Solutions Showcase: part 5 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
AI-Powered Construction Report SaaS (MeinBüromeister)
Turning construction-site voice notes, photos, and messages into structured reports through an automated AI-powered backend for German trade companies.
Section: Custom SaaS Platforms
Overview
MeinBüromeister is a B2B SaaS platform for German construction and trade companies. It allows workers to submit job updates through WhatsApp instead of preparing every report manually. The backend organizes incoming information, generates structured reports, and asks workers to review them before submission.
The Business Problem
Construction workers often send separate voice notes, photos, and text corrections from job sites. Office staff must identify the correct customer and project, organize materials and working hours, and format the information into professional reports. This creates repetitive administrative work and makes report preparation more time-consuming. The goal was to reduce this manual effort while keeping workers involved in reviewing and approving their reports.
The Solution
An n8n-based backend receives WhatsApp messages and groups related inputs into a single session. OpenAI Whisper transcribes voice recordings, while Claude AI extracts relevant report information into structured data. After the worker reviews and approves the report, the backend stores it in Supabase for delivery to the office dashboard. Supporting workflows automate customer onboarding, subscription management, team access, and error handling.
Project Snapshot
A production backend connecting WhatsApp messaging, AI-powered report extraction, worker approval, report storage, customer onboarding, and subscription lifecycle management.
How the System Works
System Architecture
The backend is organized around an n8n automation layer that sits between WhatsApp, the AI services used for transcription and extraction, and the Supabase/Stripe infrastructure that powers the office dashboard.
Supporting Integrations
- Stripe: Checkout, subscription lifecycle events, plan changes, and subscription-based access rules.
- Supabase Auth: Authentication support for the application.
- Supabase Storage: Storage for uploaded photos and other media.
- Docker: Supports the self-hosted deployment environment.
Core Automation Workflows
The backend is built around interconnected n8n workflows that automate WhatsApp message handling, AI-powered report generation, customer onboarding, and subscription management. Each workflow handles a specific responsibility and integrates with the relevant APIs and backend services to support the complete reporting lifecycle. Some main automation workflows are shown below.
1. Core Onboarding & Workflow Management
This workflow handles company onboarding, setup-code verification, worker registration, subscription checks, report approval, project management, and notifications through interconnected n8n automation nodes.
Image: Core onboarding and workflow management: company setup, worker registration, subscription checks, report approval, project handling, and notifications across 15 interconnected automation groups.
2. AI-Powered Report Processing Workflow
This workflow processes WhatsApp messages using Whisper and Claude AI to extract structured report data, enrich customer and project details, validate reports, and handle database updates and notifications.
Image: AI-powered report processing: message intake, voice transcription, Claude-based data extraction, report generation, and save/notification handling.
Product Experience
Report inbox
Image: The office inbox organizes incoming reports by date, technician, customer/project, category, and status.
Customers and projects
Image: The project view groups customers and highlights open-report counts and recent work.
WhatsApp work history
Image: Workers review and approve each AI-generated report directly in WhatsApp before it goes to the office.
- <30s: Voice note to structured report
Image: Once approved, the report is saved, confirmed back to the worker on WhatsApp, and delivered to the office as a PDF.
Core Backend Capabilities
- AI Report Extraction: Supports four report categories (Rapport, Aufmaß, Neues Angebot, and Notiz). The AI extracts work descriptions, materials, dimensions, and working hours while using prompt guardrails to reduce invented details.
- Multi-Input Session Handling: Groups related voice notes, photos, captions, and corrections into a single processing session instead of treating every incoming message as a separate report.
- Project Matching and Clarification: Uses available employee and project records to associate reports with the correct destination. When a match is ambiguous, the workflow can request clarification.
- Onboarding and Access Management: Supports company setup, worker invitations, registration tracking, and access checks to ensure incoming messages are routed correctly.
- Subscription Lifecycle Management: Handles relevant Stripe events and subscription states, including active, canceling, and canceled subscriptions. It also manages plan mapping and seat limits.
- Failure Handling and Validation: Validates incoming data and AI-generated output, handles incomplete sessions and invalid actions, and provides controlled paths for processing failures.
Results & Metrics
- 5: Production workflows
- 5: Testing rounds
- 30+: Test scenarios per round
- 25+: Bugs found & fixed
The project delivered five production workflows connecting WhatsApp, AI-powered report extraction, Supabase, and Stripe. Across five rounds of end-to-end testing, more than 25 bugs were identified and fixed, with over 30 test scenarios executed per round.
Technical Challenges & Solutions
During development and end-to-end testing, several integration and AI reliability issues required targeted solutions.
1. Stripe Subscription Data Handling
Challenge
The Stripe checkout event did not always contain all the subscription information required by the workflow.
Solution
Retrieved the complete subscription details directly through the Stripe API before continuing with subscription processing.
Outcome
Improved the reliability of subscription data handling.
2. Subscription Plan Mapping
Challenge
Mapping subscription plans based on payment amounts could lead to incorrect plan identification.
Solution
Used Stripe product IDs to identify plans instead of relying on monetary amounts.
Outcome
Made plan identification more consistent across subscription events.
3. AI Hallucination Control
Challenge
Claude AI could occasionally introduce materials or details that were not present in the worker’s input.
Solution
Refined the AI prompt with guardrails to discourage unsupported details and keep extraction grounded in the supplied information.
Outcome
Improved the consistency of structured report generation.
4. Supabase PATCH Response Handling
Challenge
Some Supabase PATCH operations returned empty responses, creating difficulties for downstream workflow nodes.
Solution
Explicitly referenced upstream node outputs where required instead of relying on the PATCH response to provide all subsequent data.
Outcome
Made downstream data handling more reliable.
5. End-to-End Integration Testing
Challenge
The system depended on multiple connected services, including WhatsApp, AI models, Supabase, and Stripe, making integration failures difficult to isolate.
Solution
Conducted five rounds of end-to-end testing, covering more than 30 scenarios per round, and fixed over 25 identified bugs.
Outcome
Improved integration reliability across the production workflows.
Key Takeaways & Future Development
Key Takeaways
- Workflow automation: Built and integrated five production n8n workflows connecting WhatsApp, AI services, Supabase, and Stripe.
- AI reliability: Improved structured report extraction through prompt engineering, validation, and guardrails against unsupported details.
- Integration engineering: Resolved issues involving Stripe subscription events, plan mapping, and Supabase response handling.
- End-to-end testing: Completed five testing rounds, identifying and fixing more than 25 bugs across the integrated system.
- Cross-functional collaboration: Coordinated with the frontend engineer on database requirements and data contracts to connect backend workflows with the React dashboard.
Closing Summary
MeinBüromeister demonstrates how workflow automation, AI-powered information extraction, and integrated SaaS infrastructure can simplify construction reporting. The primary contribution was engineering the backend workflows and integrations that connect field communication with structured reports, subscription management, and the office dashboard.
Page · Plain text
AI-Powered 24/7 Voice Support Agent for eCommerce Stores
A 24/7 AI voice agent that answers store calls using your product and policy data, escalating only complex calls to humans.
Section: n8n Automations, AI Agents, AI Agents for Ecommerce
Project Overview
The AI-Powered 24/7 Voice Support Agent automates customer support calls for eCommerce stores using conversational AI and a centralized knowledge base. Built around VAPI, n8n, Slack, and Google Sheets, it can answer common questions about products, pricing, shipping, returns, and store policies through natural voice conversations.
The system understands customer intent, retrieves relevant store information, responds in real time, and supports optional escalation for complex or high-risk issues. This reduces repetitive work for support teams while providing customers with access to assistance around the clock.
Technologies: VAPI · n8n · Slack · Google Sheets · AI Voice Agent
01. The Problem: Support Calls Don’t Scale
Before automation, customer support teams handled incoming calls manually.
Common challenges included:
- Repeating answers about products, sizes, shipping, returns, and order status.
- Switching between store systems and knowledge documents during calls.
- Missing calls during peak hours or outside business hours.
- Providing inconsistent answers depending on the agent handling the call.
Impact per team
- Long wait times and dropped calls.
- Frustrated customers seeking answers to basic questions.
- Inconsistent use of product and policy information.
- High dependency on human agents for repetitive FAQs.
Core challenge: Build a 24/7 support system that can resolve common customer queries using the store’s own knowledge while escalating issues that require human attention.
02. Results After Automation
After implementation, the voice agent can answer calls around the clock and handle common customer questions automatically.
Key improvements
- Calls answered without waiting for a human agent.
- Common FAQs handled through conversational AI.
- Complex or high-risk issues escalated when required.
- Responses grounded in available store product and policy information.
