workflow was needed to support incoming calls, human transfers, and automatic fallback to the AI agent without interrupting the caller's experience.
How It Works
- Receive Incoming Call: The caller dials the designated Twilio phone number, which routes the call through the inbound Twilio Function.
- Connect to ElevenLabs: The inbound function registers the call with ElevenLabs and connects the caller to the AI voice agent.
- Handle the Conversation: The ElevenLabs agent communicates with the caller and handles their request.
- Request Human Assistance: When the caller asks for a human representative, the AI agent invokes the
connect_to_human webhook tool. - Transfer the Call: The
/connect-human Twilio Function initiates the transfer to the designated human phone number. - Handle the Human Answer: If the human answers, Twilio connects the caller and the human representative.
- Return to AI When Unanswered: If the human does not answer before the timeout, the
/after-dial function redirects the caller back to the AI agent. - Continue the Conversation: The AI agent apologizes for the unavailable representative and continues assisting the caller.
Result
The proposed workflow brings AI call handling, human assistance, and automatic fallback into one connected calling experience.
It is designed to support:
- Incoming calls routed to the ElevenLabs AI agent.
- On-demand transfers to a human representative.
- Automatic return to the AI agent when the human does not answer.
- Continued conversations without requiring the caller to restart the call.
The workflow will be validated against three scenarios: a normal AI call, a successful human transfer, and an unanswered human transfer followed by an AI fallback.
Tech Stack
- ElevenLabs: Provides the AI voice agent, conversation instructions, and
connect_to_human webhook tool. - Twilio: Handles incoming calls, call transfers, and the return-to-AI process.
- Call.com: Provides the caller number used for testing.
- GHL: Retains the existing calendar functionality without changes.
Where This Pattern Applies
The same approach can be used in voice automation systems where callers need access to both AI assistance and human support.
- Customer Support: Transfer complex customer queries to human agents.
- Sales: Connect interested prospects with sales representatives.
- Appointment Management: Escalate scheduling requests that require human assistance.
- Service Businesses: Route customer calls to available staff while maintaining AI support when they are unavailable.
- Call Centers: Combine automated call handling with human escalation and fallback.
The general pattern is to let AI handle routine conversations, transfer callers when human assistance is requested, and restore AI support when the human representative is unavailable.
Page · Plain text
From a Signed DocuSign Contract to a Master Sheet Row and an Itinerary Slide
Turning a signed DocuSign travel contract into a master sheet row, a filed contract and an itinerary slide, automatically.
Section: Make Automations
Project Overview
This Make automation supports operations for a group travel company that manages college formal events.
When a group signs a travel contract in DocuSign, the workflow processes the completed contract and supports three follow-up tasks: recording trip details in the master operations spreadsheet, filing the signed contract in the group's Google Drive folder, and producing a Friday, Saturday, and Sunday itinerary slide.
Tools: Make, DocuSign, Google Apps Script, Anthropic Claude (claude-sonnet-4-6), Google Sheets, Google Slides, and Google Drive.
01. The Challenge
Signed travel contracts contain information that must be transferred into several operational resources, including:
- Hotel names and room counts
- Check-in ages
- Buses and venues
- Event times
- Food and bar packages
- Payment and task due dates
Manually transferring these details into the master sheet, filing the contract, and building a customer-facing itinerary is repetitive and can lead to errors.
02. The Solution
A Make scenario automates the process after a DocuSign envelope is completed. It downloads the signed document, obtains structured contract data through a Google Apps Script web app, and uses Claude to generate the three-day itinerary text.
The workflow then routes the results into three paths: a new-contract path, an addendum path, and an archive path.
03. How It Works
Step 1: Detect the Signed Contract
The workflow starts when a DocuSign envelope is completed.
Step 2: Download the Document
Make downloads the signed contract for further processing.
Step 3: Extract Contract Information
An HTTP request sends the document to a Google Apps Script web app, which returns the contract fields as structured data.
Step 4: Generate Itinerary Text
Claude uses the structured fields to write the itinerary content for Friday, Saturday, and Sunday.
Step 5: Route the Results
A router directs the workflow into three paths:
- New Contract: Handles the new-contract path.
- Addendum: Handles the addendum path.
