SmartDecision turns written policies like pricing, eligibility, and fraud thresholds into decision tables your team can read and edit in plain English. Apps resolve them over an API in milliseconds, and it all runs on a single self-hosted binary with a local LLM. Nothing leaves your network.
Early access is rolling out in small batches. No spam, one email when it's your turn.
One rule, three forms: the plain-English policy your team writes, the decision table it becomes, and the API your apps call.
“A loan is approved if credit score is 700 or higher, age is between 21 and 65, and income is at least €10,000. Scores from 650 to 699 go to manual review.”
| credit_score | age | income | decision |
|---|---|---|---|
| >= 700 | 21...65 | >= 10000 | approved |
| 650...699 | 21...65 | >= 10000 | review |
| * | * | * | rejected |
POST /api/resolve/214
credit_score = 712
age = 34
income = 18000{ "decision": "approved" }
Every growing application accumulates hundreds of hidden decisions: pricing rules, eligibility checks, fraud
thresholds, approval workflows. They start as simple if statements and end as deeply nested
logic nobody wants to touch: hard to test, risky to change, impossible for non-engineers to read.
SmartDecision pulls those decisions out of the codebase and into decision tables: a format business teams can read, engineers can test, and applications can call.
Write the rule the way you'd explain it to a colleague. SmartDecision's local LLM converts it into a structured decision table with inputs, outputs, and rules you can inspect and edit by hand.
New decision
Decision policy
A loan is approved if credit score is 700 or higher, age is between 21 and 65, and income is at least €10,000. Scores from 650 to 699 go to manual review.
The prompt should be a clear and comprehensive statement of the decision policy.
Pin expected outcomes as decision tests. Run them against the table before anything ships, so a rule change never silently breaks an edge case.
| Test input | Expected output | Updated | Actions |
|---|---|---|---|
| credit_score = 700 | approved | now | |
| credit_score = 699 | rejected | now |
Applications send inputs to one REST endpoint, authenticated with an API key, and get the evaluated result back in milliseconds. Evaluation is deterministic rule-matching; the LLM only drafts tables, it never sits in the request path.
Resolve API
const formData = new FormData();
formData.append("credit_score", "712");
fetch("https://bi.smartdecision.io/api/resolve/214", {
method: "POST",
headers: {
Authorization: "HV3g…LqU5",
},
body: formData,
});Important: the resolve API key is a secret that should be kept confidential. Share it only with trusted parties.
cp.POST /api/resolve/:id with an API key. Works from any language that can make an HTTP request.Discounts, promotions, regional pricing, tier thresholds. Adjusted by the people who own the policy.
Who can access a feature, upgrade a plan, or apply for a service. Defined once, resolved everywhere.
Thresholds and transaction policies evaluated locally, without exposing sensitive data to anyone.
Gate features by user attributes, regions, or experiments without redeploying the application.
Everything runs inside your infrastructure: the rule engine, the web console, and the LLM. Credit scores, transaction amounts, eligibility inputs: none of it ever crosses your network boundary, at authoring time or at resolution time. If your compliance team's first question is “where does the data go?”, the answer is nowhere.
SmartDecision is rolling out to a small group of early users. Leave your email and we'll reserve your spot.
Early access is rolling out in small batches. No spam, one email when it's your turn.