Mechanical Governance for LLM Decisions — model-agnostic governance regimes (R1/R2/R3), hard gates, entropy commit-reveal and governance metrics for high-stakes LLM decision systems.
An open-source AI reasoning framework that uses dialectics, semantic graphs, and polarity management to drive LLMs toward objective synthesis and advanced human-AI collaborative decision-making.
A long-form article introducing the Twin Test: a practical standard for high-stakes machine learning where models must show nearest “twin” examples, neighborhood tightness, mixed-vs-homogeneous evidence, and “no reliable twins” abstention. Argues similarity and evidence packets beat probability scores for trust and safety.
A long-form article and practical framework for designing machine learning systems that warn instead of decide. Covers regimes vs decimals, levers over labels, reversible alerts, anti-coercion UI patterns, auditability, and the “Warning Card” template, so ML preserves human agency while staying useful under uncertainty.
MIDAS is an open platform for governing execution authority at decision surfaces across agents, AI systems, and enterprise workflows.
Agent skills for designing, training, evaluating and improving application-specific decision systems. Primitive/model selection, data assembly, export/reload and bounded hill climbing. TypeSafe Jev is the default hosted exemplar; independent of TypeSafe.
Longform article reframing abstention (reject option / selective prediction) as product design, not model weakness. Covers coverage as a KPI, calibration as a prerequisite, threshold selection under review capacity and risk, queue/UX design for human-in-the-loop workflows, and anti-patterns that break safety in production.
Defines the decision layer for AI systems where deployment outcomes are governed, recorded, and reconstructable. 5th conforming implementation of draft-farley-acta-signed-receipts (IETF).
Decision Infrastructure System is an experimental platform for evaluating the governability of AI-enabled systems. It measures whether AI workflows remain influenceable, explainable, and correctable throughout execution using a presentation-driven architecture and deterministic assessment pipeline.
Multi-agent DAG with fitted intent and sentiment classifiers in front of a deterministic, auditable policy layer, plus event-driven proactive outreach.
Defines the Selection Layer — the decision system through which AI models determine visibility, inclusion, and recommendation.
Deterministic governance system for AI-driven marketing that separates diagnostics, human reasoning, and execution into strictly controlled layers.
Event-driven NLP governance architecture using FastStream, Redpanda, and PostgreSQL with auditability, human-in-the-loop control, and ethical safeguards.
Computational framework for Constraint-Driven Stability with scientific toy models and applied AI decision surfaces.
Product briefs for AI/deterministic systems that make consequential decisions on unstructured input in regulated environments — research data, health, finance. Each project states the decision, the constraints, the metric, and the human escalation path.
Turn-based control architectures
CFS (Cognitive Flow System) — a causal influence framework for modeling how decisions emerge in complex systems through structured causal constraints. DOI: https://doi.org/10.5281/zenodo.19142077 DOI: https://doi.org/10.5281/zenodo.19103972
Open-source framework for Decision Traces in complex decision systems. Providing a verifiable audit trail for observable, explainable, and humane choices in software and agentic engineering
Governed AI-assisted decision workflow for regulatory authoring with validation, review orchestration, and auditability
Control-plane architecture for AI & agentic systems: governance as admission control, decision admissibility, and audit-grade evidence.
To associate your repository with the decision-systems topic, visit your repo's landing page and select "manage topics."