Skip to main content
Services / AI Integration

Pragmatic AI features, shipped into real products.

No moonshots. I help product teams integrate LLMs, embeddings and classical ML into software they already ship — with an eye on cost, latency, evaluation and the very real risks that come with putting generative models in front of customers.

02 Capabilities

Where AI actually earns its keep inside day-to-day products.

01

LLM features

Summarisation, classification, drafting and extraction — wired into your existing stack with proper fallbacks and evals.

02

RAG & knowledge search

Retrieval-augmented assistants over your docs, tickets or codebase. Honest about what embeddings can and can’t do.

03

Agentic workflows

Tool-using agents for internal ops — careful scoping, audit logs, human-in-the-loop where it matters.

04

Predictive & classical ML

When regression or a gradient-boosted tree is the right answer, we use that instead of a 70B model.

05

Evals & observability

Golden sets, regression tests, latency & cost dashboards. Knowing when a new model is actually better.

06

Strategy & advisory

Short engagements to pressure-test an AI roadmap, a vendor choice, or a due-diligence question.

03 Principles

A sceptic’s approach to a hyped field.

  • 01

    Problem first, model second

    If the problem can be solved with a SQL query or a rule, it probably should be.

  • 02

    Measure before you believe

    Every AI feature ships with an eval set. Vibes are not a quality bar.

  • 03

    Guardrails, not prayers

    Structured outputs, rate limits, PII filtering, and clear failure modes.

  • 04

    Own your evals, not your weights

    Use hosted models when sensible. Self-host when privacy, cost or latency demand it.

Let’s talk

Thinking about an AI feature and want a sanity check before you commit?

hello@liauw-media.com