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