About
About Build with AI
Build with AI is run by Don Proudfoot in Cape Town, South Africa.
Who is behind it
Don Proudfoot is the founder of Build with AI, based in Cape Town. He has worked in construction since 2007, is PMP certified and runs a construction project management practice. He builds AI workspaces for owner-led businesses.
The same kind of workflows run in that practice. See AI workflows for construction project managers for what we built there.
Nineteen years on commercial building sites
Don started in construction in 2007 as a junior straight out of his studies. Since then he has run commercial developments in Cape Town from feasibility through to close-out: offices, mixed-use buildings and hospitality projects. His practice works for developers as their project manager and principal agent, coordinating the full consultant team, the contractor and the client from the first drawing to the final account.
That work is paperwork-heavy. Minutes, progress reports, contractor instructions, payment certificates and the registers behind them all have to be right, on time, every week. It is where the AI workflows on this site started: built first for his own projects, then tested there week after week before any client saw them.
What is running today
- More than ten AI workspaces in daily use across his own businesses and client businesses.
- Live systems for an accounting practice, a travel agency and a window manufacturer, each set up around how that business already works.
- Weekly meeting minutes, progress reports and pricing comparisons on live construction projects, drafted by AI and checked by a person before they go out.
How he works
One workflow at a time, starting with the job that costs your team the most hours. Every workflow has a person approving what goes out, and your team learns to run it themselves rather than depending on an outside consultant. The scope and price are agreed before any work starts, and the final payment is only due once every workflow works.
The method
The method is the one on the home page. We use the same approach in our own day-to-day work: give AI the right context, set clear limits and keep people responsible for decisions.
- Map. Choose the workflow, authoritative inputs, responsible people and desired outcome.
- Define. Agree systems, access, approval points, exclusions and acceptance criteria.
- Build & check. Tailor the workspace and test normal work, missing information and the agreed failure cases.
- Hand over & adopt. Give a brief orientation, leave practical lessons and record acceptance. Adoption support stays within the agreed scope.
Start with the work.
Email Don with a repeatable task that slows your team down. We’ll discuss a useful first workflow and a scope you can assess before you commit.