Work
I build AI-native products end to end - from the data and extraction pipelines underneath to the polished front-ends on top — shipped solo or in teams, and I build them fast.
Recent project examples
JutJut
jutjut.co.uk →Opportunities for young people shouldn't depend on luck. JutJut connects young people to the life-changing opportunities they'd otherwise never hear about.
An AI-powered data pipeline discovers opportunities from around the UK, structures them and feeds them to users according to their interests and career goals. All wrapped up in a highly responsive UI with low operational costs.
Next.js · React · TypeScript · Tailwind · Turborepo · FastAPI · Pydantic · Supabase
RedLines
In progressCreating easy access to planning applications for the public, industry and government.
A georeferencing engine for planning documents. It recovers the red-line site boundary that exists only as pixels on a map figure inside a PDF and places it in real-world coordinates as GeoJSON — via a cheap-to-expensive ladder (embedded GeoPDF metadata, coordinate-grid affine solve, declared-extent captions, scale-bar-and-anchor, basemap match) backed by PDF parsing, computer vision and OCR. First vertical: UK planning red-line boundaries.
Python · FastAPI · PyMuPDF · GDAL · OpenCV · Tesseract OCR · vision models · shapely · pyproj · GeoJSON
Developing AI agents and data pipelines
Read the Field Notes →Building large-scale systems for finding, processing and analysing information from many different sources.
A production-scale system combining AI agents, data pipelines and quality controls to turn varied, unstructured information into reliable data and analysis. The engineering lessons — including architecture, verification, cost control and scaling — are documented in the Field Notes.
AI agents · data pipelines · document processing · entity resolution · quality control · human review
Build challenges
I set myself a brief and turn it into working software.
Watch the build challenges →What I do
I build large-scale AI data systems, solo and in teams — turning messy documents and web pages into reliable structured data, and building the checks that make an LLM’s output trustworthy enough to act on. The working method is documented in the Field Notes.
Build a better data workflow
AukInfo designs and builds AI agents, data pipelines and automated systems that turn difficult information into useful outputs.
Discuss your data or automation project