Two people. Both senior. Both on your project.

Chris Matthews

Co-founder · Strategy, Product, Commercial

chris.matthews@silkyinsights.com+64 21 432 321

• Led AI strategy and adoption end-to-end at board level for a regulated NZ organisation
• 33% efficiency gain from production LLM triage agents
• 134 research artefacts synthesised into 20 evidence-based prompting principles

Chris has spent over eight years running client-facing AI discovery and turning early-stage ideas into agentic, voice-enabled and governed production systems. He works on the question that comes before the code: what is worth building, whether the data is ready, and what order the work should happen in.

Through Silky Insights he has shaped and delivered semantic search and RAG platforms, workflow automation and LLM-enabled decision-support products, and runs the discovery workshops that advise CEOs and boards on feasibility, build-versus-buy decisions and responsible adoption.

He has held AI strategy, adoption and delivery end-to-end at board level in a regulated New Zealand organisation, taking it from first experiments through structured discovery and solution design to enterprise-wide adoption. That work included production LLM triage agents with approved knowledge boundaries and escalation rules, delivering a 33% efficiency gain in operational handling, and the research and prompting design behind a voice and call agent strategy: 134 research artefacts on voice-agent psychology and latency reviewed to define 20 evidence-based prompting principles.

He has also built quality and risk governance foundations from the ground up alongside external regulatory and privacy stakeholders. Evaluation loops, escalation rules and human oversight are built into every system he has shipped. A mechanical engineering background, five years building Silky Insights from a standing start into a profitable advisory practice, and a habit of scoping ambiguous problems and carrying them through to real delivery, not a strategy deck.

Luke Doyle

Co-founder · Chief Technology Officer

Luke is Silky’s CTO and builds the systems. His work covers the full path from unstructured source material to something a product can query: document ingestion, extraction from PDFs and tables, foundational database design, vector search, and the retrieval architecture that decides what a model actually sees.

He started by building a chess-playing bot with machine learning written from scratch, which is a fair summary of how he still works, down to the mechanism rather than the abstraction. He specialises in RAG systems and structured outputs: getting reliable, traceable results out of models rather than plausible-sounding ones, which is what makes AI usable in compliance and other high-stakes settings.

He leads the technical work on every engagement, deploys across Azure, GCP and AWS into infrastructure the client controls, and owns the evaluation and monitoring that tells you whether retrieval is genuinely working. He is also the person who explains what the system is doing in plain language, to whoever needs to understand it.