Living journal
Everything I’m learning
The full record — discoveries, lessons and practical applications, newest first.
- CertificateNew
Building AI Responsibly Means Looking Beyond the Model — UNESCO Global MOOC (modules 7–10)
Responsible AI isn't about controlling technology, it's deliberate choices — sustainability, proportionality, real human oversight, governance beyond regulation. Course complete: 10 of 10 modules done.
Read more → - BuildingNew
Checking the real environment before I build
A hosting mismatch and a shell syntax difference both cost real time this build — confirming the actual deployment target and shell now happens before any code gets written.
Read more → - BuildingNew
Knowing what verification actually proves
Traced logic, stubbed type-checks, tests run outside the normal runner — all of it catches real bugs, none of it replaces actually running the build.
Read more → - BuildingNew
Asking before building, logging as I go
Resolving real ambiguity with a direct question before writing code, and keeping a running build log so every session starts from the actual state of the project.
Read more → - Certificate
Building Responsible AI Is a Human Problem — UNESCO Global MOOC (modules 4–6)
Fairness is a property of the experience, not the model. Working through privacy, data minimisation, transparency and accountability — 6 of 10 modules done.
Read more → - Certificate
Ethics of AI — UNESCO Global MOOC (modules 1–3)
The biggest challenges in AI aren't technical, they're human. Working through who benefits, who's harmed, who decides — 3 of 10 modules done.
Read more → - Building
Multi-agent orchestration
How to split a complex task across several small agents without losing track of what each one is doing.
Read more → - Exploring
Local-first architecture
Rethinking how much of an app can live on-device before you actually need a server.
Read more → - Exploring
Design systems for AI products
What changes in a design system when part of the interface is generated rather than fixed.
Read more → - Shipped
Guardrails for autonomous tools
Practical, lightweight checks that keep automated systems safe without slowing them down.
Read more →