Digital workshop
Builder. Tinkerer.
Explorer.
Lifelong learner.
Exploring how AI can make complex work more accessible, helping more people build, create and solve problems they previously could not.
This is a collection of projects, experiments, lessons and systems built in public.
Living journal
What I’m learning
Most of my work starts with curiosity. I enjoy exploring how people can use AI and automation to tackle ideas that previously felt too technical, time consuming or complex.
This section becomes a living journal of discoveries, lessons and practical applications.
- 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 →
Built & shipped
Featured projects
Each one covers the problem, the approach, the outcome and what it taught me.
Right now
Current experiments
Small, in-progress bets. Some will ship, some will get quietly parked — both outcomes are worth recording.
Robin — the Researcher at 80 percent
ActiveOne agent, one job: whatever I forward during the day gets researched live and lands as a structured, fully-sourced note in my vault by 5pm. Handling 10–14 real items a day — repos verified live, hype called out, unverifiable stuff filed as needs-input instead of guessed. Fortnight gate coming up: promote the next node, or add nothing because one agent still holds.
AgentsLocal-firstObsidianRead more →Alfred, hands-free and house-wide
ActiveCustom wake word trained, conversation loop proven, phone voice working over HTTPS on the LAN, answers grounded in my own notes with citations and refusal, and web search added through a self-hosted metasearch that only fires when explicitly asked. Still local, still private, still $0. Now living with it daily to see how false-trigger tuning, real household noise and the screens around the house actually hold up.
VoiceLocal LLMSmart homeRead more →Split-flap board
ActiveLive and shipping features weekly — this round tightened message-row packing and gave the dad joke its own laugh emoji. Next up: getting it in front of the actual TV and seeing what breaks that a browser window never would have shown me.
Hardware displayWebRead more →Working style, more than any one project
ActiveFiguring out how to actually collaborate well on a build: when to ask before building versus just building, how much to verify before handing something back, what “done for tonight” should mean.
ProcessCollaborationRead more →
Field notes
Workshop notes
Short write-ups on what worked, what didn’t, and what I’d do differently next time.
- New
Adopt before you build
The plan said build a research agent. The honest check before writing a line of it found I’d already been running one since July — and adopting it took hours, not weeks.
Read note → - New
The boring parts of a project are where the real bugs hide
A price calculated per-pack instead of per-piece, an Excel table that silently stopped growing, an import wizard that stalls without saying so — none of it was interesting to find. All of it was real.
Read note → - New
Working style is the real experiment here
Not a project — a running experiment in how the work itself happens: when to ask, how much to verify, and what counts as done for the night.
Read note → - New
Check the real environment before you build
A hosting mismatch and a one-character shell difference both cost real time this week — the same root cause: checking assumptions after building instead of before.
Read note → - New
Indirect checks catch real bugs — they just don't replace the real thing
Logic traced by hand, code checked against a stub, tests run outside the normal runner — all of it caught real bugs. None of it replaced actually running the build.
Read note → - New
Ask before you build, log as you go
The messiest, most expensive parts of this build were the ones nobody asked a question about first. The cheapest insurance was a ten-minute log.
Read note →
Get in touch
Let’s build something worth writing about
Open to conversations about AI, automation and building in public. Find me at any of these.