Corint home

Agentic decision engine.
Production-ready
execution.

A decision engine built for AI agents. Execute approved risk strategies with deterministic results, reason codes, and traceable decision records.

PERFORMANCE, IN CONTEXT

Built for the critical path.
Measured on your workload.

A Rust execution core designed for fast decisions. Start with the published figures, then validate your rules, data dependencies, and deployment.

TAIL LATENCY
<ms

p99 rule-evaluation latency

For pure rule evaluation. The original website presents this as a target—not an end-to-end response-time guarantee.

THROUGHPUT
+

decisions / second / instance

Published in the engine README. Hardware, workload, and test methodology are not specified alongside the figure.

Efficient by design

Rust runtime, cached features, and short-circuit rule evaluation.

Scale the deployment

Distribute traffic across isolated instances. Validate shared-state behavior.

Plan for failure

Configure health checks, failover, and recovery. Test before production.

Corint Definition Language

CDL describes real risk operations,
not just simple rules.

CDL is the common language between risk teams, engineers, Corint Decision, and Corint Work. It covers the full online decision workflow, while staying structured enough for AI-assisted generation and optimization.

End-to-end risk logic

CDL defines rules, rulesets, pipelines, registry routing, features, lists, API calls, and final decision mapping in one model.

Built for real production flows

It can represent login, payment, KYC, credit, AML, review routing, service calls, and feature-backed online decisions.

More than a simple DSL executor

Unlike lightweight rule DSLs, CDL separates detection, signal generation, orchestration, context, and actions for complete risk workflows.

LLM-friendly by design

The declarative structure is readable enough for analysts and structured enough for LLMs to generate, modify, and explain safely.

Works with Corint Work

Corint Work can analyze outcomes, propose CDL changes, optimize thresholds, and prepare strategy updates for review.

Reviewable and auditable

Strategies stay in plain YAML, so teams can diff, approve, version, test, and deploy changes through controlled workflows.

Three-layer architecture

Rules detect. Rulesets signal. Pipelines decide.

Corint Decision separates detection, signal generation, and orchestration so strategies stay reusable, explainable, and easy to operate through code review and version control.

1

Rules

Pattern detectors

Atomic risk logic units detect individual patterns and produce scores without deciding final actions.

2

Rulesets

Signal generators

Rulesets combine rule results, aggregate scores, and produce approve, decline, review, hold, or pass signals.

3

Pipelines

Decision orchestrators

Pipelines route events, call APIs and services, execute rulesets, and map signals to final results and actions.

Runtime and operations

From a strategy file to a running decision.

The project is organized as a Rust workspace that covers parsing, compilation, execution, repository loading, server integration, and API-facing decision execution.

Rust runtime

Built as a Rust workspace with core, parser, compiler, runtime, SDK, server, repository, FFI, and LLM modules.

Production APIs

Expose decision execution through HTTP and gRPC server layers with health checks, tracing, CORS, and config loading.

Repository driven

Load CDL assets from a Git-friendly filesystem repository or PostgreSQL-backed repository with versioning patterns.

Hot reload path

Reload rules and configuration without rebuilding application code, enabling controlled strategy operations.

Features, lists, APIs

Bring risk context into every decision.

Corint Decision combines request fields with computed features, reusable policy assets, and API responses before pipelines produce final actions and auditable evidence.

Real-time feature context

Calculate aggregation, expression, lookup, and datasource-backed features before rules run, so every decision has current risk context.

Reusable policy assets

Manage blocklists, allowlists, sanctions data, VIP users, countries, IPs, emails, and other risk assets as governed strategy inputs.

APIs with explainability

Call internal or external services during pipelines, then return matched rules, scores, reason codes, traces, and processing time for audit.

Integrations

Built for online risk systems.

Event routing

Registry files route login, payment, registration, transaction, or custom events to the right pipeline.

API and service calls

Pipeline steps can call configured external APIs, internal HTTP or gRPC services, and message queues.

Feature stores

Look up online features from Redis or other configured stores and combine them with event context.

Audit persistence

Decision results can be persisted for later audit, analysis, debugging, and model or strategy review.

Put your approved strategy to work.