- Human agents able to focus on more complex customer needs.
Time and effort savings
Before
- Approximately 100–200 repetitive calls per week.
- Around 2–3 hours per day spent answering FAQs.
After
- Routine call handling automated.
- Human involvement primarily reserved for escalations and exceptions.
Estimated monthly impact
- Approximately 40–60 hours saved per support team.
- More time available for complex and high-value support cases.
Consistency improvements
- Responses use the configured product and policy knowledge base.
- Reduced reliance on improvised answers.
- Easier alignment with updated store information when the knowledge base is maintained.
03. The Solution: AI-Powered Voice Agent
The system acts as a virtual customer support representative capable of handling common eCommerce questions independently.
It:
- Provides natural, conversational voice responses 24/7.
- Uses store knowledge covering products, pricing, inventory, policies, and FAQs.
- Answers common questions without requiring a human agent.
- Maintains conversational context across follow-up questions.
- Supports optional escalation for complex or high-risk calls.
- Can send call summaries and capture relevant information through n8n, Slack, and Google Sheets.
04. How the System Works
Phase 1: Knowledge Base and Store Data
Relevant store information is collected and organized for retrieval during calls.
This may include:
- Product details, sizes, colors, and availability.
- Pricing and promotions.
- Shipping fees and delivery times.
- Return, refund, and exchange policies.
- Frequently asked questions.
The knowledge base should be kept up to date to reduce the risk of outdated responses.
Phase 2: Incoming Call and Intent Detection
- A customer calls the support number.
- VAPI answers with a configured greeting and voice.
- The customer's speech is converted into text.
- AI identifies the intent, such as a product question, order inquiry, or policy clarification.
Phase 3: Knowledge Base Lookup
The system retrieves relevant information to answer the customer's question.
For example:
- Product specifications and availability.
- Delivery timelines and shipping costs.
- Return and refund conditions.
- Promotions and bundles.
- Order details for authenticated users, where the required integration is configured.
Phase 4: Voice Response Generation
- AI prepares a relevant, conversational answer.
- Text-to-speech generates the spoken response.
- The answer is played to the customer in real time.
Phase 5: Multi-Turn Conversation
The agent maintains context throughout the call, allowing customers to ask follow-up questions about products, orders, and policies without restarting the conversation.
Phase 6: Human Escalation and Call Summary
When configured, complex or high-risk calls can be forwarded to a human agent. The workflow may also support callback requests or ticket creation.
After the call:
- VAPI sends call-end information to an n8n webhook.
- n8n processes the call summary and relevant details.
- Slack receives the summary.
- Google Sheets records applicable information.
05. Business Value
- 24/7 Availability: Customers can receive assistance outside normal business hours.
- Reduced Support Workload: AI handles repetitive FAQs automatically.
- Consistent Answers: Responses are based on configured store knowledge.
- Faster Resolution: Common questions can be answered in a short conversation.
- Better Knowledge Utilization: Product and policy information supports customer interactions.
- Human Escalation: Complex cases can be routed to people when required.
- Call Visibility: Summaries and captured details can be recorded for follow-up.
06. Expected Impact
Time Savings
Automating repetitive calls reduces the time support agents spend answering routine questions, allowing them to focus on complex issues.
Error Reduction
Using maintained product and policy data helps reduce inconsistent or improvised answers.
Call Handling Speed
Common questions can potentially be resolved in one or two exchanges, depending on their complexity.
Knowledge Utilization
Centralized store information can be reused across voice interactions, improving consistency and accessibility.
Estimated time savings: Approximately 40–60 hours per month per support team, depending on call volume and automation coverage.
07. Workflow Architecture
The main components work together as follows:
- VAPI: Handles voice interactions and call management.
- Knowledge Base: Supplies relevant product and policy information.
- AI Processing: Understands customer questions and prepares responses.
- n8n: Processes call-end events and coordinates follow-up actions.
- Slack: Delivers call summaries to the support team.
- Google Sheets: Stores applicable call records and captured information.
08. How to Replicate the System
Step 1: Configure the VAPI Voice Agent
- Create the voice agent and configure its greeting and voice tone.
- Connect the store knowledge base.
- Test its ability to answer FAQs and product or policy questions.
Step 2: Configure the Call-End Webhook
- Create a webhook node in n8n.
- Configure VAPI to send call-end information to the webhook.
- Verify that the webhook receives the expected call details.
Step 3: Import the n8n Workflow
- Open
ShopTalk AI – Call Summary & Lead Capture (1).json. - Import the workflow into n8n.
- Connect the VAPI webhook to the workflow.
- Configure Slack and select the appropriate summary channel.
- Connect Google Sheets and select the spreadsheet and required columns.
Step 4: Test the Flow
- Make a test call.
- Ask product or policy questions.
- Test a follow-up question.
- End the call.
- Verify that the call summary appears in Slack.
- Confirm that a row is added to Google Sheets when applicable.
Step 5: Activate the Workflow
Once testing is complete, activate the n8n workflow and verify that the VAPI webhook is configured correctly.
The voice agent can then handle customer calls continuously, while n8n processes call summaries and related follow-up actions.
09. Final Outcome
The AI-powered voice support system transforms repetitive customer support calls into a more consistent and scalable operation.
- Customers can receive answers at any time.
- Human agents spend less time handling repetitive FAQs.
- Product and policy information supports consistent responses.
- Complex issues can be escalated when necessary.
- Call summaries and relevant records improve follow-up visibility.
- Support teams can handle routine demand without relying exclusively on additional staff.
The result: A scalable, 24/7 voice support experience that reduces repetitive work while keeping human agents available for the issues that need them most.
Page · Plain text
ClickUp: Automating Operations for Veterinary Specialist Partners
ClickUp setup used to automate operations for a veterinary specialist partnership.
Section: ClickUp Setups
ClickUp: Automating Operations for Veterinary Specialist Partners
A centralized ClickUp operations system integrating appointment scheduling, patient information, lab results, reminders, and referral coordination for Veterinary Specialist Partners (VSP).
Category: ClickUp Setups Technologies: ClickUp, Calendly, Jotform, Gmail, RingCentral, Slack
1. Project Overview
Veterinary Specialist Partners (VSP) operates veterinary facilities in Louisville and Evansville, providing specialized care for pets with complex medical conditions. Managing appointments, patient information, lab communications, and follow-ups manually created administrative overhead and made coordination across locations more difficult.
The solution used ClickUp as a central operations workspace, connecting scheduling and communication tools through automated workflows. Appointments, related information, reminders, cancellations, and follow-up activities could be managed with greater consistency.
2. The Challenge
Before the implementation, several operational processes depended on manual work.
Fragmented Appointment Management
Appointments were booked through external scheduling tools and needed to be organized across different locations and appointment types. Staff had to maintain accurate records and keep appointment statuses up to date.
Incomplete Patient Information
Required forms, medical details, and laboratory results could arrive through separate systems and email communications. Locating the relevant information alongside an appointment required additional coordination.
Manual Reminders and Follow-Ups
Patient reminders, form-completion checks, and post-appointment follow-ups required staff attention. Inconsistent follow-up processes could result in missed administrative steps.
Cancellation and Record Synchronization
When appointments changed or were cancelled, the corresponding records and lists needed to remain consistent across the scheduling system and ClickUp.
3. Project Objectives
The project focused on the following objectives:
- Centralize appointment management: Maintain a unified view of appointments across Louisville and Evansville.
- Automate scheduling workflows: Synchronize new bookings and cancellations from Calendly.
- Connect patient information: Link Jotform submissions and relevant medical information to appointment records.
- Improve communication: Automate appointment reminders using email and RingCentral SMS.
- Organize laboratory communications: Attach incoming lab emails and documents to the relevant ClickUp tasks.
- Maintain accurate records: Synchronize custom fields and clean up past appointments across lists.
- Improve operational visibility: Give staff a more consistent way to track appointments, referrals, and follow-up activities.
4. The Solution
4.1 Calendly to ClickUp Integration
Calendly bookings are captured and converted into ClickUp tasks.
- New appointments are added to the appropriate ClickUp lists.
- Appointment types and locations are organized separately.
- Tasks use relevant tags and custom fields for easier identification.
- A centralized Appointments list consolidates bookings from both locations for teams that need an organization-wide view.
Image: Calendly-to-ClickUp appointment automation screenshot from Make.com
This setup reduces the need to manually transfer appointment information between systems.
4.2 Jotform Integration and Patient Information
The workflow monitors required Jotform submissions associated with scheduled appointments.
- Patient form submissions are tracked.
- Relevant medical information is connected to the corresponding ClickUp appointment record.
