ULUOPS

Research

How the infrastructure works

The ideas behind UluOps — six core innovations that make AI judgment observable, persistent, and self-improving.

01

Recursive Appreciation

Agents audit agents. A prompt engineering agent can audit its own definition, find real issues, and improve. Improvements to meta-layer agents cascade through every domain-layer agent they evaluate.

02

Cognitive Parallax

The same artifact examined through multiple epistemological traditions reveals structural properties invisible from any single perspective. Aristotelian, Popperian, Humean, and Confucian lenses produce triangulation signal no individual framework can generate.

03

Composition Lift

Workflow compositions of multiple agents produce synthesis scores above the average of their component scores. Compositions are first-class evaluation units with their own emergent epistemic behaviors.

04

Cross-Model Triangulation

Content-based fingerprinting means the same issue produces the same identity regardless of which model surfaced it. High cross-model agreement carries stronger evidential weight than single-model recurrence.

05

Immutable Forensics

Every validation run is a permanent, unalterable record. This creates the scientific discipline of measurement: measurable, reproducible, and improvable through empirical observation over time.

06

Domain Portability

The infrastructure remains constant; only the definitions change. The same agents, workflows, and measurement apparatus work across software, security, prompts, ML pipelines, and beyond.

Evidence

What the data shows

135+

Agent definitions

33

Cognitive lens agents

2–4

Cycles to convergence

7+

Domains validated

Structural inheritance raises new agent baselines by 10–15 points before any domain-specific tuning.

Agents typically converge in 2–4 recursive audit cycles, suggesting a structural ceiling rather than infinite improvement.

Proven across software engineering, security, prompt design, ML pipelines, patent analysis, and philosophical inquiry.

Open Questions

What we're still learning

Convergence theory

Under what conditions does recursive self-evaluation converge, and at what structural ceiling? Is the limit Godelian, or artifact-specific?

Meta-learning

Can the system learn which agents to create? What are the optimal structures for recursive improvement and automated domain adaptation?

Cross-paradigm synergies

Which philosophical and analytical frameworks compose productively? Are there emergent properties at certain composition depths?

See the infrastructure in action

Explore the documentation, browse the agent catalog, or start building.