Insights and thoughts

From the history of reading to how AI is changing information retrieval, and why books still offer irreplaceable benefits for the brain, focus, and connection.

Flow is a SwiftUI-based iOS app built to block doom scrolling; this story covers how I vibe coded it with AI tooling, navigated Apple's frameworks, and partnered with my brother to ship it.

Data stories work when they have a clear claim, focused evidence and facts, and a visible outcome that closes the loop. Using the CF+O (Claim-Facts-Outcome) structure to guide your argument, design for the audience with purposeful titles and annotated visuals, and anchor everything to a single five‑second moment that changes what the audience believes or does next.

From semantic models to AI agents: how NL2SQL tools and MCP‑connected assistants evolved self‑service analytics, letting anyone query and visualise live databases in plain language.

AI is limited today because it cannot truly understand or maintain context the way humans do. As context windows expand, tools like Model Context Protocols, AI agents, and integrated systems will allow AI to act more intelligently, bridging the gap toward AGI.

Analysts who embrace AI as a productivity tool and double down on skills like storytelling, prompt engineering, and strategic thinking will become even more valuable.

When creating data visualisations, you face a fundamental choice: design for quick insights and pattern recognition (perception) or enable precise measurements and exact readings (precision).

Explainable AI and model interpretability make AI decisions transparent and understandable, which is essential for building trust and accountability in the age of complex, generative AI.

Creating a data-led audience audit procedure using LinkedIn ad data to prove product value without a full setup.