- Missing forms can trigger email and SMS reminders two days before the appointment.
- Staff can access the relevant information from the associated task.
This helps staff identify outstanding administrative requirements before appointments take place.
4.3 Laboratory Email and Attachment Management
Gmail integration brings relevant laboratory communications into ClickUp.
Incoming lab emails and attachments are added to the corresponding patient or appointment task, making related information easier to locate without manually searching through email conversations.
4.4 Appointment Cancellations
Cancellation handling keeps appointment records aligned between Calendly and ClickUp.
- Cancelled appointments are removed from active appointment lists.
- Cancelled records are moved to a dedicated Cancelled Appointments list.
- Staff can also initiate cancellations through a ClickUp dropdown field, with the change reflected in the scheduling workflow.
Image: ClickUp custom-field automation screenshot.
This provides a clearer distinction between upcoming and cancelled appointments.
4.5 Centralized Appointment Lists and Synchronization
A master Appointments list provides a consolidated view of bookings from Louisville and Evansville.
Custom-field changes are synchronized across the relevant location-specific and central lists, helping maintain consistent appointment information for teams working across departments.
4.6 Automated Appointment Reminders
RingCentral is integrated to send SMS reminders for upcoming appointments.
Image: Ring Central SMS reminder workflow screenshot.
Automated reminders help patients prepare for scheduled visits and reduce the amount of manual communication required from administrative staff.
4.7 Past Appointment Cleanup
Appointments whose dates have passed are automatically removed from the relevant active lists.
This keeps the operational workspace focused on upcoming appointments and outstanding tasks rather than outdated records.
5. Workflow
This workflow connects scheduling, information management, communication, and appointment status updates within the ClickUp operations workspace.
Image: The broader Louisville and Evansville recheck workflow screenshot.
6. Tools and Integrations
| Tool | Purpose |
|---|
| ClickUp | Central appointment lists, tasks, custom fields, and workflow automation |
| Calendly | Appointment booking and cancellation events |
| Jotform | Patient forms and medical information collection |
| Gmail | Laboratory communications and attachments |
| RingCentral | Automated SMS appointment reminders |
| Slack | Supporting team communication and coordination |
7. Outcomes and Business Value
Improved Operational Efficiency
Appointment creation, cancellation handling, record synchronization, and past-appointment cleanup reduce repetitive administrative work.
Better Information Organization
Centralized appointment lists connect scheduling records with relevant patient information and laboratory communications, making information easier for staff to find.
More Consistent Patient Communication
Automated reminders and form-completion notifications support more consistent communication before scheduled visits.
Improved Cross-Location Visibility
The central Appointments list provides a consolidated view of bookings across Louisville and Evansville, supporting teams that need visibility across both facilities.
More Maintainable Operations
Custom fields, dedicated lists, and defined automation rules provide a structured foundation that can be refined as operational requirements change.
8. Technical Highlights
- Event-driven automation: Appointment creation and cancellation events initiate the relevant workflows.
- Structured task management: ClickUp lists, tags, and custom fields organize appointments by location and type.
- Cross-list synchronization: Relevant field updates are reflected across centralized and location-specific lists.
- Integrated communications: Calendly, Jotform, Gmail, and RingCentral support scheduling, information collection, laboratory communications, and reminders.
- Automated record maintenance: Past appointments are removed from active lists to keep the workspace current.
9. Future Improvements
Potential next steps include refining automation rules based on staff feedback, expanding reporting on appointment statuses and follow-up completion, and reviewing notification workflows to ensure they continue to meet the needs of both locations.
10. Conclusion
The ClickUp implementation brings key operational processes for Veterinary Specialist Partners into a more connected system. By integrating appointment scheduling, patient forms, laboratory communications, SMS reminders, cancellations, and centralized tracking, the solution reduces repetitive administrative work and helps teams maintain more consistent records across Louisville and Evansville.
The result is a structured operations workspace designed to support appointment coordination, information accessibility, and ongoing workflow improvement.
Page · Plain text
PeakNIL Athlete Content Automation
Two n8n workflows that find athlete news, draft the post, and publish it to Instagram once a person approves.
Section: n8n Automations
Project Overview
PeakNIL connects college athletes with brands for Name, Image, and Likeness (NIL) opportunities. To attract brand partnerships and maintain a consistent social media presence, the team needs a steady stream of posts highlighting athlete achievements across 28 sports.
This project uses two connected n8n workflows to automate the process. The first monitors athlete news, evaluates stories, drafts captions, and sends content for review. The second detects the manager’s email response, generates a branded graphic, and publishes the post to Instagram after approval.
Human approval remains part of the publishing process, helping ensure that the final content aligns with PeakNIL’s brand and content standards.
Technology stack: n8n, Claude, Google Sheets, Gmail, Placid, Instagram.
The Business Problem: Scaling Athlete Coverage
PeakNIL manages hundreds of athletes across 28 sports. Finding relevant stories and turning them into social media content requires ongoing research, writing, image selection, graphic design, and publishing.
The main challenges include:
- Time-consuming research: Staff must regularly check news about a large athlete roster.
- Manual content production: Captions, headlines, photos, and branded graphics require several separate steps.
- Inconsistent coverage: Manual processes make it difficult to maintain a regular posting schedule across all athletes.
- Incomplete athlete records: Missing information can make it harder to identify and track athletes.
- Brand safety: Posts must focus on positive, relevant achievements and avoid injuries, losses, and controversies.
- Publishing control: Content must be reviewed and approved before it appears on Instagram.
The objective was to reduce repetitive work while improving consistency and retaining human control over publication.
The Solution
Two connected automations handle the work, and a person approves the result.
Workflow 1: Athlete Monitor (finds and drafts)
- Runs every weekday and picks athletes from the roster sheet. It skips anyone with missing data or scanned in the last 3 days.
- Searches for recent news (last 3 days) from trusted sports sources.
- Claude decides whether the story is worth posting, assigns a content category, and writes the caption and a short headline.
- Finds a clean photo of the athlete and emails the draft to the content manager for review.
Image: Workflow 1, Athlete Monitor: a schedule trigger reads the roster from Google Sheets, searches for news, has Claude draft the post, and emails it to the content manager through Gmail.
Workflow 2: Reply Detection (approves and publishes)
- The manager replies to the email with an image number or “approve”.
- The workflow reads the reply, builds a branded graphic with the chosen photo and headline, and sends it back for a final check.
- Once approved, it publishes the post to Instagram and updates the tracking sheet.
Image: Workflow 2, Reply Detection: a Gmail trigger reads the manager’s reply, then one branch builds the graphic with Placid and another publishes to Instagram after approval
How the System Works
Step 1: Read the Athlete Roster
The Athlete Monitor workflow retrieves athlete records from Google Sheets and checks whether each record contains the information needed for monitoring.
Athletes with incomplete data or who were scanned within the previous three days are skipped.
Step 2: Discover Recent News
For eligible athletes, the workflow searches trusted sports sources for relevant news published within the last three days.
This creates a pool of recent stories that can be evaluated for potential social media content.
Step 3: Evaluate and Draft Content
Claude evaluates each story for suitability, assigns a content category, and generates a short headline and caption.
The content must follow PeakNIL’s positive, brand-safe approach, avoiding injuries, losses, and controversies.
Step 4: Send the Draft for Review
The workflow finds a suitable athlete photo and sends the proposed content to the content manager by email.
The manager can review the story and select an image or provide an approval response.
Step 5: Generate the Branded Graphic
The Reply Detection workflow reads the manager’s response and uses Placid to create a branded graphic from the selected photo and headline.
The graphic is sent back for a final check before publishing proceeds.
Step 6: Publish and Update Tracking
After approval, the workflow publishes the post to Instagram and updates the athlete content tracking sheet in Google Sheets.
This closes the loop between discovery, content creation, review, and publication.
05. Workflow Architecture
Workflow 1: Athlete Monitor
Weekday schedule → Google Sheets athlete roster → Eligibility checks → Recent news search → Claude story evaluation and caption writing → Athlete photo selection → Gmail review email
Workflow 2: Reply Detection
The first workflow prepares content for review. The second uses the manager’s response to continue the process and publish only after approval.
Content Rules and Human Approval
The automation is designed to maintain a positive and brand-safe social media presence.
Story Selection
Claude evaluates whether a news story is worth posting and assigns it a content category before generating the draft.
Brand Safety
The content rules exclude stories focused on injuries, losses, or controversies. This helps keep the proposed content aligned with the project's positive athlete-celebration approach.
Human Review
The content manager receives the draft by email and provides a response. The workflow then generates the branded graphic and sends it for a final check.
Publishing remains approval-gated: the workflow is designed to publish to Instagram only after the required human approval.
