Insights
Product, design, AI, and engineering perspectives from our team.
AI Incident Response: What to Do When Your Model Fails in Production
When an AI model fails in production, the failure is often silent — no error code, just degrading outputs. This guide is a practical incident response playbook for ML and LLM systems: detection, severity classification, rollback, stakeholder communication, and post-incident review, built for technical leaders who need to extend their existing incident processes to cover AI-specific failure modes.
The Open Knowledge Format: AI-ready knowledge without lock-in
The Open Knowledge Format (OKF) is a vendor-neutral way to turn scattered organisational knowledge into a portable, AI-ready asset. Here's what it is, why it matters for RAG and AI readiness, and how to start.
Change Management for AI Adoption: Getting Staff to Actually Use It
AI rollouts stall not because the technology fails, but because the people side is an afterthought. This post breaks down why adoption flatlines and provides a practical eight-step change management playbook to drive genuine, sustained AI usage across your teams.
Upskilling Your Engineering Team for AI: A Practical Plan for CTOs
Most engineering teams can integrate an API — far fewer are ready to build production AI systems that are observable, compliant, and resilient. This post gives CTOs a concrete plan: how to map current capabilities, build tiered learning paths, design hands-on projects, and decide when to train versus hire.
Fine-Tuning Small Language Models for Domain-Specific Tasks
Fine-tuning a small language model can outperform a frontier model on narrow tasks — but only when the task, data, and economics actually justify the overhead. This article covers when fine-tuning makes sense, how to prepare data and evaluate properly, and how to honestly assess the cost trade-off against prompting a frontier model API.
Caching Strategies for LLM Applications: Reducing Latency and Cost
Caching is one of the most underused levers for reducing cost and latency in production LLM applications. This article covers prompt caching, semantic caching, and response caching — what each layer does, when to use it, and how to think about invalidation and observability.
Structured Outputs and Function Calling: Making LLMs Reliable
Structured outputs and function calling are the mechanisms that make LLMs viable in production workflows — but reliable implementation requires deliberate schema design, validation layers, and observability from the start. This guide covers how to use both patterns effectively, when to choose each, and the failure modes that catch teams off-guard at scale.
Agentic RAG: When Retrieval Needs Reasoning
Standard RAG works well when one retrieval pass is enough. Agentic RAG is the architecture for problems that require planning, iterative retrieval, and reasoning over results from multiple sources. This post covers the patterns, the platform options, and the real engineering trade-offs.
Australia's Voluntary AI Safety Standard: A Compliance Checklist
Australia's Voluntary AI Safety Standard sets out ten guardrails for responsible AI adoption. This practical checklist walks Australian businesses through each guardrail — what it requires, what to do, and how to sequence the work based on your current AI maturity.