Latest Articles
- 24 days agoAI Coding
The Autonomous QA Cycle: LangGraph, Langfuse, and a Custom LLM Judge
Real QA isn't linear. How I built Cairn around a state graph, Langfuse observability, and an LLM judge that asks whether a passing test actually proves anything.
- 27 days agoAI Coding
AI Agent Skills Promise 65% Savings. A Benchmark Found 8.5%.
JetBrains tested Caveman on 82 SkillsBench tasks. Token savings fell short, quality stayed flat, and cost variance erased the gain. What actually moves agent work forward.
- 28 days agoAI Coding
Why I Dropped the Big Prompt and Went Skills-First
A big system prompt overloads AI agents instead of making them reliable. Cairn's Skills-First approach loads only the skill needed now and keeps deterministic work in code.
- about 1 month agoAI Coding
From Eval to Your Own QA Agent: Why Generating Code Is No Longer Enough
After eval as a truth mechanism, building Cairn: why AI code generation needs an autonomous verification layer, not just more tests.
