Practical AI · Thursday, October 29, 2026
Heidi Porter highlighted a peer-reviewed study of a rubber hose production line where a modified vision model detects defects without an LLM. An LLM is subsequently used only to draft candidate explanations and corrective actions based on retrieved maintenance history, accompanied by rule-based guardrails to ensure output stays within evidence.
“This is a published peer-reviewed study... of a rubber hose production line. And so a camera watches the line and a modified you only look once vision model finds the defects.”
“They use rule-based checks, traditional programming, to check whether the draft stayed within the evidence that it pulled.”