07. Integrations and Their Roles
| Integration | Responsibility |
|---|
| n8n | Orchestrates both workflows and connects the services. |
| Google Sheets | Stores the athlete roster and tracks content activity. |
| Claude | Evaluates news stories and drafts headlines and captions. |
| Gmail | Delivers draft emails and detects manager responses. |
| Placid | Generates branded social media graphics. |
| Instagram | Receives approved social media posts. |
Each service has a defined role, allowing the workflow to move content between research, writing, review, design, and publishing.
08. Results and Business Value
The project is designed to reduce the manual effort required to create athlete-focused social media content while improving consistency across the roster.
Delivered Capabilities
- Automated weekday monitoring of athlete records.
- Recent-news discovery using a three-day lookback.
- AI-assisted story evaluation, categorization, and caption writing.
- Photo selection and email-based content review.
- Automated branded graphic generation.
- Reply-driven approval processing.
- Instagram publishing after approval.
- Google Sheets tracking updates.
- Checks for incomplete athlete records and recently scanned athletes.
Expected Business Value
- Less manual time spent researching athletes and drafting posts.
- More consistent coverage across sports and athletes.
- Faster preparation of social media content.
- A repeatable review and publishing process.
- Better visibility into athlete records that need attention.
The project description does not provide measured time savings, publishing volume, engagement improvements, or brand-partnership conversion figures. These should be added after reviewing actual workflow and Instagram performance data.
Key Takeaways
- Separate discovery from publishing: The two-workflow design keeps research and drafting distinct from approval and publication.
- Use AI to reduce repetitive work: Claude handles story evaluation, categorization, headlines, and captions.
- Keep people in control: Human review remains part of the publishing process.
- Standardize visual content: Placid generates branded graphics from the selected photo and headline.
- Maintain centralized tracking: Google Sheets supports athlete records and content tracking.
- Improve coverage consistency: Automated monitoring provides a repeatable process for discovering stories across a large roster.
Future Development
- Measure time spent per post before and after automation.
- Track the number of stories discovered, drafts reviewed, and posts published.
- Measure engagement by sport, athlete, and content category.
- Add monitoring for failed news searches, missing photos, and incomplete athlete records.
- Evaluate the quality of AI story selection and caption drafts through reviewer feedback.
- Add reporting on publishing frequency and approval turnaround time.
Final Outcome
PeakNIL Athlete Content Automation connects athlete news discovery, AI-assisted drafting, email-based review, branded graphic creation, and Instagram publishing in two n8n workflows.
The system is designed to help PeakNIL maintain a consistent flow of athlete-focused content while reducing repetitive production work. By keeping human approval in the publishing process, it balances automation with editorial oversight and brand safety.
Page · Plain text
WidowWise Platform Automation, Data Integrity & Dashboard Modernization
Repairing and expanding a connected learning platform with automated enrollment synchronization, accurate reporting, and certificate delivery.
Section: Make Automations
1. Overview
Wings for Widows is a Minnesota-based nonprofit that provides free one-to-one financial coaching to widows through a network of approximately 150–170 volunteer CFP advisors. Its digital learning operations run through two distinct programs: WidowWise University (WWU), which provides free and scholarship-funded courses, and Advising Through Widowhood (ATW), a separate paid financial advisor certificate program.
The platform uses Teachable for course delivery, Airtable for operational data and dashboards, Make.com for email and certificate workflows, and Mailchimp for student and advisor communications.
The engagement focused on reverse-engineering and repairing an existing automation system, resolving recurring data and dashboard problems, improving enrollment synchronization, and expanding reporting and certificate automation.
Client: Wings for Widows Platform: WidowWise / WidowWise University Additional Program: Advising Through Widowhood (ATW) Industry: Nonprofit · Financial Education · Professional Training
2. The Problem
The existing system had recurring synchronization and reporting problems that affected enrollment records, dashboard accuracy, and student completion workflows.
The main challenges included:
- Inaccurate dashboards: Engagement status fields were sometimes blank, causing totals and charts to show incorrect figures.
- Duplicate enrollment records: The original synchronization logic could overwrite previous enrollment history when a student enrolled in the same course more than once.
- Unreliable data synchronization: Teachable enrollment data was not consistently matched to the correct Airtable records.
- Manual certificate issuance: Completed students required a manual certificate process, creating delays and additional administrative work.
- Data quality issues: Duplicate registrations, unmatched enrollment records, and incorrectly classified records affected reporting accuracy.
- Automation ownership risk: The primary Teachable API secret belonged to the previous developer, creating a dependency for maintaining the synchronization system.
3. How It Works
The solution connects the learning platform, operational database, automation workflows, and communication system.
Step 1 — Teachable to Airtable Synchronization
Teachable provides the course, student, enrollment, completion, and transaction information used by the operational system.
Airtable serves as the central data layer, containing 20 tables covering people, enrollments, completions, products, lessons, modules, transactions, prices, coupons, graduates, and automation errors.
Scheduled JavaScript automations synchronize Teachable information into Airtable.
Step 2 — Enrollment Matching and Data Integrity
The original enrollment-matching logic used a combination of course and user identifiers. This could cause a new enrollment cycle to overwrite an earlier record.
The matching logic was rebuilt around each enrollment's actual Person and Product relationships.
- Existing records for the same person and course are identified.
- The record with the highest completion percentage is treated as the current enrollment cycle.
- A new record is created only when progress has moved backwards, indicating a genuine restart.
- Historical enrollment information is preserved instead of being overwritten by a duplicate synchronization event.
Additional JavaScript and Airtable field-formatting issues were identified during testing and corrected before production.
Screenshot to add: Teachable enrollment records alongside their corresponding Airtable enrollment records. Highlight the Person and Product relationships and the corrected matching logic.
Step 3 — Engagement Status and Dashboard Accuracy
Dashboard totals were not reconciling because some incoming Teachable records had blank Engagement Status fields.
The synchronization process was updated so Engagement Status is automatically derived from Percent Complete on every sync run.
- Existing records with blank statuses were backfilled using actual completion data.
- The recurring synchronization logic was corrected so new records receive the appropriate status automatically.
- A separate In Progress metric was fixed after identifying an incorrect filter and inconsistent Percent Complete data.
This removed the need for repeated manual corrections to dashboard records.
Screenshot to add: Airtable dashboard showing Total, Completed, In Progress, and Not Started, alongside the Engagement Status and Percent Complete fields.
Step 4 — Graduation and Certificate Automation
A certificate automation pipeline was built around the student's completion status.
When Engagement Status changes to Completed:
- A sequential Certificate ID is generated.
- Certificate and mailing details are sent to C&M Printing.
- Chris receives the CFP continuing-education filing information.
- The process is gated to prevent certificates from being issued when registration data is incomplete or mismatched.
The workflow also addressed real completion-record issues, including students stuck at 99% and certificate records requiring manual intervention.
Screenshot to add: Make.com certificate automation scenario, the generated Certificate ID in Airtable, and an example of the certificate notification workflow.
Step 5 — Dashboard Expansion
Several dashboards were built or improved to provide more reliable operational reporting.
- ATW Enrollments: Corrected metric-card calculations so dashboard figures reconcile.
- All Courses (Select to Filter): Created a unified dashboard with a live course-selection dropdown.
- ATW Progression (Pace & Stuck Points): Rebuilt based on detailed client feedback, including a clearer advisor grid, normalized completion percentages, and enrollment information.
- Percent Complete (Normalized): Added a safety-net formula to protect against incorrectly scaled Teachable values.
Screenshot to add: The ATW Enrollments dashboard, All Courses dashboard with its course selector, and ATW Progression dashboard.
Step 6 — Automation Ownership and Reliability
The Teachable API credential previously belonged to the original developer, creating an operational dependency.
A new independently owned API secret was created, and the synchronization automation was repointed to use it.
This restored the client's control over the integration and reduced dependency on the previous developer.
Screenshot to add: Teachable API integration configuration and the relevant Make.com or Airtable automation scenario. Do not expose API keys or credentials.
4. The Result
The engagement transformed a recurring maintenance problem into a more reliable learning and reporting system.
Enrollment synchronization was rebuilt around actual student and course relationships, preserving enrollment history and reducing the risk of duplicate records. Dashboard calculations were corrected, and Engagement Status is now automatically derived from completion data during synchronization.
Certificate issuance was automated through sequential Certificate IDs, print-partner notifications, and completion checks. Additional dashboards improved visibility into course enrollment, advisor progression, and student completion.
The platform's API ownership was also transferred away from the previous developer, giving the client independent control over the integration.