- Archive: Handles the archive path.
The scenario connects with Google Sheets, Google Slides, and Google Drive as part of the downstream processing.
Image: Part of the Make scenario: the DocuSign trigger and download, the HTTP call to the Apps Script web app, Claude, and a router that splits into Google Sheets, Slides and Drive paths.
04. Workflow Architecture
The workflow uses a router to separate the processing paths after the contract information and itinerary text have been prepared.
05. Example Output: Three-Day Itinerary
The example itinerary slide presents a group's Friday, Saturday, and Sunday schedule. The supplied screenshot has group, date, hotel, and company details blurred for privacy.
Suggested placement: Include the itinerary screenshot here, after the workflow architecture section, to show an example of the generated output.
Image: An example three-day itinerary slide (group, dates, hotel and company details blurred for privacy).
06. Tools and Integrations
- Make: Coordinates the automation and routes the workflow.
- DocuSign: Triggers the process when a contract envelope is completed and provides the signed document.
- Google Apps Script: Returns contract fields as structured data.
- Anthropic Claude: Generates the three-day itinerary text.
- Google Sheets: Supports master operations data.
- Google Slides: Supports the itinerary slide.
- Google Drive: Supports contract filing.
07. Outcome
The workflow automates key steps following contract completion, connecting signed-document processing with structured trip data, itinerary text generation, and downstream document handling.
Page · Plain text
Case Study Aircall Daily Warm Call
Automated pipeline that pulls fresh leads from a CRM every morning, sends a personalized heads-up email, and loads a ready-to-dial Aircall campaign before the sales rep even logs in.
Section: n8n Automations
Overview
This project automates daily warm-lead outreach using n8n, HubSpot, Gmail, and Aircall. Every weekday, it selects up to 30 eligible contacts, sends personalized emails, and adds successfully emailed contacts to a new Aircall campaign. It also updates HubSpot and maintains a backup log to prevent duplicate outreach.
The Problem
The sales team previously spent time every morning collecting warm leads from HubSpot, sending introductory emails, and manually adding contacts to Aircall campaigns.This repetitive process reduced selling time and created risks such as duplicate outreach, incorrect phone numbers, and calls being made to contacts who had not received the introductory email.
How It Works
- Scheduled Execution: n8n starts the workflow every weekday at 6:00 AM EST, before the sales team begins its day.
- Retrieve HubSpot Contacts: The workflow collects eligible contacts from a designated HubSpot segment, retrieving up to 500 contact IDs before applying the daily selection limit.
- Validate and Select Leads: It retrieves contact details, normalizes phone numbers into E.164 format, skips contacts already contacted that day, and selects up to 30 contacts.
- Prevent Duplicate Outreach: Selected contacts are marked in HubSpot with the current date. Their details are also saved in a backup data table for auditing.
- Send Personalized Emails: The workflow builds personalized HTML emails using the contact's first name and the sales representative's signature, then sends them through the representative's Gmail account.
- Create the Aircall Campaign: n8n duplicates a master Aircall campaign, adds the current date to its name, and prepares it for the selected contacts.
- Synchronize Email and Calls: Only contacts whose emails were successfully sent are added to the Aircall campaign. Their email activity is also logged on their HubSpot timeline.
- Launch the Campaign: The workflow launches the campaign so the sales representative can open Aircall and start calling without preparing the list manually.
The Result
The automation connects lead selection, personalized email outreach, and Aircall campaign preparation in one workflow. It removes the need to manually build daily call lists, keeps email and calling activities synchronized, and prevents contacts from being selected repeatedly on the same day.
Automation Testing Results
| Metric | Result |
|---|
| Contacts processed per test run | 30 |
| Email delivery success rate | 100% (30/30) |
| Aircall contact loading success | Approximately 93% |
| Duplicate contacts observed | None |
| Daily list and campaign preparation | Automated |
Note: Results are based on structured testing and dry runs. The remaining Aircall loading failures were linked to malformed phone numbers in legacy CRM records. Call connection rates, email replies, and sales impact have not yet been measured.
Tech Stack
- n8n: Manages the scheduled workflow, contact selection, email delivery, and campaign creation.
- HubSpot: Provides contact records, lead segments, daily outreach flags, and activity logging.
