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.
A search that's actually directed
Anyone can open a site, set two filters and read back the first three results. What a competent person does instead is look at forty options, read the reviews, check the photos, and only then propose three. The difference isn't the tools — a worker already drives a real browser — it's that somebody has to decide how wide to look and what counts as good.
So before a worker starts, a selection gets a brief: hard criteria that disqualify kept apart from soft ones that merely score, a minimum number of candidates to gather before discarding any, several distinct search angles (one route always returns the same subset), and a quality bar made of concrete checks rather than adjectives — "rated 8+ with at least 100 reviews", not "make it good". The brief also adds what an expert would think of and the request didn't say: travelling with your own car means you'll need somewhere to park it.
That brief is composed off the conversation's critical path, which is exactly why it can afford to think. Then the worker follows the funnel in order — gather wide, filter by the hard rules, score the survivors, and spend the real effort verifying only the finalists.
The same structure works whatever the subject. Choosing a laptop, surveying the state of the art on a topic, researching a book, picking a library: the domain changes, the shape of directing a search doesn't. And a proposal can be made of pieces — somewhere to stay plus how to get there — so you compare and pick whole plans instead of assembling them yourself from separate lists.
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.
The narrowest-scoped worker in the system
A worker can also be launched from a conversation on the agent network — but only opt-in, and with the tightest leash of any session: a disposable working directory, version control reachable only through a bridge scoped to one pre-authorized repository, and file access enforced by a real hook rather than a polite instruction. Two separate operator decisions have to both be in place before it can run at all.