Writing
What we have had to work out while building an Agent IDE — parallelism, cost, evaluation, and where the boundaries of an honest wrapper are.
All pieces
Our own notes from building the product. The reading notes on other people's published research are a separate page: Blog.
- 2026Changing exactly one thing6 min read
Most tools that put a coding agent inside their own UI end up reimplementing it. There is a narrower move: launch the real CLI, and point one URL somewhere else.
- 2026Two agents, one repository6 min read
The moment you run a second coding agent on the same checkout, the two start overwriting each other. Linked git worktrees are the fix, and they are why parallel sessions are usable at all.
- 2026Evidence, not a verdict from the model6 min read
An agent that reviews its own work grades the diff. What you actually need to know is whether a person could finish the task — and that question needs somebody using the thing.
- 2026Cheap per call, expensive per hour5 min read
Every individual model call looks too small to matter. An afternoon of four agents does not. The gap between those two facts is where budgets quietly go.
- 2026The name we changed5 min read
We shipped under "ADE" — agentic development environment — long enough that our own X handle still says it. Then we changed the words on the front page to Agent IDE. Here is what the two names each get right.