- Aircall: Creates and launches daily outbound calling campaigns.
- Gmail / Google Workspace: Sends personalized emails from the sales representative's mailbox.
- Backup Data Table: Maintains an independent record of selected contacts for auditing and troubleshooting.
Where This Pattern Applies
- Sales Teams: Prepare daily calling lists and coordinate email and phone outreach.
- B2B Companies: Follow up with warm leads collected through CRM segments.
- Lead Generation Agencies: Automate outreach preparation for multiple sales representatives.
- Customer Acquisition Teams: Keep email introductions and follow-up calls organized in one process.
Page · Plain text
Webex Recording Transcription and Case File Automation
Automating meeting transcription storage, case identification, and record tracking using Zapier, Webex, Box, Calendly, Microsoft Excel, AI, and Google Sheets.
Section: Zapier Automations
Overview
This solution automates the process of retrieving Webex meeting transcripts, matching meetings with client cases, storing documents in Box, and tracking records in Google Sheets. It uses Calendly matching for direct case identification and AI-assisted matching when a usable case number is not available.
The Problem
Meeting transcripts need to be associated with the correct client and case before they can be stored and tracked. Handling this manually requires staff to review meeting details, identify the relevant case, download transcripts, locate the correct Box folder, upload files, and update tracking records.
The process becomes more difficult when meeting information does not contain a usable case number. An automated approach was needed to support both direct case matching and matching through existing client records.
How It Works
- Receive Meeting Data: A Webhook triggers the automation when meeting-related information is received.
- Retrieve Webex Details: The workflow fetches meeting information and checks whether a transcription is available.
- Collect Participants: It retrieves participant details and formats meeting start and end times.
- Match Calendly Events: JavaScript compares meeting information with scheduled Calendly events and retrieves the corresponding invitee details.
- Identify the Case: The workflow checks whether a valid case number is available through the Calendly match.
- Use AI When Needed: If direct matching does not provide a usable case number, the workflow downloads client records from Excel as CSV and uses AI by Zapier to identify a matching client and case number.
- Find the Box Folder: The identified case number is used to search for the corresponding folder in Box.
- Download and Store the Transcript: The Webex transcription is retrieved and uploaded to the relevant Box folder.
- Update Tracking Records: Google Sheets logs the participant name, available case number, and Zapier run reference.
Result
The automation brings meeting retrieval, case identification, transcript storage, and record tracking into one connected process. It supports both direct Calendly-based matching and AI-assisted client matching, allowing transcripts to be routed according to the information available.Box maintains the associated transcript documents, while Google Sheets provides a record of the processed meetings and their related references.
Daily Processing Metrics
| Metric | Daily Volume |
|---|
| Meetings processed | 5 |
| Meetings with available transcripts | 3 |
| Transcripts uploaded to client folders in Box | 3 |
Tech Stack
- Zapier: Connects applications and manages automation, filters, loops, and conditional paths.
- Webex: Provides meeting information and transcription access.
- Calendly: Supplies scheduled meeting and invitee information.
- JavaScript: Handles meeting matching and data processing.
- Box: Stores transcripts in the corresponding case folders.
- Google Sheets: Maintains meeting and case tracking records.
Where This Pattern Applies
The same approach can be used wherever incoming documents or recordings need to be matched with existing client records and stored in the correct location.
- Legal Services: Match meeting recordings and transcripts with case files.
- Healthcare: Organize consultation recordings and related documents.
- Insurance: Associate recorded client statements with claim records.
- Recruitment: Match interview recordings with candidate profiles.
- Customer Support: Attach call transcripts to customer and support records.
The general pattern is to retrieve incoming information, identify its matching record, store the associated document, and update the tracking system. The matching logic and connected applications can be adapted to different business processes.
Page · Plain text
A Slack Bot That Answers Trip Questions from an Ops Master Sheet
A Make scenario that lets a team member ask a plain-English trip question in Slack and get an answer drawn only from the ops master sheet.
Section: Make Automations
Project Overview
This internal operations tool helps a group travel team find trip information using plain-English questions in Slack, without manually searching through a large Google Sheets workbook.
