T11-R2 ecosystem
Guardrail: A check you can fail: schema, cap, and a person for an action that is hard to undo.
Human handoff
NIST AI RMF
OWASP LLM risks
Recording statutes
The voice channel does not remove the tool cap or the person who must approve an action that is hard to undo.
A later test can add a script you wrote. It cannot add a legal conclusion.
Write the goal in one sentence.
Name the input and the allowed output.
Save the trace next to the result.
The answer looks fluent and is wrong. Check whether a source passage actually contains the claim.
The loop never stops. Set a step cap and stop when the tool result repeats.
Sources and go deeper
- OWASP Top 10 for Large Language Model Applications community last checked 2026-10
- NIST AI Risk Management Framework spec last checked 2026-10
- Speech to Speech, docs.x.ai vendor The page title is Speech to Speech. The body names the Grok Speech to Speech API and also calls the site SpaceXSI Docs. last checked 2026-10