← // SELECTED WORK

An AI system. Under control.

How we made an unreliable AI platform safe to sell, helping the team support larger clients and unlock new revenue.

Result

≈ +€60k revenue unlocked

3 new enterprise clients × ~€20k one-off project value each.

Situation

An e-commerce startup with several AI services already running faced the challenge of scalability. The codebase wasn't standardised, redundant architectural layers were generating latency, and the lack of an observability and testing strategy made it difficult to guarantee the quality and flexibility needed as the product evolved.

Decision

We performed a full refactoring to standardise the codebase and removed redundant layers, optimising performance. We improved the management of tools like LiteLLM and LangSmith to gain full visibility into AI flows, refining prompts to improve their effectiveness. We then introduced a suite of unit and integration tests to lock in the correctness and quality of the exposed services.

Result

The business could finally sell the product with confidence. Reliability stopped being a sales risk: the team could see what was happening inside the AI flows, fix quality issues faster, and support larger clients. That stability helped unlock about €60k in new project revenue.

Trace a wrong catalog price to the failing step uses a runnable example to separate stale tool data from an answer that misquotes a correct lookup.

LLMOps / LangSmith / LiteLLM / Scalability / E-commerce

Have a project in mind?hello@41dots.com ↗