5. Results & Metrics
The source documents specific implementation outcomes rather than a complete before-and-after performance study.
| Area | Documented outcome |
|---|
| Airtable operational database | 20 tables |
| Enrollment synchronization | Rebuilt around Person and Product relationships |
| Engagement Status | Automatically derived on every sync |
| Dashboard accuracy | Metric-card calculations corrected |
| Certificate workflow | Sequential Certificate ID and automated notifications |
| Dashboard expansion | ATW Enrollments, All Courses, and ATW Progression |
| API ownership | New independently owned Teachable API secret |
6. Tech Stack
- Teachable: Learning management system hosting courses and enrollment information.
- Airtable: Central operational database, enrollment records, completion tracking, and dashboards.
- Airtable Automations: JavaScript-based scheduled synchronization and data processing.
- Make.com: Outbound email automation and graduation/certificate workflows.
- Mailchimp: Student and advisor communications, including welcome, reminder, continuation, completion, and access-related emails.
7. Where This Pattern Applies
- Nonprofit Organizations: Manage scholarship programs, participant records, course completion, and automated communications.
- Educational Institutions: Synchronize student enrollments, academic progress, certificates, and reporting dashboards.
- Professional Certification Providers: Automate eligibility checks, completion tracking, certificate generation, and continuing-education records.
- Online Learning Platforms: Maintain accurate student histories across repeat enrollments, course restarts, and completion cycles.
- Coaching Organizations: Track client and advisor progress, program participation, and follow-up workflows.
- Training and Development Teams: Combine learning platforms with operational databases to monitor employee training and certification.
This pattern is useful for organizations that rely on multiple connected platforms to manage people, enrollments, learning progress, and communications. By improving synchronization, data integrity, and workflow automation, they can build a more dependable operational system around their existing tools.
Page · Plain text
From Manual Calendar Checking to Automatic Tutor Matching
Finding the right tutor for a family used to mean checking the tutor sheet and then each tutor's calendar, one by one. Now a staff member posts the request in Slack, and a ranked list of tutors who are really free arrives in the same thread within minutes.
Section: n8n Automations
From Manual Calendar Checking to Automatic Tutor Matching
- Browser automation
- n8n automations
- AI agents
Works with: n8n, Slack, Skyvern, Google Sheets, TutorBird, Claude
Before A tutor sheet and 56 separate calendars to check for every request
Now One ranked report in Slack, in about 2 to 4 minutes
Project overview
A tutoring company places children with tutors. For every family request, one question matters most: which tutors are free at the times this family needs, and right for this child?
Answering it means combining two sources: a tutor sheet (who is available now, where they work, which grades, what experience, how many students) and a separate calendar in TutorBird for each of 56 tutors.
Growlyze built a Slack bot that does this check. A staff member posts the request in a fixed numbered format. The bot shortlists the right tutors from the sheet, has a browser automation read their live TutorBird calendars, matches their free time to the family’s windows and session length, and replies in the same thread with a ranked report.
The bot also handles the family’s time zone, applies the company’s rule for how many sessions a week a tutor must cover, and says why a tutor is only a partial match.
Key results at a glance
| Metric | Before | After |
|---|
| Time to a match report | 6–8 minutes | 2–4 minutes |
| Calendars read per request | All 56 tutors | Only the shortlisted tutors (24 in the first live test) |
| Tutor information | A sheet plus 56 separate calendars | One ranked report in Slack |
| Name matching | Two name formats: “First Last” in the sheet, “Last, First” in TutorBird | All 34 tutors marked available matched to their TutorBird names |
| Temporary page errors | Re-run by hand | Retried automatically, up to 3 attempts |
Report times come from measured live runs (2:00 and 3:54). The calendar figure comes from the first live test, a remote request with 24 shortlisted tutors. No other numbers are claimed.
01. The business challenge
When a family asks for a tutor, speed and accuracy both matter. A family left waiting, or promised a time that can’t be kept, can lose trust quickly. Matching a request to the right tutor involves several connected problems.
1.1 Every request has many conditions
A match has to fit the child’s grade, any experience the family needs (such as ADHD or autism), a city or online, the session length (for example 45 or 60 minutes), how many sessions a week, and the family’s free windows in their own time zone. All of these have to be true at once.
1.2 The answers live in two places
The tutor sheet says who is available now, where they work, which grades they teach, what experience they have and how many students they already have. Their actual free time sits in a separate TutorBird calendar for each of 56 tutors, which has to be opened through the website.
Image: The TutorBird calendar, where each tutor’s lessons and free time live. Student and tutor names are blurred.
1.3 Time zones and names don’t line up
Families write their free times in their own zone (ET, MT, PT and others), while TutorBird shows times in Eastern. The sheet writes names as “First Last”, while TutorBird writes “Last, First”, and some names have a middle name or a two-word surname.
1.4 Free time isn’t always usable time
A tutor can be free for 30 minutes inside a family’s window when the session needs 45 or 60. A request for two sessions a week also needs two separate days, not one long gap.
1.5 A wrong match is costly
If a tutor looks free and isn’t, the family is promised a time that can’t be kept. A child waits longer for help, and the team has to start the search again.
02. The solution: a Slack tutor-matching bot
Growlyze built the bot around the company’s own tutor sheet, TutorBird calendars and Slack channel. It replaces none of them. It connects them, so one Slack message sets the whole check in motion.
2.1 A request in Slack
A staff member posts the request as eight numbered lines: student, remote or address, backup option, session length, how often, the family’s free times, grade, and any experience needed. The bot adds a “working on it” reaction and checks every line; if one is missing, it replies in the thread and says which. AI turns the days named in the request, even a range like Monday to Friday, into real dates for the upcoming Sunday-to-Saturday week.
Image: An example request posted in Slack. The sender, student name and address are blurred.
2.2 A shortlist from the tutor sheet
The bot reads the tutor sheet and keeps tutors who are marked available now, work in the right city or remote, and teach the child’s grade. AI then checks which of them have the experience the family asked for, matching on meaning (“Autism” and “Autism Spectrum Disorder” count as the same condition) and requiring every condition named. For in-person requests, the bot also works out how far each tutor is from the family.
2.3 A live calendar read with Skyvern
The bot sends the dates and the shortlisted tutors, written the way TutorBird writes names, to Skyvern. Skyvern logs into TutorBird, selects those tutors and reads each tutor’s free times for the requested days from that tutor’s own calendar column. The workflow checks every 30 seconds until the read is done, and if TutorBird has a temporary page problem it retries up to two more times.
2.4 Matching free time to the family
AI turns the family’s free-text availability into clear day and time windows, including “either day” options. The bot matches sheet names to TutorBird names, converts times from TutorBird’s Eastern time into the family’s time zone, and keeps only the free time that fits a window and is long enough for the session length.
2.5 A ranked report in the same thread
The bot then checks how many sessions a week each tutor can cover. Tutors who cover every requested session are full matches; those who cover fewer are partial matches, with the reason and any too-short slots listed; the rest are named as having no availability. The top pick is chosen from the full matches (closest for in-person requests, then fewest students), and remote backups are added when too few in-person tutors fit. The report is posted as a reply to the original message, with a check-mark reaction.
Image: An example report. Student and tutor names, and the logo, are blurred.
2.6 Clear failure messages
If a step fails, the bot replies in the thread with “Match failed for this request” and the reason, and marks the message with an X. Temporary calendar errors are retried first, so the team only sees an error when every attempt has failed.
03. End-to-end workflow
The whole process runs as one n8n workflow, started by the Slack message.
Image: The n8n workflow, from the Slack message to the posted report.
- Request posted in Slack
- Dates and fields read from the request
- Shortlist built from the tutor sheet
- Calendars read by Skyvern, with automatic retry
- Free time matched to the family’s windows and session length
- Weekly frequency checked and tutors sorted
- Top pick chosen
- Report posted in the same thread
There is one path from the Slack message to the posted report, and any failure is reported back to the same thread.
04. What makes this solution different?
Built around the company’s own rules
The bot uses the company’s grade bands, experience matching and student counts. When a family accepts “1x or 2x a week”, a full match must cover the higher number, so tutors who can only do one session show as partial.
Reads only the tutors who could match
The sheet filters run first, and only the shortlisted tutors’ calendars are read. In the first live test that was 24 tutors instead of all 56.
AI where judgment is needed, fixed rules where precision is needed
AI reads the family’s free-text availability and matches experience and names. Time-zone conversion, overlap, session-length checks and sorting follow fixed rules.
Partial matches explain themselves
Every partial match says why it falls short (for example, one session of two) and lists any slots that were too short for the session.
