Your AI works, until it runs for a week.

Production readiness for AI systems. Observability, cost tracking, safety guardrails, and alerting so you know what happened before the invoice arrives.

Early AI systems work in small tests, then fall over in production. Costs spike, quality drifts, and nobody can trace why. You end up with a system that is expensive and unpredictable.

We build production readiness: policy-as-code and guardrails, distributed tracing, cost tracking, alerting, and anomaly detection. The infrastructure that makes AI systems reliable and accountable.

You get systems that keep working after the demo, not just during it.

Policy-as-code and safety guardrails

Guardrails that prevent bad behaviour before it ships. Policies that are enforced in code.

Observability and distributed tracing

Trace requests end to end, see where failures happen, and understand why.

Cost tracking and alerting

Know where spend goes and get alerts before costs get silly.

Anomaly detection and reliability checks

Detect drift and failure patterns early, before users notice.

Ready to discuss your needs?

Book a 30-minute call

Services offered

Things That is a product engineering practice focused on building AI systems that help people make sense of complexity. For over 20 years, we've worked with teams at Google, IBM, Air New Zealand, Kpler, EE, News UK, Tesco, and The Economist, sitting in the space between product strategy and hands-on engineering. When specialist help is needed, we work with a network of senior consultants and product designers.

We're not consultants who hand off to developers. We're product engineers and designers who think strategically about what users need, then build it, from architecture to APIs to interfaces to production deployment. Our work is hands-on, writing code, reviewing pull requests, designing schemas, and testing edge cases, but always with the human experience in mind.