An AI assistant for a one-person engineering business
XCAN Engineering Service sells new and used HOWO, SINOTRUK, DAF, IVECO, Volvo and MAN trucks and genuine spare parts, and provides on-site diagnosis, repairs, maintenance and emergency support to more than 100 transport companies. Morphlix built a business website on Amazon Web Services (AWS) with an AI assistant for routine questions and structured capture of the requests that need the owner, so routine information is available while the owner concentrates on engineering work. Live since 24 August 2026.
- SMB
- AI
- Customer Support
- AWS
- Timeline
- Live since 24 August 2026
- Industry
- Heavy-Duty Trucks & Engineering Services
Results
61.6%
of routine enquiries resolved by AI
77 of 125 routine enquiries, without the owner's intervention, 1–28 October 2026.
2.4 s
typical AI response time
1–28 October 2026, instead of waiting for a callback.
The challenge
Routine questions competed with paid engineering work
Customers contacted XCAN mainly by phone, text or email, and routine enquiries about truck availability, warranties, delivery, spare parts and service bookings needed the owner's direct attention.
The owner is often on site
The owner frequently works on site or under vehicles, so answering each message straight away wasn't always practical.
Questions competed with paid work
Routine questions took time away from paid engineering jobs.
Requests were hard to track
Requests that needed later attention were difficult to track consistently.
No unverified promises
Any automation had to avoid making unverified promises about stock, pricing or technical diagnoses.
XCAN needed basic information available at all hours, with the owner still in charge of anything that needs his judgement.
The solution
A website, an AI assistant and structured enquiry capture
A dedicated business website
Customers can explore trucks, spare parts and engineering services, then submit enquiries and service requests.
An AI customer assistant
The assistant answers common questions outside working hours and helps customers find relevant information.
Centralised request capture
Requests that need the owner, such as price quotations, stock checks and technical diagnoses, are recorded and sent to him by email and through a simple dashboard.
Controlled AI responses
Safety rules keep the assistant within approved information and stop it presenting unverified prices, inventory or technical conclusions as facts.
Outcome
Routine information on hand, the owner on the work
- 61.6% of routine enquiries resolved by the AI assistant (77 of 125) without the owner's intervention (1–28 October 2026).
- 2.4-second typical response time, instead of waiting for a callback.
- Enquiries and bookings captured centrally, giving the owner a structured way to follow up on requests that need human judgement.
Technology stack
AWS services behind XCAN
Edge and delivery
- Amazon Route 53
- Amazon CloudFront
- AWS WAF
- AWS Certificate Manager
- Amazon S3
Compute
- Amazon API Gateway
- AWS Lambda
Data
- Amazon DynamoDB
AI
- Amazon Bedrock
Security and operations
- AWS KMS
- Amazon CloudWatch
- Amazon EventBridge
- Amazon SNS
Business Impact
Support that extends the expertise, not replaces it
XCAN can make routine information available while its owner concentrates on engineering work, customer jobs and other revenue-generating activities. The business keeps human oversight for decisions that need accurate inventory information, commercial judgement or technical expertise.
For a specialist business with limited administrative capacity, AI can extend customer support without replacing the expertise that makes the business valuable.
More from the library.
All case studiesAI · Productivity
Seshira: AI-native project management
An engineering assistant on Amazon Bedrock AgentCore that plans sprints, turns PRDs into tasks and flags blockers, with about 80% less planning effort.
Agriculture, Engineering & Automotive
Sallis: one digital front door for three divisions
One website and a Morphlix Connect enquiry workflow for an agriculture, engineering and automotive company, with 99.8% availability.
Work with the studio
Ready to future-proof
your infrastructure?
Tell us what you are building and where the current stack is holding you back. We will come back with an architecture and a plan.