Each tutor is read from their own column
Skyvern takes each tutor’s availability from that tutor’s own calendar column, and the read is set up to check that the number of tutors matches the number of columns.
Temporary errors fix themselves
If TutorBird has a temporary page problem, the bot retries up to two more times before showing an error.
05. Business impact
Match reports in 2–4 minutes
Measured live runs finished in 2:00 and 3:54. Before tuning, matches had slowed to 6–8 minutes; removing an unused calendar-read step and checking for results every 30 seconds instead of every 2 minutes brought them back down.
Fewer calendars to read
Only the shortlisted tutors’ calendars are read. In the first live test, that was 24 tutors instead of all 56.
Less manual re-running
Temporary TutorBird page errors used to mean re-running the request by hand. The bot now retries up to two more times on its own. This has been tested with simulated failures, and the first live retries are still to be observed.
Clearer shortlists
Each report names the full matches, the partial matches with the reason, and the tutors with no availability, so the team can see why someone was or wasn’t suggested.
Accuracy checked by hand
In two test requests, all 21 and all 24 tutors in the reports were checked against the raw calendar data and the tutor sheet, and every time range and experience label matched. All 34 tutors marked available in the sheet matched their TutorBird names.
06. Technology stack
| Technology | Role in the solution |
|---|
| n8n | Workflow automation: runs every step, from request to report |
| Slack | Where requests are posted and where the report is replied |
| Skyvern | Browser automation: logs into TutorBird and reads the tutors’ free times |
| TutorBird | The calendar system the team already uses |
| Google Sheets | The tutor roster: availability, location, grades, experience, student count |
| Claude (Anthropic) | AI for dates, free-text availability, experience matching, name matching and ZIP estimates |
| Zippopotam.us | Turns ZIP codes into locations for distance checks |
The technologies support the bot’s main functions: request intake, shortlisting, calendar reading, matching and reporting. The team keeps working in Slack, TutorBird and their own tutor sheet.
07. Future enhancements
The following items were identified as future improvements rather than completed capabilities.
Warn when a tutor can’t be found in TutorBird
Today a tutor the calendar reader can’t find shows up as having no availability. The report should say “not found” instead.
Refresh and retry inside the calendar reader
Retrying inside the Skyvern run itself would let a temporary page error recover in seconds, instead of starting the whole read again.
An error message for every failed step
Some steps, such as the AI steps, don’t report a failure to Slack. Adding that would make sure no request is ever left without a reply.
08. Where this pattern applies
This isn’t really about tutoring.
Worked example: a home care agency. A family asks for a caregiver who speaks Spanish, lives nearby, and is free Tuesday and Thursday afternoons. The sheet shortlists caregivers who are active, certified and in the right area. A browser bot reads only those caregivers’ schedules in the scheduling system, keeps the ones free at the family’s times, and posts a ranked list in Slack.
Where else it fits:
- Salons and spas: stylist to appointment
- Field service: technician to job
- Clinics: provider to patient visit
- Fitness and coaching: trainer to member
- Language services: interpreter to event
- Legal and accounting: advisor to client intake
The shape: a request comes in, a sheet shortlists who qualifies, a browser bot reads the live calendars, and a ranked answer lands where the team already works.
What changes from case to case: the filters in the sheet, the calendar system being read, and the rules for what counts as a match.
Conclusion
Matching a family to a tutor depends on a tutor sheet and 56 separate TutorBird calendars, each with its own times, time zones and name formats.
Growlyze connected them with a Slack bot that shortlists tutors from the sheet, reads the shortlisted tutors’ live calendars, converts times to the family’s zone, and replies with a ranked report that explains every partial match.
Measured reports arrive in 2–4 minutes, and temporary calendar errors are retried automatically. The team keeps using Slack, TutorBird and their own tutor sheet.
Page · Plain text
Automatic Cleanup of Scheduled Posts When a Card Is Unapproved
An n8n workflow that checks every 15 minutes for cards that are no longer approved and removes their still-scheduled posts from Metricool, without touching anything already published or about to go out.
Section: n8n Automations
Project Overview
This project automates the cleanup of scheduled social media posts using n8n, Airtable, and Metricool. When a content card is denied, returned to review, or has a scheduling failure, its previously scheduled posts may still be waiting to publish.
The workflow checks Airtable every 15 minutes for cards with statuses such as Pending Review, Denied, Schedule Failed, or a blank status. It retrieves the associated Metricool post IDs, checks each post's current state, and applies safety rules to determine whether it should be deleted, retained, cleared from the card, or checked again later.
The workflow also updates Airtable with the results, clears obsolete post IDs, records timestamped audit entries, and removes the scheduled time when a post is deleted so the content can be scheduled again after approval.
Technology stack: n8n, Airtable, Metricool, X, Facebook, LinkedIn, Threads.
01. The Business Problem: Unapproved Content Can Still Be Published
A content team manages social media scheduling through Airtable cards and Metricool. Each card stores the Metricool post IDs for its scheduled posts across supported social platforms.
If a card's approval status changes after scheduling, the posts already queued in Metricool may still be published. Without an automated cleanup process, the team must manually locate and unschedule each post.
The main challenges include:
- Approval changes after scheduling: Posts can remain queued even after a card is denied or returned for review.
- Multiple social platforms: A single card can contain separate Metricool post IDs for X, Facebook, LinkedIn, and Threads.
- Publishing safety: Deleting a post that is already published or about to go live can create unnecessary disruption.
- Repeated processing: Previously handled post IDs should not be checked repeatedly on every scheduled run.
- Auditability: The team needs a record of which posts were deleted, retained, or cleared, and when.
- Temporary API failures: A failed lookup or deletion should not prevent the workflow from processing other posts.
The goal was to make scheduled-post cleanup automatic while maintaining strict safeguards around publishing status and timing.
02. The Solution: Automated Unscheduling with Safety Checks
A single n8n workflow runs every 15 minutes and searches Airtable for cards that may require cleanup.
The workflow separates each eligible card into individual Metricool post IDs and checks each post sequentially, with a short pause between API calls. A decision step determines whether each post should be deleted, kept, cleared, or retried during a later run.
Only future, unpublished posts that meet the deletion criteria are sent to Metricool's delete endpoint. Published posts and posts due within the next five minutes are protected. Posts that are already overdue but are not marked as published are also left untouched for manual checking.
After processing, n8n updates the corresponding Airtable card, clears IDs for deleted or already-missing posts, records timestamped decisions in the Unschedule Log, and clears the Scheduled Time when a post is deleted.
If a lookup or deletion fails, the workflow leaves the relevant record untouched so that a later run can retry it.
03. Project Snapshot
| Item | Detail |
|---|
| Platform | n8n |
| Schedule | Every 15 minutes |
| Source of approval status | Airtable |
| Social scheduling platform | Metricool |
| Supported networks | X, Facebook, LinkedIn, Threads |
| Input | Airtable cards and Metricool post IDs |
| Decision logic | Status, publishing state, and scheduled time |
| Processing method | One post ID at a time |
| Audit trail | Timestamped Unschedule Log in Airtable |
| Error handling | Failed lookups and deletions remain available for retry |
| Status | Live and running on an automatic schedule |
04. How the System Works
Step 1: Find Cards Requiring Cleanup
Every 15 minutes, the workflow searches Airtable for cards with a status of Pending Review, Denied, Schedule Failed, or blank, provided they still contain a Metricool post ID.
This identifies content that may no longer be eligible for publication but still has scheduled posts associated with it.
Step 2: Split Cards into Individual Posts
A code node converts each eligible card into one item per Metricool post ID.
The workflow checks its processing log and skips IDs that have already been handled and recorded. This reduces unnecessary repeated processing of settled posts.
Step 3: Retrieve Each Post from Metricool
The workflow requests the current details of each post from Metricool, processing one post at a time with a short pause between requests.
If an API lookup fails, the error does not stop the entire workflow. The affected post is left untouched so the workflow can try again during a subsequent run.
Step 4: Apply the Safety Rules
A decision step evaluates the retrieved post information and assigns an action:
- Delete: The post is unpublished and scheduled sufficiently far in the future.
- Keep: The post is already published or is due within the next five minutes.
- Clear: Metricool no longer has the post, so the stale ID can be removed from Airtable.
- Retry later: A lookup or deletion fails, leaving the relevant record unchanged for another attempt.
An overdue post that is not marked as published is not automatically deleted. Instead, the workflow records that someone should check its status in Metricool.
Step 5: Delete Eligible Posts
The Delete? branch sends a deletion request to Metricool only for posts marked for deletion.
Posts assigned any other action bypass the deletion request and continue through the merge step. This keeps the delete operation separate from the logic that decides whether deletion is safe.
