← All case studies

E-COMMERCE / AI

AI System Optimisation, Observability & Quality Assurance

How we stabilised a fragmented AI platform for an e-commerce startup, introduced full observability, and unlocked the team's ability to ship faster.

LLMOpsLangSmithLiteLLMScalabilityE-commerce
The problem

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.

What we did

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

Platform stabilisation and the new observability layer were the main drivers of change, allowing us to monitor every interaction and proactively act on quality. This data-driven approach unlocked the team's ability to ship new features quickly. The quality leap had a direct impact on the startup's growth: the reliability achieved allowed them to scale their commercial offering, leading to the acquisition of several high-profile new clients they previously couldn't have handled.