Engineering

Shipping LLM features without breaking production

Marcus Lee, Principal EngineerJun 20267 min read

Large language models have moved from novelty to expectation. Customers now assume your product can summarise, draft and answer — but bolting an LLM onto a live system is where most teams get burned.

Start with a narrow, reversible surface area. Pick one workflow where a wrong answer is cheap, ship it behind a feature flag, and measure before you widen. We treat every model call like an external dependency: timeouts, retries, fallbacks and a hard budget.

Evals are non-negotiable. Before launch we build a golden set of 50–200 real examples and score every prompt change against it in CI. A change that looks better in the playground often regresses on the long tail — the eval catches it.

Guardrails sit on both sides of the model: input validation and PII stripping going in, schema validation and toxicity checks coming out. If the model returns something unparseable, we fail closed to a deterministic path rather than showing the user a broken response.

Roll out by cohort, watch your latency and cost dashboards like a hawk, and keep the kill switch one click away. Done this way, AI features become just another well-instrumented part of the stack — not a production incident waiting to happen.

Let's build what's next.

Tell us about your product and we'll come back within one business day with a clear path forward — no obligation.

Headquartered in Hong Kong — engineering and delivery across Eastern Asia and Eastern Europe, with US partners as fractional CTOs.

Start a project

Tell us what you're building — no obligation.