How to use AI coding tools like a senior engineer
AI governance for risk and compliance teams is ultimately about operational trust. This blog explores how financial services organisations can move Gen AI systems safely into production through clear policy frameworks, AI risk ratings, observability, lifecycle ownership, audit trails, and APRA-aligned operational controls.
Building trust through AI Governance with Australian regulators
AI governance for risk and compliance teams is ultimately about operational trust. This blog explores how financial services organisations can move Gen AI systems safely into production through clear policy frameworks, AI risk ratings, observability, lifecycle ownership, audit trails, and APRA-aligned operational controls.
Building trust through AI governance in Financial Services
AI governance in financial services is ultimately about trust. This practical guide explores how to build Gen AI systems that can move safely into production through accuracy, explainability, operational controls, and compliance validation. From model optimisation to auditability, learn how regulated organisations can build AI systems that users, risk teams, and regulators can confidently rely on.
AWS Vector Store for RAG – Beyond OpenSearch
Compare AWS vector store options for RAG, including OpenSearch, S3 Vectors, Aurora pgvector, and more. This guide breaks down Bedrock Knowledge Bases integrations and custom pipeline approaches to help you choose the right solution based on latency, cost, and architecture.
Agentic AI: From Hidden Tool to Trusted Partner
Agentic AI is transforming the way we work, evolving from hidden tools in the shadows to trusted collaborators. In this blog, we explore the four stages of agentic AI, the key risks of data, hallucination, and context drift, and why human-in-the-loop governance is essential for building trust and maximising productivity.
How AI Became My Coding Assistant (And Why It Should Be Yours Too)
AI coding assistants are changing how developers work. In this blog, Ian Ng shares how Amazon Q Developer became a powerful coding partner, helping automate routine tasks so developers can focus on architecture, problem-solving, and building better solutions faster.
AI Agent Evaluation Techniques: Step 1 in AI Excellence
Evaluating AI agents is the critical first step in achieving AI excellence. This blog explores modern frameworks and benchmarks that assess agents’ core capabilities, domain-specific performance, generalist reasoning, and evaluation methodologies, ensuring AI systems are reliable, adaptable, and ready to deliver real business value.
Advanced Prompt Engineering for AWS
Advanced prompt engineering for AWS goes beyond basic prompts. By using techniques like chain-of-thought reasoning, few-shot learning, and iterative refinement, you can guide AI to deliver smarter, context-aware solutions that actually work within real-world project constraints. In this post, I share the methods I use on client projects to turn AI into a true consulting partner.
Prompt Engineering for AWS: Why I Started Having Real Conversations with AI
Prompt engineering for AWS has transformed the way I work in cloud consulting. By learning to give AI tools like Amazon Q and Amazon Bedrock the right context, constraints, and roles, I’ve gone from getting generic answers to receiving tailored, cost-saving solutions. In this post, I share the practical techniques that turn AI into a true partner for solving complex AWS challenges.
AI isn’t always the answer: When Generative AI is not it
Explore when Generative AI isn’t the best tool and why traditional machine learning models often provide better solutions in specific scenarios.