The team stores trip information in the MASTER tab of the Master Ops Fall 26/Spring27 workbook. Each row represents a group trip and contains information about dates, destinations, operations coordinators, sales representatives, contracts, hotels and rooming, transport, events, task due dates, and payment status.
Tools: Make, Slack, Google Sheets, and Anthropic Claude (claude-sonnet-4-6).
01. The Problem
The operations master sheet contains more than 55 labelled fields per trip, spanning columns A to BH.
Finding a specific detail—such as a group's hotel information or room counts—requires locating the correct trip row and navigating to the relevant column. This makes answering everyday operational questions more time-consuming.
02. The Solution
A six-module Make scenario connects Slack with Google Sheets and Claude to process questions and return relevant trip information.
The workflow:
- Receives the question and Slack channel through a webhook.
- Uses Claude to convert the question into structured search terms.
- Searches the master sheet for matching trips.
- Combines the matching rows into readable text.
- Uses Claude again to generate an answer based only on the retrieved information.
- Posts the answer back to the same Slack channel.
03. How It Works
Step 1: Receive the Question
A custom webhook receives the incoming question and the Slack channel information.
Step 2: Identify the Search Terms
Claude interprets the plain-English question and converts it into structured search terms that can be used to find relevant trips.
Step 3: Search Google Sheets
The scenario searches the operations master sheet for trips matching the extracted criteria.
Step 4: Format the Matching Results
The matching spreadsheet rows are combined into readable text using a text aggregator.
Step 5: Generate the Answer
Claude uses the retrieved text to answer the original question. The answer is restricted to the information provided by the matching spreadsheet results.
Step 6: Reply in Slack
The final answer is posted back to the same Slack channel where the question originated.
Image: The Make scenario: a custom webhook, Claude turning the question into search terms, a Google Sheets search, a text aggregator, Claude answering from the results, and a Slack message.
04. Workflow Architecture
The scenario separates question interpretation, data retrieval, result formatting, and answer generation into distinct steps.
05. Example Use Case
A team member asks:
“How many groups do we have in Nashville from April 9–11, 2027?”
The bot searches for trips matching the destination and dates, then returns the matching groups with their trip dates and destinations in Slack. The example screenshot shows group names blurred for privacy.
Image: An example answer in Slack: the question, the search terms Claude worked out, and the matching groups with their dates and destination (group names blurred for privacy).
06. Tools and Integrations
- Make: Connects the workflow modules and coordinates processing.
- Slack: Provides the interface for asking questions and receiving answers.
- Google Sheets: Stores the operations master data used to answer questions.
- Anthropic Claude: Converts questions into search terms and generates answers from the retrieved results.
07. Outcome
The scenario gives the operations team a conversational way to retrieve trip information from a large master sheet. Team members can ask questions in Slack and receive structured answers based on matching spreadsheet records, without manually searching across the workbook.
Page · Plain text
HubSpot Industry Classifier with Gemini
An automated workflow that classifies HubSpot companies into industry groups using Google Gemini and sends uncertain records for human review.
Section: n8n Automations, AI Agents
Overview
This project uses n8n and Google Gemini Flash to automatically classify company records in HubSpot. The workflow runs every hour, retrieves companies from a designated HubSpot list, and checks whether their industry group is already assigned. Gemini analyzes company information and suggests an industry based on the categories available in HubSpot.
To maintain CRM data quality, the workflow validates every suggested category and checks its confidence score before updating a record. Companies that cannot be classified reliably are marked as Needs R&D for human review. A dry-run mode also allows the team to test the workflow without changing live CRM records.
The Problem
Many HubSpot company records may have missing or inconsistent industry classifications. Updating these records manually takes time and can lead to inconsistent categories.
Using AI without proper checks also creates risks, such as invented industry groups, unreliable classifications, and repeated processing of companies that have already been classified.
How It Works
- Scheduled Execution: n8n starts the workflow every hour and loads its configuration, including the company limit, confidence threshold, and dry-run setting.
- Retrieve Company Records: The workflow retrieves companies from a designated HubSpot list, collecting up to 100 records per run.
- Check Company Information: It retrieves each company's name, domain, website, and existing industry group. Already classified companies and records without usable information are skipped.
- AI Classification: Google Gemini Flash analyzes the available company information and returns a suggested industry group, confidence score, exclusion flag, and reasoning.
