Engineering a CI-Triage Decision System
A ground-up technical study of Kirti's cost-sensitive CI-triage system: labels, trust gates, observers, evidence contracts, fusion, distillation, and human judgment around AI-assisted coding.
Read article ->Blogs
Studies for AI-native engineers.
Long-form essays on agentic systems, AI coding workflows, evaluation, and the engineering judgment behind reliable AI work.
Designing an AI Pull-Request Review Agent
A first-principles architecture study of a production-grade AI pull-request review agent: specialist reasoners, grounded context, orchestration, memory, evaluation, observability, and human review.
Read article ->Structural Reasoning Is the Missing Piece of Agentic AI
Reliable AI agents need more than longer context windows. They need explicit state, graphs, task DAGs, validators, proof logs, and feedback loops around the model.
Read article ->Genesis: The Loop That Prompts Itself
An AI coding plan is not a pile of prompts. It is a small machine that writes the to-do list, delegates work, checks results, and records what got done.
Read article ->