An undocumented codebase has always been a tax on new hires. In the agent era it's a different problem.
Agents don't go quiet when they hit a gap in context. They fill it. Confidently, and wrong. The architectural decision everyone knows because they were in the room? That doesn't exist to the fleet. They'll reverse it, or build on top of it in ways that silently invalidate it.
Write down why the system is the way it is. Not for the humans. For the context window.
Jason Waldrip
Posted on • Originally published at imacto.com
The context your agents don't have
For further actions, you may consider blocking this person and/or reporting abuse
Top comments (1)
This is basically the real “docs are for machines now” shift.
Feels like the failure mode isn’t missing docs anymore—it’s incorrect inference under missing context.
Do you think “write once for agents” docs end up being more like strict constraints (almost like code), or still just narrative explanations?