- Validate the Result: n8n checks whether the suggested industry exists in HubSpot's allowed options. It also applies a minimum confidence threshold of 0.6 and limits confidence to 0.65 for companies without a domain.
- Update or Flag Records: Valid classifications are written to HubSpot with relevant classification details. Uncertain or excluded companies are marked as Needs R&D for human review.
- Control Updates: Dry-run mode prevents changes to live records during testing. A Wait node also separates updates to help manage HubSpot API rate limits.
The Result
The workflow provides an automated and controlled process for classifying HubSpot company records. It uses Gemini to suggest categories while HubSpot provides the approved industry options. Validation rules, confidence checks, and human-review routing help prevent unreliable classifications from being accepted automatically.
Workflow Configuration Metrics
| Metric | Result |
|---|
| n8n workflow nodes | 22 |
| Execution schedule | Every hour |
| Maximum companies per run | 100 |
| Confidence threshold | 0.6 |
| No-domain confidence cap | 0.65 |
| AI model | Google Gemini Flash |
Note: These figures describe the workflow configuration. Actual companies processed, classification accuracy, human-review rate, and time saved have not yet been measured.
Tech Stack
- n8n: Runs the scheduled automation and manages the classification process.
- HubSpot: Provides company records, approved industry groups, and the destination for validated updates.
- Google Gemini Flash: Analyzes company information and suggests industry classifications with confidence scores and reasoning.
Where This Pattern Applies
- CRM Management Teams: Keep company industry fields consistent across large CRM databases.
- Sales Teams: Organize company records for better segmentation and reporting.
- Marketing Teams: Group companies into relevant industries for targeted campaigns.
- Business Data Teams: Automate data enrichment while routing uncertain records for manual review.
This pattern is useful for businesses that need to enrich large datasets with AI while maintaining control over data quality and ensuring uncertain results receive human review.
Page · Plain text
Enterprise Ticketing & Revenue Data Pipeline
An automated reporting system that collects ticket sales data from multiple vendors, calculates festival revenue and attendance, and updates a central dashboard using Python and Google Cloud.
Section: Python Automation
Overview
Palm Tree Crew, a live music festival organizer, needed a reliable way to track ticket sales, revenue, and attendance across multiple festival locations. We developed a Python-based automation pipeline on Google Cloud that collects daily reports from Ticketmaster, Front Gate Tickets, and Posh through Gmail. The system processes the reports, applies the required business rules, stores the results in BigQuery, and updates a Google Sheets dashboard for the management team.
The Problem
The operations team had to download daily ticket reports from different vendors, extract the information from PDFs and emails, and manually enter the numbers into Google Sheets. They also had to calculate multi-day attendance and track revenue from separate VIP and sponsorship spreadsheets. This process took hours, increased the risk of errors, and made it difficult for management to view total revenue and remaining ticket capacity in one place.
How It Works
- Start the Automation: Google Cloud Scheduler triggers the Python service on Cloud Run at the scheduled reporting time.
- Collect Vendor Reports: The system uses the Gmail API to retrieve daily audit emails from Ticketmaster, Front Gate Tickets, and Posh.
- Extract Ticket Data: Custom Python parsers process Ticketmaster PDF reports and Front Gate HTML email tables to extract ticket sales information.
- Apply Business Rules: The system calculates daily attendance, 24-hour sales rates, and remaining capacity. It also splits two-day passes across the correct festival days.
- Store Data in BigQuery: Processed information is saved in three tables: raw reports, parsed report lines, and daily snapshots.
- Update the Dashboard: The Google Sheets API rebuilds the executive dashboard with ticket sales, revenue, attendance, sales rates, and remaining capacity.
- Include Offline Revenue: VIP table and sponsorship data from external spreadsheets is connected through Google Sheets IMPORTRANGE, bringing online and offline revenue into one view.
Result
The system brings ticket sales collection, revenue calculations, and reporting into one automated pipeline.
- Replaces hours of manual report collection and data entry with scheduled automation.
- Combines ticket sales data from multiple vendors in one dashboard.
- Reduces manual calculation errors and duplicate ticket counting.
- Provides a combined view of online ticket sales, VIP tables, and sponsorship revenue.
