Insights · Field notes and evidence
Ideas from the work.
Evidence from delivery.
Articles unpack the principles behind dependable data and AI systems. Case studies show the constraints, decisions and outcomes behind selected work.
- Articles
- 02
- Case studies
- 03
Showing 5 insights.
Building carbon compliance around a numerical source of truth
How deterministic calculation, constrained language generation and visible provenance combine in a more dependable carbon-compliance product.
When an LLM should not do the maths
A practical design rule for systems that need both exact calculation and useful generated explanation.
From physiological signals to product-ready monitoring
Leading applied R&D across ECG, PPG, temperature and oxygen-saturation data, from collection and evaluation to Android and cloud integration.
The model is only one part of the system
Why framing, data contracts, evaluation and delivery usually matter more than another round of model tuning.
Turning impact research into an open calculation toolkit
Translating stakeholder needs and impact research across people, natural and built environments into data structures, calculation logic and a phased product roadmap.
Continue the conversation
Working through a similar problem?
I’m always interested in difficult data, applied research and systems that need to earn trust.
Start a conversation