system one · playground

typed decisions,
not text.

Give the model a state and a focused question. It returns a typed decision with probabilities, not a paragraph of generated text.

01 / start with an example

choice

Who should handle this request?

Route a duplicate-charge message to the right team.

noul

Is this meeting time confirmed?

"I land at 8:00" is an arrival time, not a slot.

noul

Does this message need urgent help?

A checkout outage that is losing orders right now.

score

How frustrated is this customer?

Place a support message on a three-level scale.

choice

Which tool fits the next step?

Let an agent pick its next tool call.

noul

Should a human review this action?

Add a review step before a risky change.

choice

Continue, retry or stop?

Decide what an agent loop does after a failed step.

score

How ready is this lead to buy?

Score an inbound sales email.

02 / playground

Choose one answer from your options.

input / choice

↺ reset

The context to evaluate. JSON objects and arrays are sent as JSON.

03Choices4 / 8
A
B
C
D

output

awaiting result

Your decision appears here

Ready when you are.

  • Billing
  • Technical support
  • Sales
  • Other

ready to evaluate

Edit the input, then run a decision to see the result.

The model runs in this process: software asks a structured question and gets a typed decision with probabilities.