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({ token: HF_TOKEN });
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

The package is public; the weights are in private preview. SBDecision.load() raises SBAccessError with contact details if your Hugging Face token does not have access. To try it on your own option set, contact 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.