Step 6: Update Airtable and Record the Outcome
After the deletion and non-deletion branches merge, a code node prepares one update per Airtable card.
The workflow:
- Clears IDs for posts that were deleted or were already missing from Metricool.
- Adds a timestamped entry to the card's Unschedule Log for each handled post.
- Clears the Scheduled Time when a post is deleted, allowing the content to be scheduled afresh after approval.
- Leaves failed lookup or deletion records unchanged so they can be retried.
Airtable stores the resulting updates, giving the team a record of the cleanup decisions.
05. Workflow Architecture
The workflow has four main functional layers:
- Discovery: Finds Airtable cards that may have obsolete scheduled posts.
- Post-level processing: Handles each Metricool post ID separately.
- Safety and action routing: Determines whether a post should be deleted, kept, cleared, or retried.
- Record synchronization: Updates Airtable IDs, scheduled times, and the audit log.
This separation helps ensure that a post is not deleted simply because its Airtable card has an unsuitable status. Its individual publishing state and scheduled time must also satisfy the safety rules.
n8n Workflow
Image: The workflow is live and includes protections for published content, posts about to go out, and operations that fail. Its next improvement opportunity is to measure cleanup performance and monitor unresolved cases over time.
06. Safety Rules and Deletion Logic
The workflow applies the following rules before deleting a scheduled post.
| Post condition | Action | Reason |
|---|
| Future post, not published, and more than five minutes from its scheduled time | Delete | Eligible for automatic cleanup. |
| Already published | Keep | Published content must not be deleted by this workflow. |
| Scheduled within the next five minutes | Keep | Avoid interfering with content about to go live. |
| Past its scheduled time but not marked as published | Keep and flag for manual checking | Avoid making an unsafe assumption about its status. |
| Metricool no longer has the post | Clear the stale post ID | The post is already gone, so the ID no longer needs to remain on the card. |
| Lookup or deletion request fails | Leave unchanged and retry later | Preserve the record for a subsequent attempt. |
The same safety rules apply across all supported networks, including X.
07. Airtable Synchronization and Audit Logging
Airtable remains the central record of approval status and scheduled-post identifiers.
After processing, the workflow synchronizes the card with the actual cleanup outcome.
| Airtable field or record | Purpose |
|---|
| Card status | Identifies content that may require unscheduling. |
| Metricool post IDs | Tracks the scheduled posts associated with the card. |
| Unschedule Log | Records timestamped actions and decisions. |
| Scheduled Time | Cleared when a post is deleted so it can be scheduled afresh. |
The log provides visibility into what was deleted, retained, or cleared, along with the time of the action. Failed operations remain available for retry rather than being treated as successful cleanup.
08. Reliability and Error Handling
The workflow is designed to continue processing other posts when an individual operation encounters an error.
Sequential API Requests
Metricool is called one post at a time, with a short pause between requests. This reduces the risk of overwhelming the service when many cards require cleanup.
Failure Isolation
A failed lookup or deletion does not stop the entire workflow. The affected post is left untouched, allowing a later run to retry it.
Previously Handled IDs
IDs that have already been handled and logged are skipped, reducing repeated checks of settled posts.
Separate Decision and Deletion Paths
The workflow sends only posts explicitly marked for deletion to Metricool's delete operation. All other decisions bypass the delete request and continue through the merge path.
These controls reduce unnecessary API calls and help protect posts that should remain scheduled. They do not imply that API failures or every possible scheduling edge case are eliminated.
09. Results and Operational Capabilities
The project description confirms that the workflow is live and runs automatically. It does not provide measured figures for the number of posts cleaned up, API success rate, time saved, or prevented accidental publications.
Implemented Capabilities
- Automatic checks every 15 minutes.
- Identification of Airtable cards requiring scheduling cleanup.
- Individual processing of Metricool post IDs.
- Skipping of previously handled and logged IDs.
- Protection for published posts and posts due within five minutes.
- Manual-review handling for overdue posts not marked as published.
- Removal of eligible future, unpublished posts.
- Cleanup of stale post IDs when posts are already missing.
- Timestamped Unschedule Log entries.
- Scheduled Time clearing after deletion.
- Retry behavior for failed lookups and deletion requests.
Metrics to Measure Next
A measured production review could track:
- Number of cards and posts evaluated per run.
- Number of posts deleted, retained, cleared, and retried.
- Average time between an approval-status change and cleanup.
- Number of failed Metricool requests.
- Number of posts that require manual status checks.
- Number of duplicate or unnecessary cleanup attempts.
- Any cases where an unapproved post remained scheduled or a valid post was incorrectly targeted.
These figures would help quantify the operational value and verify the effectiveness of the safety rules.
10. Key Takeaways
- Approval status must remain synchronized with scheduling: Changing an Airtable card does not automatically remove a post already queued in Metricool.
- Evaluate individual posts before deletion: A card's status alone is not enough to determine whether every associated post can safely be removed.
- Protect publishing boundaries: Published posts, posts due within five minutes, and ambiguous overdue posts receive special handling.
- Keep an audit trail: Timestamped Unschedule Log entries make cleanup decisions visible to the team.
- Handle failures without losing state: Failed operations remain available for a later retry.
- Use sequential API calls: Processing posts one at a time helps control the request rate.
11. Future Development
The next stage should focus on measuring reliability and improving operational visibility.
- Add a periodic summary of deleted, retained, cleared, and retried posts.
- Track repeated failures and alert the team when a post remains unresolved across multiple runs.
- Measure the time between card-status changes and successful cleanup.
- Review manual-check cases to determine whether additional Metricool status signals could safely resolve them.
- Test the workflow against edge cases involving multiple networks, missing post IDs, schedule changes, and posts close to their publication time.
- Maintain an audit of cleanup outcomes to support ongoing verification of the deletion safeguards.
12. Final Outcome
The Automatic Cleanup of Scheduled Posts workflow provides an automated safeguard between Airtable approval decisions and Metricool's publishing queue.
By checking cards every 15 minutes, evaluating each associated post, applying time- and status-based deletion rules, and recording the outcome in Airtable, it helps prevent obsolete scheduled content from being left in the publishing queue.
Page · Plain text
AI-Powered Customer Support Agent
An AI agent that reads support tickets, applies your SOPs and product manuals, and drafts accurate replies in the customer’s language.
Section: AI Agents, AI Agents for Ecommerce
AI-Powered Customer Support Agent
An AI agent that reads support tickets, applies company SOPs and product manuals, and drafts accurate responses in the customer's language.
Technologies: n8n, Zapier, PostgreSQL, Supabase, Google Sheets, OpenAI
Project Overview
Customer support teams often spend significant time reading long ticket conversations, searching through standard operating procedures (SOPs), reviewing product manuals, and preparing responses to routine customer questions.
This project introduces an AI-powered customer support agent designed to automate these repetitive tasks. It classifies incoming tickets, retrieves relevant policies and product information, applies business rules, and generates customer-ready response drafts alongside internal support notes.
The system also supports ongoing knowledge synchronization so that responses can reference current SOPs and product documentation. Complex or exceptional cases can be escalated for human review.
01. The Problem: Manual Customer Support Doesn't Scale
Before automation, support teams faced several operational challenges.
Time-consuming manual research
Agents had to read lengthy tickets and conversation threads, then switch between multiple sources to find the information needed to respond correctly.
- SOP documents and internal policy guides
- Product manuals and troubleshooting instructions
- Order details and purchase information
- Warranty, return, and refund conditions
Inconsistent decision-making
Different agents could interpret the same policy differently, particularly when handling returns, refunds, warranty claims, missing items, defective products, and payment issues.
Outdated knowledge
When product manuals or SOPs changed, agents could unknowingly rely on outdated information, increasing the risk of incorrect responses.
Operational impact
These challenges resulted in:
- High manual workload for support agents.
- Inconsistent, non-standard customer responses.
- Longer response and resolution times.
- More effort required to onboard new agents.
- Difficulty scaling support as ticket volumes increased.
Core challenge: The business already had the necessary knowledge, but needed a system to retrieve, apply, and use it consistently across support tickets.
02. The Solution: AI-Powered Customer Support Agent
The solution acts as a virtual senior support agent that combines ticket understanding, policy-based decision-making, product knowledge retrieval, and response drafting.
What the system does
- Reads incoming tickets and their conversation history.
- Understands customer intent and identifies the ticket category.
- Detects the customer's language and relevant case details.
- Retrieves applicable SOPs and product manuals.
- Applies configured business rules for returns, refunds, warranties, and other support cases.
- Drafts customer replies in a clear, friendly tone.
- Generates internal support notes explaining the relevant policy or manual and suggested next steps.
