CLI

I started using AI coding tools sometime in 2024. At first, that mostly meant Cursor-style code completion: useful, occasionally surprising, but not yet the kind of agentic workflow where I could hand over a repository-level task and expect sustained progress. Then the tools became more agentic. The models were not strong enough yet, but the interaction pattern changed. I could ask for bigger changes. The agent could edit several files. It could follow a plan, run tests, and try again. ...

I’ve been using Claude Code extensively for the past few months. One day, while working on a startup consulting project, I needed to reference an analysis Claude had helped me with. I had discussed alternatives, evaluated tradeoffs, and settled on a design approach for an Architecture Decision Record (ADR). But I hadn’t asked Claude to generate the usual markdown report. The analysis was gone from my immediate context. Somewhere in the conversation history, buried across multiple platforms where I work. ...