AI & ML4 min
Evaluating LLM features before you launch them
Shipping an AI feature without an evaluation harness is shipping a system nobody can prove works. Here is the eval setup we build on every engagement.
Insights
Notes from the work.
Architecture, performance, and how we actually ship — written by the people on the project.
- Architecture4 min
The strangler fig: migrating legacy systems without a freeze
Big-bang rewrites fail for structural reasons, not technical ones. A field guide to incremental extraction from systems that cannot go offline.
- Performance3 min
What Core Web Vitals actually cost you in revenue
We instrumented six e-commerce clients to correlate LCP and INP with conversion. The numbers were larger than any of them expected.
30 minutes · CET · no deck
Book the call. Leave with a plan.
Bring the paper, the WhatsApp thread, or the spreadsheet. We will tell you what to build first — and what not to.