https://john.onlee.io/en/blog/Recent content in Insights on John on LeeHugoenTue, 23 Jun 2026 00:00:00 +0000https://john.onlee.io/en/blog/how-to-make-an-ai-coding-agent-actually-yours/Tue, 23 Jun 2026 00:00:00 +0000https://john.onlee.io/en/blog/how-to-make-an-ai-coding-agent-actually-yours/I built Monet to fix the agent that forgets yesterday’s conventions. How an agent that writes its own memory, reads what mattered, and grows with use actually works.https://john.onlee.io/en/blog/coding-agent-customization-survey/Sun, 31 May 2026 00:00:00 +0000https://john.onlee.io/en/blog/coding-agent-customization-survey/Two developers, same tool, wildly different setups. How deep coding agent customization goes — from bare defaults to full pipelines — and what actually pays off.https://john.onlee.io/en/blog/behavioral-llm-benchmark/Tue, 26 May 2026 00:00:00 +0000https://john.onlee.io/en/blog/behavioral-llm-benchmark/What today’s LLM benchmarks actually measure, what they miss, and why we need behavioral benchmarks instead of more knowledge tests.https://john.onlee.io/en/blog/token-economics/Thu, 21 May 2026 00:00:00 +0000https://john.onlee.io/en/blog/token-economics/Two requests with near-identical input tokens, a 46x cost gap. How prompt caching really works, and why agents should be designed around structured state.https://john.onlee.io/en/blog/claude-opus-economics/Wed, 20 May 2026 00:00:00 +0000https://john.onlee.io/en/blog/claude-opus-economics/Opus prices fell 67% in a year. A weekend of napkin math on GPU costs, batching, and tokenizer overhead to estimate what Anthropic actually makes per token.https://john.onlee.io/en/blog/does-your-coding-agent-need-memory/Thu, 14 May 2026 00:00:00 +0000https://john.onlee.io/en/blog/does-your-coding-agent-need-memory/Coding agents re-read the same files and re-ask the same questions every day. What memory actually does for an agent, how it differs from docs, and when it pays off.https://john.onlee.io/en/blog/context-window-management/Mon, 11 May 2026 00:00:00 +0000https://john.onlee.io/en/blog/context-window-management/Bigger context windows didn’t give better results. Notes on the context-management problems that keep recurring in real coding agent sessions.