Control loopscomingcoming soon

When to use a session#

• Now and then: a ticket, a payment, a tool call

  Use

  POST /v1/decide

  Why

  Each decision stands alone; one request, one answer

• Many inputs at once

  Use

  Fan-out or a batch job

  Why

  Parallel requests within your rate limits, or half price when it can wait

• More than 10 times a second, on one evolving input

  Use

  A session comingcoming soon

  Why

  The context is sent once and stays loaded; each frame carries only what changed

A decision layer, never the controller#

A vehicle runs in layers. The inner loop keeps it stable, many times a second, on its own controller. Above it sits a layer that decides what to do: continue or abort, which mode, which manoeuvre next. That is the layer a session serves. Its answers feed your controller, which stays in charge of the vehicle.

• Mission and planning

  Decides

  The route, the task, the next job

  Runs on

  Your planner, with /v1/decide calls when it needs a judgment

• Decision layer

  Decides

  Which mode now, continue or abort, the next action

  Runs on

  A DecisionNode session comingcoming soon

• Inner control loop

  Decides

  Attitude, speed, motors, brakes

  Runs on

  Your flight or motion controller, untouched

The loop#

1. 1.Open a session once, with the mission brief as state and the questions every frame should answer.
2. 2.On every tick, send only what changed as a frame: telemetry, a sensor reading, a camera frame.
3. 3.Hand each reply to your controller as a request, not a command: it applies the mode when the answer clears your threshold and the controller's own limits allow it.
4. 4.When no fresh reply has arrived by your deadline, the controller keeps its current mode or runs its own failsafe. Your code decides that on its own, every time.
5. 5.End the session when the mission ends.

Sessions has the full client in Python and TypeScript: one task streams frames, one reads replies and hands them on.

Designing frames#

• Put the constant part in the session. The brief, the rules and the geofence go in state once; frames carry readings.
• Keep frames small. A frame holds at most 4,096 tokens or one image. Name the fields (battery, wind_mps) so the model knows what each value is.
• Choose the window for the decision. A mode change that depends on a trend needs a few recent frames; a reflex check on the current frame needs one. Send "reset": true when the situation changes completely, such as after landing.
• Ask only what this tick needs. List questions on a frame to answer some of them; each frame is billed for the questions it asks.

What to build#

• Drones and vehicles, civilian: mission supervision for survey, inspection and delivery flights; return, hold and land decisions; mode selection.
• Simulators and games: the next manoeuvre or action from a stream of state.
• Industrial monitoring: machine state to action, alert or hold, from sensor frames.
• Long-running agents: stream tool results and get a typed next step, without resending the whole context each time.