LLM Safety and Security with Model Armor
Introduction Large Language Models (LLMs) unlock incredible new possibilities, but they also open doors to prompt injections, data leaks, and toxic outputs. If you’re building serious applications, security and compliance aren’t optional. That’s where Google Cloud Model Armor comes in. Model Armor is a guardrail service designed to protect your AI pipelines, offering rule-based filtering […]
Patterns of agentic AI
Introduction Retrieval augmented generation (RAG) marked a breakthrough for enterprise AI by helping teams surface insights and answer questions at high speed. For many, it was a launchpad: copilots and chatbots that streamlined support and reduced the time spent searching for information. However, answers alone rarely drive real business impact. Most enterprise workflows demand action […]
AI That Can Change Itself
Introduction Large language models (LLMs) are powerful but fixed; they cannot change their weights for new tasks, knowledge, or examples. We introduce Self-Adapting LLMs (SEAL), a framework that lets LLMs adjust by creating their own finetuning data and update steps. When given new input, the model makes a self-edit — this may restructure the information, […]
Introduction to AI Agents and Context Engineering
Walking through a context-driven project automation example Overview In the not-so-distant past, most “AI” systems were just advanced calculators—great for crunching numbers, but terrible at adapting or remembering what they’d done before. Fast forward to today: AI agents powered by large language models (LLMs) like OpenAI’s GPT-4 can now reason, plan, and act with an […]
How AI/ML is Transforming Finance: Smarter Decision-Making for CFOs
The financial sector is increasingly adopting AI/ML (artificial intelligence/machine learning) more quickly. The 2024 SAP Concur CFO Insights survey showed that 51% of finance executives had a minimal investment in AI, a steep jump from just 15% in 2023. Yet 58% accept that their fundamental understanding of how AI can add value to finance is […]
How Can AI/ML Help the COO or Head of Operations Deliver Highly Effective, Efficient, and Profitable Operations?
In 2025, Australian businesses face mounting commercial pressure to streamline operations and, in the process, drive up profitability. COOs and Heads of Operations have shifted focus from managing processes to driving innovation and resilience. Artificial Intelligence (AI) and Machine Learning (ML) are central to this transformation, which has proven essential for striking the right balance […]
Exploring the power of graph databases in the age of GenAI
In the rapidly evolving landscape of artificial intelligence (AI), the way we store and retrieve data is critical. With the advent of Generative AI (GenAI) technologies, the need for efficient and effective data management systems has never been greater. Among the various database options available, graph databases, such as Neo4j, are emerging as a powerful […]
The Chief Artificial Intelligence Officer Explained: A Guide to the CAIO Role
The role of the Chief Artificial Intelligence Officer (CAIO) has become essential as more organisations adopt AI into their business strategy. Unlike the Chief Technology Officer (CTO), who primarily oversees the development and implementation of technology across an organisation, the CAIO focuses on strategically deploying AI to transform business operations and drive competitive advantage. Their […]
Leveraging Porter’s Five Forces and AI/Machine Learning in Modern Organisations
Porter’s Five Forces model, developed by Michael E. Porter in 1979, remains a cornerstone for analysing the competitive forces that shape industries and strategies within organisations. This framework provides a structured lens through which to examine not just the field of artificial intelligence (AI) and machine learning (ML) but the broader spectrum of modern organisational […]
Advanced Chunking Strategies for RAG
What is Chunking? Nowadays, the development of large language models (LLMs) is progressing rapidly. However, with their advancements come certain drawbacks, such as hallucinations. To address this issue, Retrieval-Augmented Generation (RAG) was developed. Let’s briefly introduce RAG. RAG is a natural language processing technology that combines retrieval and generation. It operates through the following steps: […]