---
title: Cleanlab (NeMo Guardrail)
type: guardrail
provider: nvidia
category: safety
source: 'https://github.com/NVIDIA-NeMo/Guardrails'
license: Apache-2.0
tags:
  - guardrail
  - nemo
  - rails
  - colang
dateAdded: '2026-04-17'
featured: false
origin: official
language: en
description: >-
  """ https://cleanlab.ai/tlm/ https://help.cleanlab.ai/tutorials/tlm/
  how-does-the-tlm-trustworthiness-score-work """ flow cleanlab trustworthiness
  """
---

```coffee
"""
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"
```