Technology · Brain Workers
Live sessions that do the real work.
When a request needs actual reasoning — research, multi-step tasks, writing or modifying a widget's code — the FlashBrain launches a Brain Worker: a live, steerable session with its own tools and memory access.
A worker isn't a one-shot script — it's a live, bidirectional session the FlashBrain governs for as long as it runs. It can inject a refinement mid-task ("actually, make it green" — without opening a second one), kill it outright, or answer a question the worker is waiting on.
Agnostic of the executor
The interface underneath is a single seam — a worker backend can be Claude Code today, another coding agent tomorrow, and different backends can run side by side. Swapping the executor never touches how the FlashBrain talks to a worker.
Three channels, one session registry
Every live worker is tracked in one in-memory registry — the single source of truth for what's running, so the UI always reconciles cleanly instead of showing orphaned tasks. Communication with a worker runs on three channels: injecting a refinement downward, the worker reporting status upward over the bus, and a request/response channel for a worker to ask a question or use a lent tool (like web search) under an explicit allow/confirm/deny policy — a worker can never call an operator-only capability on its own.