# Root Cause Analysis

NVIDIA released the Factory Operations Blueprint (FOX), a reference architecture that adds a factory manager agent to existing factory systems and has it coordinate specialist agents for inspection, root-cause analysis and fleet management. Previously, factory teams had to gather evidence across systems, consult specialists and coordinate the next step, which took substantial time and manual querying. FOX's SMT reference example follows an AOI alert through secondary inspection, rework transport in a digital twin and analysis of reflow oven readings, then returns a PDF report with source records and recommended actions.

NVIDIA released the Factory Operations Blueprint (FOX), a reference architecture that adds a factory manager agent to existing factory systems and has it coordinate specialist agents for inspection, root-cause analysis and fleet management. Previously, factory teams had to gather evidence across systems, consult specialists and coordinate the next step, which took substantial time and manual querying. FOX's SMT reference example follows an AOI alert through secondary inspection, rework transport in a digital twin and analysis of reflow oven readings, then returns a PDF report with source records and recommended actions.

Root-cause analysis of steel casting defects and equipment failures has moved its key checks out of prompts and into code. Previously a general-purpose model answered wrong and right with equal confidence, once calling temperatures above 1,300°C physically impossible and recommending a sensor replacement. The system constrains the model with deterministic decision gates, page-level documentation cards and verbatim citation checks, and on one casting raised mentions of the defect location from zero to 16, 11 and 3, while quantification density stayed far below the reference analysis.

Root-cause analysis of steel casting defects and equipment failures has moved its key checks out of prompts and into code. Previously a general-purpose model answered wrong and right with equal confidence, once calling temperatures above 1,300°C physically impossible and recommending a sensor replacement. The system constrains the model with deterministic decision gates, page-level documentation cards and verbatim citation checks, and on one casting raised mentions of the defect location from zero to 16, 11 and 3, while quantification density stayed far below the reference analysis.

SDO, an operator agent for Kubernetes applications, distills each resolved incident into reusable operational memory: parameterized playbooks that record diagnosis and repair steps, non-LLM detectors that decide from cluster state which playbook applies, and an architecture summary that binds playbook roles to the current application. Across 11 open-source microservice applications, SDO cuts resolution time on recurring faults by 52%, with median resolution falling from 584 s to 282 s and tokens from 5.4M to 2.2M; when deploying applications from source, operational memory reduces deployment time and token use by 47.5%.

SDO, an operator agent for Kubernetes applications, distills each resolved incident into reusable operational memory: parameterized playbooks that record diagnosis and repair steps, non-LLM detectors that decide from cluster state which playbook applies, and an architecture summary that binds playbook roles to the current application. Across 11 open-source microservice applications, SDO cuts resolution time on recurring faults by 52%, with median resolution falling from 584 s to 282 s and tokens from 5.4M to 2.2M; when deploying applications from source, operational memory reduces deployment time and token use by 47.5%.