Technology · FlashBrain
The reflex layer.
Zaelar's own orchestration code — not a general-purpose reasoning agent. It answers every turn in under a second, drives the canvas, and decides what's worth escalating.
Every input — a voice turn, a connector message, a UI click — passes a deterministic gate before it ever reaches a model: is this actually directed at the agent, or ambient noise? Does it need a hard interrupt ("stop", "close everything")? Only what's left goes to the prompt.
One small prompt, composed live
The prompt isn't a static persona — it's assembled per turn from live state: identity and mission, what's on screen right now, a synthesized slice of recent conversation, plus a terse layer of available tools. A small, fast, non-reasoning model reads it and responds with either spoken text or a tool call.
Tool catalog
The model decides what to do by calling a function, not by matching keywords. That keeps the decision reliable even on a small, cheap model. The tools offered change with context — most only appear when they're actually relevant.
| tool | what it does | when it's offered |
|---|---|---|
| escalate | Launches a Brain Worker | always |
| web_search | One factual answer, resolved in the turn (~1-2s) | always |
| reveal_secret | Fetches an encrypted operator secret, out-of-band | always |
| play_music / play_video | Fuzzy media requests, resolved in-turn | always |
| widget_data | Runs one declared action on an open widget | when widgets are open |
| reply_message | Drafts a reply, gated by a confirm step before sending | when there are messages |
| delete_widget | Deletes a widget for good, with confirmation | when widgets are open |
| set_style_directive | Applies and persists a standing behavior rule | always |
| authenticate_web | Opens the browser to log in to a site | always |
| send_to_worker / stop_worker / answer_worker | Steers a live Brain Worker | only with live workers |
escalate to a Brain Worker.