OpenPrompts
← Back to catalog
NVIDIAGuardrailsSafety & Moderation

Cleanlab (NeMo Guardrail)

""" https://cleanlab.ai/tlm/ https://help.cleanlab.ai/tutorials/tlm/ how-does-the-tlm-trustworthiness-score-work """ flow cleanlab trustworthiness """

"""
https://cleanlab.ai/tlm/

https://help.cleanlab.ai/tutorials/tlm/#how-does-the-tlm-trustworthiness-score-work

"""

flow cleanlab trustworthiness
  """Guardrail based on the trustworthiness score."""
  $result = await CallCleanlabApiAction
  if $result.trustworthiness_score < 0.6
    if $system.config.enable_rails_exceptions
      send CleanlabTrustworthinessRailException(message="Trustworthiness score is below threshold")
    else
      bot response untrustworthy
    abort

flow bot response untrustworthy
  bot say "$bot_message \nCAUTION: THIS ANSWER HAS BEEN FLAGGED AS POTENTIALLY UNTRUSTWORTHY"
Automated safety scan: no suspicious patterns found.

Heuristic text scan aligned to the OWASP Agentic Skills Top 10. How we scan

Provider
NVIDIA
Origin
Official
Type
Guardrails
License
Apache-2.0
Language
English
Added
2026-04-17
#guardrail#nemo#rails#colang