- Displays daily attendance, sales rates, and remaining ticket capacity.
- Allows new festival shows and ticketing platforms to be added through a standard onboarding template.
Tech Stack
- Python: Handles report extraction, data processing, and business calculations.
- Google Cloud Run: Hosts and runs the Python automation service.
- Google Cloud Scheduler: Triggers the pipeline at scheduled intervals.
- BigQuery: Stores original reports, parsed ticket data, and calculated daily snapshots.
- Gmail API: Retrieves daily ticketing reports from vendors.
- Google Sheets API: Builds and updates the executive dashboard.
- IMPORTRANGE: Connects external VIP table and sponsorship revenue spreadsheets.
Where This Pattern Applies
The same approach can help organizations that collect operational and financial data from multiple external sources.
- Event Organizers: Combine ticket sales and attendance data across different events.
- Music Festivals: Track revenue, ticket sales, and venue capacity across multiple locations.
- Ticketing Companies: Process reports from different ticketing platforms.
- Hospitality Businesses: Combine revenue and booking data from multiple systems.
- Finance Teams: Automate daily reporting and bring information from separate spreadsheets into one dashboard.
The general approach is to collect reports from different sources, extract and process the data, apply business rules, and deliver updated results through a centralized dashboard.
Page · Plain text
Salesbeast AI Outbound Sales Machine
An automated outbound sales system for discovering target companies, enriching decision-maker profiles, evaluating lead quality, and generating personalized email outreach.
Section: n8n Automations
Overview
Salesbeast is a three-layer AI-powered outbound sales system designed to automate company discovery, decision-maker identification, lead qualification, and personalized email generation.The system collects business information from multiple sources, evaluates potential leads using qualification rules, and uses AI to research decision-makers and prepare tailored email variations.
The Problem
Finding suitable companies and identifying the right people to contact requires searching multiple platforms, reviewing company websites, checking business information, and researching individual profiles.
After collecting this information, sales teams must manually assess lead quality and write personalized outreach messages. This process can become time-consuming and difficult to manage across large prospect lists.
How It Works
- Collect Company Data: D7 Networks identifies companies based on industry, location, and company size criteria.
- Enrich Business Information: Google Maps API retrieves ratings, reviews, phone numbers, and business hours. Website scraping collects company information, services, and blog content.
- Identify Decision-Makers: Apollo.io searches for employees based on job titles and retrieves contact details, LinkedIn profiles, and professional background information.
- Store Enriched Records: Company information, decision-maker profiles, and enrichment logs are organized in PostgreSQL.
- Qualify Leads: The qualification layer evaluates company size, Google ratings, review counts, industry, and business activity.
- Score and Segment: Leads receive a score out of 100 and are assigned categories such as Reputation Recovery, Moderate Reputation, High Authority, or industry-specific segments.
- Research Decision-Makers: AI analyzes company information and professional profiles to identify relevant pain points, opportunities, and talking points.
- Generate Personalized Emails: The system creates three email variations for each decision-maker: pain-focused, growth-focused, and authority-focused.
- Review Email Quality: Generated emails are scored, and only emails scoring above 75 are approved. Lower-scoring emails are rejected for regeneration.
Result
The system connects company discovery, contact enrichment, lead qualification, and personalized email generation into one automated process.
It provides:
- Enriched company and decision-maker records.
- Structured lead scoring and segmentation.
- Industry-specific targeting.
- Research-based personalization.
- Three email variations per qualified decision-maker.
- Quality-scored email drafts stored for further use.
The documented design specifies an average email quality score of 88/100. This is a design-document figure, not an independently verified production performance metric.
Image: Figure 1. Company Data Collection & Enrichment
Image: Figure 2. Decision-Maker Identification
Image: Figure 3. AI Lead Qualification & Email Generation
Tech Stack
n8n: Workflow automation and coordination across the three processing layers.
D7 Networks: Company discovery based on search criteria.
Google Maps API: Business details, ratings, reviews, and contact information.
Apollo.io: Decision-maker identification and professional profile enrichment.
AI Models: Lead research, qualification support, and personalized email generation.
PostgreSQL: Structured storage for leads, decision-makers, qualification results, and email variants.
