sb-decision

The SB Decision Model, by Sarathi Balakrishnan. Give it a text and your own list of options, each written as name: when to choose it, and it returns a calibrated probability per option in one pass. Nothing is retrained per use case: the option definitions are the policy. A reserved ask option is trained to win when the deciding fact is missing from the text, so irreversible actions go to a person instead of being guessed.

Not an LLM. It never generates text. It is the router, guardrail, or triage layer in front of one.

Install

pip install sb-decision

Use

from sb_decision import SBDecision

m = SBDecision.load()  # sarathi-balakrishnan/browser-decision-model-base
m.decide(
    "Package arrived broken, second time this month. I want a manager.",
    [
        "refund: customer wants money back for a damaged, wrong, or missing item",
        "replace: customer wants the product again",
        "escalate: angry, threatens to leave, or asks for a manager",
    ],
)
# {'decision': 'escalate', 'band': 'auto', 'scores': {'escalate': 0.90, 'ask': 0.09, 'refund': 0.01, 'replace': 0.01}}

band is auto when the top score is at or above auto=0.7, review at or above review=0.4, otherwise abstain. If ask wins it is always abstain. Both thresholds are arguments; they are statements about the error rate you accept, not model constants.

Independent tags, when several options can apply at once:

m.decide(
    "Headache since morning and now my chest feels tight.",
    ["headache: pain in the head", "chest pain: pressure or tightness in the chest", "rash: skin redness or itching"],
    mode="multi",
)
# {'decision': 'chest pain', 'band': 'auto', 'tags': ['headache', 'chest pain'],
#  'scores': {'chest pain': 0.76, 'headache': 0.61, 'ask': 0.14, 'rash': 0.0}}

Many texts at once: m.scores_many(texts, options). Command line:

sb-decision "It doesn't work on my machine." -o "crash: the app exits or hangs" -o "slow: works but takes too long" -o "question: asks how to do something"

JavaScript, React or Node

The same API ships on npm as sb-decision (browser on WebGPU or WASM, and Node):

import { SBDecision } from "sb-decision";

const m = await SBDecision.load();
const r = await m.decide("Package arrived broken, second time this month. I want a manager.", [
  "refund: customer wants money back for a damaged, wrong, or missing item",
  "replace: customer wants the product again",
  "escalate: angry, threatens to leave, or asks for a manager",
]);
// { decision: "escalate", band: "auto", scores: { escalate: 0.9, ask: 0.09, refund: 0.01, replace: 0.01 } }

React and Node examples are in the npm package README: https://www.npmjs.com/package/sb-decision

Access

Package and weights are public; no token is needed. SBDecision.load() raises SBAccessError with what to check if the weights cannot be reached. Questions and use cases: Sarathi Balakrishnan at https://huggingface.co/sarathi-balakrishnan .

Writing options

• One line per option, saying when to choose it, with the boundary to its neighbours explicit.
• Describe what the text says, not what you will do about it. "chest pressure with sweating or arm tingling" scores; "tell the caller to call 911" does not.
• Keep ask in the list whenever the action is irreversible.
• Up to 12 options, 1,024 tokens, English. It decides from the text, not the world: no lookups, no arithmetic.

Results

Measured on 4,745 messages from five domains never seen in training or validation.

The teacher's own self-agreement on the same messages is 0.883.

License

Apache-2.0. See NOTICE.