Side-post in the keppt build-in-public series — an interlude before the Phase 1 implementation...
I built the same MVP twice. The autonomous agent wrote 4.6x more tests — none caught two stubbed core methods.
Related
Running Gemma 4 26B on GKE with a Single L4 GPU
Alexey Nizhegolenko DevOps Engineer, AI Infrastructure Engineer When you start looking at...
Chunking for RAG: stop tuning the wrong knob
A practical chunking playbook for RAG: why semantic splitters disappoint, what chunk size + overlap actually buy you, and a small eval harness in Python.
Cómo Evaluar AI Agents: Comparación de 3 Frameworks
Al evaluar AI agents, la elección del framework determina tus puntajes. Ejecuta pruebas idénticas en...