Why This Exists
Start Here
Why This Exists
AI systems are increasingly embedded into real workflows: code generation, customer support, security review, infrastructure provisioning, internal automation, and multi-agent orchestration.
As their scope expands, teams are noticing something: the same input produces different outputs. Policies appear declared but are bypassed. Agents escalate unexpectedly. Memory changes behavior over time. Guardrails exist, yet failures slip through.
These are usually described as hallucinations, drift, guardrail failure, or agent instability. Those words describe behavior. They do not describe the structure that behavior is executing against.
The Structural Gap
Modern AI systems are layered: inputs, prompts, policies, tools, memory, permissions, adapters, and outputs.
When behavior diverges, the model is often blamed. In practice, many failures emerge from structural conditions: constraints that were never fully specified, authorities layered without clear precedence, boundaries declared but not enforced, references that change silently, scope that expands incrementally, and parallel systems that fail to converge.
AI does not create these conditions. It executes them.
Why This Is Showing Up Now
For years, complex systems relied on human interpretation. When something behaved unexpectedly, a developer stepped in, an operator overrode a decision, a reviewer noticed something felt off, or a team compensated for edge cases.
Small structural inconsistencies were often absorbed by human judgment. As execution becomes increasingly mechanical and autonomous, that buffer disappears. Agents execute. Workflows chain automatically. State persists. Decisions propagate instantly.
Mechanical systems do not absorb ambiguity.
— PENGO
They execute it.
What This Library Does
This reference library defines recurring structural patterns, analytical lenses used to detect them, deterministic tests where applicable, and clear, bounded terminology.
It does not provide policy advice, replace model providers, offer guardrail products, or interpret intent. It names structure.
Why Naming Structure Matters
When something is described as a hallucination, investigation often stops.
When something is described as Non-Deterministic Execution, Constraint Underspecified, Authority Collision, Boundary Leakage, or Convergence Failure, it becomes analyzable. Once analyzable, it becomes measurable. Once measurable, it becomes controllable.
The Goal
AI systems are not behaving unpredictably. They are executing structure.
If structure is ambiguous, behavior will diverge. If authority overlaps, behavior will conflict. If boundaries are unclear, scope will expand.
Clarity begins with naming the structural condition.
Where To Start
Most readers do not begin with patterns or analytical lenses. They begin with a problem.
If you are seeing different outputs from the same input, unexpected escalation, policies that appear declared but fail, agents that behave inconsistently, or systems that drift over time, start with Issues.
Issues describe real-world symptoms in plain language and map them to structural patterns. From there, you can trace the structure.