How we built a full AI car diagnostic web app for a Swedish startup, from architecture to launch, with real repair data and billing infrastructure.
[ Client ]
CarmyAI is a Swedish automotive tech startup building CarmyAI, a web app that acts as a virtual mechanic for everyday drivers. Users describe a symptom, paste a fault code, or upload a photo and get a clear diagnosis, cost estimate, and step-by-step repair guide. Their goal is simple: help drivers know what is wrong with their car before they spend a cent at a shop. To bring this vision to market, they needed a technical partner who could own the entire product build from the ground up.
[ Challenge ]
Carmy came to us at founding stage with a clear vision but no in-house engineering team. The product concept was strong. The technical reality was not simple.
The core problem was specificity. Generic AI responses were a non-starter. The product had to pull real manufacturer repair data, match it to a user's exact vehicle, and handle multiple input types including symptom descriptions, OBD fault codes, and photos. Vague answers would kill trust instantly.
On top of that, the business needed to launch commercially ready, not as a demo. That meant building in parallel:
They needed one partner to own the full build.
[ Solution ]
We engineered an AI-powered mechanic assistant using Claude's tool-use capabilities, built on a Next.js full-stack architecture and deployed on Vercel with Supabase as the data layer.
We built a multi-country license plate lookup system that connects to manufacturer databases across 9 countries. Users enter their plate number, and the system automatically resolves make, model, year, and internal vehicle identifiers — eliminating manual data entry and unlocking access to vehicle-specific repair data from the first interaction.
At the core of the product is a Claude-powered agent (Sonnet 4.6) equipped with 24 automotive tools. For example:
Claude autonomously decides which tools to invoke based on the user's question, chaining up to 10 tool calls per turn for complex multi-step diagnoses. When vehicle-specific data isn't available, the agent falls back to web search, ensuring no question goes unanswered.
We implemented a real-time Server-Sent Events streaming pipeline that displays exactly how user’s diagnosis was reached. This transparency builds trust with DIY owners making safety-critical repair decisions.
To keep the product economically viable at scale, we enabled Anthropic's prompt caching on system prompts and conversation history. This significantly reduces token costs on follow-up messages within a conversation, where the vehicle context and prior exchanges are already cached.
Rather than a blunt message count, we built a granular token-based billing system that logs usage per tool-calling leg. Simple questions cost less than complex multi-tool diagnostics, giving users fair value across a Free, Plus, and Pro tier — with Stripe handling subscriptions and billing management.
[ Results ]
CarmyAI launched as a complete, commercially ready product. Every layer of the platform, from AI diagnostics to billing infrastructure, was delivered production-grade from day one.
Thanks to the multi-country license plate lookup and 24 specialized automotive tools, users receive vehicle-specific repair guidance from the very first message — no manual setup, no generic answers. The AI handles everything from routine maintenance queries to complex multi-system diagnostics within a single conversation.
Real-time streaming of tool calls gives users visibility into how their diagnosis was reached. A meaningful differentiator for safety-conscious DIY owners making repair decisions. Transparency is a feature, not an afterthought.
Prompt caching on system prompts and conversation history significantly reduces per-conversation token costs, keeping the unit economics viable as usage grows across Free, Plus, and Pro tiers.
[ Case Studies ]
We have helped over 200 businesses grow their value and improve how they work through better software.
Let’s discuss your goals and how AI can help you achieve them faster.
