Software development with AI
I build custom applications, integrations and assistants, with the practices that keep software alive: specification, review, tests, observability and maintenance.
Who it is for
Product and engineering teams with a specific problem.
Pilot in production
In about 4 weeks
Automated evaluations
From the start
Cost and latency
Instrumented
Everything this area covers
For when nothing on the market covers what you need.
What it looks like in practice
An internal assistant connected to the ERP for the operations team.
An application that generates technical documentation from the repository.
An MCP integration exposing internal systems to the team's assistants.
Related package · 4 weeks
From idea to pilot in four weeks
Something working with real users before committing a larger budget.
- Week 1 · Discovery and specification
- Week 2 · Clickable prototype and base integration
- Week 3 · Building the full case
- Week 4 · Evaluation, observability and handover
- Code, documentation and a plan for what comes next
The same path on every project
Discover
I look at processes, teams, tools and opportunities.
Prioritise
I rank the cases by impact, effort, feasibility and risk.
Prototype
I build a scoped pilot and measure whether it actually helps.
Roll out
I integrate the solution and train the people using it.
Measure
I instrument adoption, quality, cost and latency.
Scale
I add new cases and maintain the ones already running.
Does this fit your case?
Half an hour to understand your situation and tell you honestly whether this helps, what it would take and what to expect.