What is AI context?
AI context is what an assistant should know before it touches your work: how you like things done, what must never be done, where things are. fenbs keeps it on the board.
Last checked
AI context is everything an assistant should know before it starts: what you are making, how you write tasks, what it must never do, where things are, what it learned last time. Every assistant has some way of remembering it — a memory, a project file, a system prompt — and every one of those lives inside that assistant. Change assistant and you start from nothing.
Keep it with the work, not with the assistant
fenbs keeps AI context on the board, in short notes with a category — About, How we work, Words, Rules, Where things are — at two levels: notes for everything, and notes for one project. An assistant connected over MCP calls fenbs_get_context on arrival and reads exactly the notes for what it is about to work on, never the other projects’. Switch from Claude to Cursor tomorrow and the new one reads all of it the moment it connects.
Assistants can add to it
A note an assistant writes — “the staging server is at …”, “tests need the API running” — is signed with its name and marked as learned by an assistant, so what one worked out is waiting for the next. Anyone who can see the board can read the context; changing it needs the permission to change tasks.