Local LLM / Local deployment and operations
Local LLM: Data retention controls
Set retention and deletion rules for prompts, outputs, traces and uploaded documents.
Environment and inputs: Self-hosted inference and retrieval services; gateway, OS and runtime settings require deployment-specific configuration.
When to use it
Treat the model server as a production dependency with an owner and a recovery path. Verify the actual network boundary and running configuration, then retain enough sanitized evidence to explain failures without collecting unnecessary prompt content.
Check the result
Expire test records and verify removal from primary storage and relevant caches.
Save and compare results
Save the test input, configuration and result. Fix the failing boundary, repeat the same test and compare it with the saved working configuration.
Scope and limits
These exercises have not been tested on your systems. Check feature support and configuration names against the installed release and linked documentation.