Where This Pattern Applies
- B2B Sales: Identify target companies and relevant decision-makers.
- Marketing Agencies: Build enriched prospect lists for outreach campaigns.
- Recruitment: Research organizations and identify relevant hiring contacts.
- Business Development: Discover companies matching specific market criteria.
- Lead Generation Agencies: Qualify and segment prospects before outreach.
- SaaS Companies: Build targeted outreach campaigns using company and professional profile information.
The general pattern is to combine business data collection, contact enrichment, qualification rules, and AI-assisted personalization into a connected outbound sales workflow.
Page · Plain text
Newsletter Generator: From a Google Sheets Row to a Draft Campaign
A Make scenario that turns one row of a Google Sheets newsletter planner into a finished draft campaign in Campaign Monitor, in one of three layouts chosen by the editor.
Section: Make Automations
Project Overview
This Make scenario automates the creation of newsletter draft campaigns using content stored in Google Sheets. Editors prepare the newsletter information in a spreadsheet, select one of three templates, and mark the row for creation. Make then builds the newsletter and creates a draft campaign in Campaign Monitor.
01. The Challenge
Creating a newsletter manually requires editors to copy titles, images, excerpts, links, and category labels into an email template. This process must be repeated for news articles, sponsored posts, a destination report, and a podcast episode.
02. The Solution
The Make scenario connects Google Sheets with Campaign Monitor to generate a newsletter draft from a single spreadsheet row. It uses the selected template to build the campaign content and updates the row when the process is complete.
03. How It Works
Step 1: Prepare the Newsletter
The editor fills in a Google Sheets row with the content for three news posts, three sponsored posts, a destination report, and a podcast episode.
Step 2: Select a Template
The editor chooses template 1, 2, or 3 and sets the Create Newsletter cell to Create.
Step 3: Find the Requested Row
Make searches the sheet on its schedule for a row marked Create and processes one row at a time.
Step 4: Route to the Selected Layout
A router directs the row to one of three routes based on the selected template number.
Step 5: Build the Newsletter
A code step assembles the newsletter content, including banners, images, category labels, titles, excerpts, links, and buttons. The layout varies according to the selected template.
Step 6: Create the Draft Campaign
An HTTP request sends the generated content to the Campaign Monitor API, which creates a draft campaign using the selected template.
Step 7: Update the Spreadsheet
After the campaign is created, Google Sheets is updated with the status Done.
Image: The Make scenario: Google Sheets searches for a row marked Create, a router picks one of three templates, a code step builds the newsletter content, an HTTP call creates the campaign from the template, and Google Sheets updates the row. A Skip step on each route handles errors.
04. Newsletter Content Structure
The generated newsletter includes:
- A top banner
- Three news posts
- A banner separating content sections
- Three sponsored posts
- A destination report
- A podcast episode
- An additional banner
News and sponsored posts include images, category labels, titles, excerpts, and links. The destination report includes a destination name and description, while the podcast section includes its date, title, description, and listening link.
05. Template Options
The scenario supports three newsletter layouts:
- Template 1: A three-row layout.
- Templates 2 and 3: Mixed layouts with two posts side by side and one centred below, using their respective templates.
06. Content Handling
The code includes defaults for missing content. Missing news or sponsored-post images use a default image, missing links point to the main website, and each campaign receives a unique name with a timestamp. The subject line and header date default to the current month and year. Sender details and the subscriber list are also set in the code step.
07. Workflow Architecture
Each template route builds the campaign content and sends it to Campaign Monitor. A Skip step on each route handles errors.
08. Tools and Integrations
- Make: Coordinates the workflow, routing, and newsletter generation.
- Google Sheets: Stores newsletter content, template selection, and processing status.
- Campaign Monitor: Creates the newsletter as a draft campaign.
09. Review and Error Handling
The campaign is created as a draft in Campaign Monitor so the team can review it before sending. If Campaign Monitor returns an error, the scenario skips that run instead of stopping with an error.
10. Outcome
The scenario allows editors to prepare newsletter content in Google Sheets and generate a corresponding Campaign Monitor draft without manually copying each content block into the email editor. The team can review the generated draft in Campaign Monitor before sending it.
Page · Plain text
End of part 2 of 7. Continue with part 3.