Nov 04, 2026
dakma-sdk 2.0: Every Forecasting AI Model Can Be Explained
dakma-sdk reaches 2.0: Every Forecast Gets an Explanation
Read more →Oct 08, 2026
dakma-sdk 1.0: Every Decision Gets a Record, Every Word Gets a Score
dakma-sdk reaches 1.0 with a stable decision event and explain_text, which attributes text decisions to individual words.
Read more →Jul 22, 2026
Introducing Dakma-SDK
An introduction to an SDK on explainability and transparency.
Read more →Jul 03, 2026
Why I'm writing here
Starting this blog to think in public about explainable AI, pragmatics, and what it actually takes to ship ML systems people can trust.
Read more →