Workbench / Issues

Missing Fallback for Unavailable Information

The task does not declare what the AI should do when required information, sources, tools, fields, or evidence are unavailable.

What This Looks Like

The AI needs a source, field, tool result, file, approval, or piece of evidence to complete the task, but that information is unavailable. The prompt or workflow does not say whether to stop, ask, use a fallback source, mark the field unknown, escalate, or continue with a limitation.

Why It Matters

Unavailable information is normal in real workflows. Without a fallback rule, the AI may guess, hallucinate, skip the missing part, proceed as if the information exists, or stall without explaining what is needed. This makes the output harder to trust and harder to recover.

Structural Signal

A required information path can fail, but the task does not declare a valid fallback state. The issue is not merely that information is missing; it is that the workflow has no governed response to the missing information.

Common Triggers

When to Use This Issue

Use this Issue when required information is unavailable and the AI task or workflow does not define what should happen next.

When Not to Use This Issue

Do not use this Issue when the fallback is declared but the AI ignores it. Do not use it when the information is available but the AI fails to retrieve it.

Category

Coverage & Guidance

Primary Pattern

PAT-0130 — Incomplete Declaration

Declared Patterns

Derived Primary Lenses

Derived Secondary Lenses

Search Intents

Ontology Metadata

Code
ISS-0074
Version
ISS-0074@0.1.0
Ontology release
0.1.0
Updated
2026-05-10T00:00:00Z

History

No public history entries recorded.

View full ontology changelog