- Escalates complex or exceptional cases for human review.
- Supports synchronization of updated SOPs and product documentation.
The objective is to automate routine research and drafting while preserving human oversight where needed.
03. How the System Works: Six-Phase Workflow
Phase 1 — Ticket Intake and Understanding
The process begins when a new customer support ticket arrives.
The AI system:
- Reads the full conversation and available ticket context.
- Identifies the customer's intent and primary concern.
- Detects the language used by the customer.
- Checks whether the ticket appears valid or is potentially spam.
- Records incoming ticket information temporarily so that it can be processed without being lost.
Output: A ticket prepared for classification, with its conversation context available for subsequent processing.
Phase 2 — Smart Ticket Classification
The system identifies the type of support request and extracts relevant details.
Ticket categories include:
- Product usage and troubleshooting
- Warranty claims
- Return requests
- Refund requests
- Missing or defective items
- Order-status questions
- Payment issues
Relevant details may include:
- Order ID
- Product SKU
- Purchase date
- Ticket urgency
- Customer's specific question or reported problem
Based on the identified category and available details, the workflow determines which SOP or product manual is relevant.
Output: A categorized ticket with extracted information and a defined knowledge-retrieval path.
Phase 3 — SOP-Driven Decision-Making
The system applies the company's documented procedures and configured business rules to the ticket.
Rules may cover:
- Warranty eligibility and conditions
- Return eligibility
- Refund conditions
- Price-based thresholds
- Other configured support policies
Instead of generating decisions solely from general AI knowledge, the workflow uses the relevant company rules to guide its response.
For example, a refund-related ticket can be evaluated against the applicable refund conditions before a response draft is generated.
Output: A proposed support decision grounded in the applicable SOPs and business rules.
Phase 4 — Product Manual Intelligence (RAG)
For product-specific questions, the system retrieves relevant information from product manuals and the knowledge base using retrieval-augmented generation (RAG).
The retrieval process supports questions involving:
- Product instructions and usage
- Product specifications
- Troubleshooting steps
- Product-specific guidance
The retrieved information provides context for the AI response, helping it address the customer's actual question rather than relying only on a general model response.
The knowledge-update component is intended to keep product information and SOPs synchronized as documentation changes.
Output: Relevant product information and policy references for the response-generation stage.
Phase 5 — Response Drafting
After the ticket has been classified and the relevant policies and product information have been retrieved, the AI generates two outputs.
A. Customer reply draft
- Friendly, professional tone
- Clear explanation of the proposed answer or next steps
- Written in the customer's detected language
- Based on the applicable SOPs and retrieved product information
- Ready for support-agent review or sending according to the configured workflow
B. Internal support notes
- Explanation of the proposed response
- Relevant SOP or product manual used
- Key information considered during processing
- Suggested next steps for the support team
These two outputs serve different purposes: the customer receives a clear response, while the support team receives context to help review the proposed answer.
Phase 6 — Continuous Knowledge Updates
The system includes a knowledge-maintenance component designed to keep support information current.
The intended process includes:
- Monitoring product manuals for updates.
- Synchronizing SOP changes.
- Removing or replacing outdated information.
- Keeping the knowledge base aligned with current documentation.
This helps reduce the risk of responses relying on obsolete policies or product instructions.
Output: A knowledge base that can be maintained as product documentation and company procedures evolve.
Image: Main workflow from n8n
04. Complete System Workflow
Main ticket-processing workflow
Knowledge retrieval workflow
Exception-handling workflow
Knowledge maintenance workflow
05. Business Value
Reduced manual research
Agents spend less time searching through lengthy SOPs, manuals, and conversation histories to prepare routine responses.
Consistent policy application
Configured business rules and relevant SOPs guide responses across return, refund, warranty, and other support categories.
Faster response preparation
The system automates ticket understanding, knowledge retrieval, and initial response drafting, helping support teams prepare replies more quickly.
Multilingual support
Customer response drafts can be generated in the language detected in the incoming ticket.
Better knowledge reuse
Existing product documentation and company procedures become reusable sources of context for support requests rather than requiring agents to locate and interpret the same information repeatedly.
Improved agent confidence
Internal support notes explain the basis of a proposed response and identify the relevant policy or manual, giving agents useful context for review.
Support scalability
Automating repetitive work can help teams handle larger volumes of routine requests without increasing manual research effort at the same rate.
06. Results and Expected Impact
The original case study reports the following figures and expected benefits.
Time and effort savings
| Metric | Reported figure |
|---|
| Routine tickets handled before automation | 50–100 per day |
| Time spent reading manuals and drafting replies before automation | Approximately 2–4 hours per day |
| Human time required after automation | Approximately 10–15 minutes |
| Monthly time saved per team | Approximately 50–60 hours |
| Equivalent support capacity freed | Approximately 1–1.5 full-time support agents |
Accuracy and consistency goals
The case study describes the intended benefits as:
- Consistent application of configured SOP rules.
- More relevant answers to product-specific questions.
- Reduced human error and knowledge drift.
- Fewer manual policy lookups.
- More consistent response preparation.
Cost efficiency
The original case study estimates AI costs at approximately $30–40 per month per agent workflow. Actual costs depend on model usage, ticket volume, retrieval infrastructure, and the deployed integrations.
Important: These metrics are reported in the supplied project description and have not been independently verified. The expected benefits should not be interpreted as guaranteed outcomes for every deployment.
07. How to Replicate This System
The supplied case study describes a workflow-based implementation using an automation platform, an AI model, and a knowledge source.
Step 1 — Prepare the workflow
- Open the workflow automation platform used for the project, such as n8n or Zapier.
- Create a new workflow.
- Import the supplied
Customer support Agent.json workflow file, if available and compatible with the platform. - Review the imported nodes, connections, and configuration.
- Save the workflow with a suitable name.
Step 2 — Connect the ticket platform
Configure the relevant ticket-platform integration.
- Enable the appropriate new-ticket event or webhook.
- Configure the endpoint that forwards new ticket information to the workflow.
- Ensure the workflow receives the ticket content and any required metadata.
- Test that incoming tickets reach the correct workflow entry point.
The exact configuration depends on the ticket platform and the available API or webhook integration.
Step 3 — Configure the knowledge base
Choose the knowledge source used for SOPs, product manuals, and supporting documents.
The original case study lists:
- Google Sheets
- PostgreSQL
- Supabase
Configure the required connection and organize the relevant support documentation. If the implementation uses RAG, ensure the retrieval and indexing components are configured for the selected knowledge source.
Step 4 — Connect the AI model
Configure the OpenAI model credentials and the workflow components responsible for:
- Ticket classification
- Intent and detail extraction
- SOP-based reasoning
- Product information retrieval and response generation
- Customer reply drafting
- Internal support notes
Use clear instructions that require responses to follow the retrieved information and configured business rules.
Step 5 — Configure business rules and escalation
Define the policies that determine how common support categories should be handled.
Examples include:
- Return eligibility
- Refund conditions
- Warranty requirements
- Price-based thresholds
- Conditions requiring human review
Confirm that exceptional cases are routed appropriately rather than being treated as routine requests.
Step 6 — Test the workflow
Submit test tickets covering different scenarios.
Verify that:
- Ticket ingestion works correctly.
- Classification and detail extraction produce the expected results.
- The appropriate SOPs and product manuals are retrieved.
- Business rules are applied as configured.
- Customer reply drafts appear in the expected format and language.
- Internal support notes contain useful context.
- Ticket data and processing results are logged correctly.
- Errors, missing information, and exceptional cases are handled appropriately.
Test return, refund, warranty, product troubleshooting, and other relevant scenarios before enabling live processing.
Step 7 — Activate and monitor the workflow
Once the workflow has passed testing:
- Enable the workflow.
- Monitor its initial runs.
- Review generated drafts and escalation behavior.
- Check that knowledge updates are reflected in subsequent processing.
- Investigate failed runs and adjust the configuration as needed.
From that point, supported tickets can be processed automatically according to the configured workflow, with human review or sending behavior determined by the deployment.
08. Final Outcome
The AI-Powered Customer Support Agent brings ticket understanding, policy retrieval, business-rule evaluation, product knowledge, and response drafting into a unified workflow.
By automating routine research and preparing customer-ready drafts, the system is designed to reduce repetitive work, improve consistency, and help support teams respond more efficiently. Its knowledge-maintenance and escalation components also support ongoing documentation updates and human handling of complex cases.
The result is a more structured approach to customer support in which AI handles repetitive processing while the support team retains visibility into the policies, information, and next steps behind each proposed response.
Page · Plain text
End of part 5 of 7. Continue with part 6.