ads-decision-flow
CommunityRoute dual-brain decisions with guardrails.
Software Engineering#auditability#HITL escalation#routing decision#adaptive decision system#dual brain#policy firewall#administrative automation
Authorwagnerra23
Version1.0.0
Installs0
System Documentation
What problem does it solve?
It prevents inconsistent or unsafe automated actions by enforcing a single, auditable dual-brain decision flow for administrative operations.
Core Features & Use Cases
- Unified Adaptive Decision System: orchestrates Risk → Confidence → Policy (firewall) → Router → Dual-Brain (Brain A/B) → optional HITL outcomes.
- PolicyEngine Safety Firewall: guarantees the correct precedence of BLOCK_ALWAYS, REQUIRE_HUMAN_REVIEW, REQUIRE_BRAIN_B, and ALLOW_BRAIN_A so automation never bypasses governance.
- Deployment-accurate Runtime Mapping: ensures Brain A runs on CT 100 while Brain B runs via Hostinger/Anthropic, and routes actions through the approved FsmActionBridge rather than shortcuts.
- Decision Auditability & Learning Loop: records outcomes into decision-memory tables to support priors/pattern learning over time.
Quick Start
Ask the AI to handle an ADS admin routing event in Modules/ADS by running through the PolicyEngine firewall and producing a RoutingDecision with the correct HITL level and Brain A/B path.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: ads-decision-flow Download link: https://github.com/wagnerra23/oimpresso.com/archive/main.zip#ads-decision-flow Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.