Enables AI assistants to make typed yes/no or multiple-choice decisions by evaluating plain-language rules from a YAML file or one-off questions against supplied context, returning probabilities and confidence scores with an uncertain flag near thresholds.
Deterministic policy enforcement for AI agent tool calls. It evaluates every tool call against user-defined rules before execution, with no LLM in the authorization path.
Enables deterministic rule-engine decisions with document-grounded explanations, along with inspection, drafting, validation, publishing, and management of domain rules, policy documents, and decision quotas.
Enables agents to route every action through a pre-execution gate that returns allow, escalate-to-human, or deny verdicts, backed by deterministic hard-rule blocks plus probabilistic gray-zone scoring, and to run a resumable orchestration loop covering routing, quality gates, stop-loss, acceptance, and escalation. Every decision, arbitration between conflicting agents, and human approval is written to an append-only hash-chained, Ed25519-signed ledger that can be postmortemed, calibrated, alert-scanned, and exported as offline verification bundles or OTel spans.
