---
sourceDocument: Australia Enable AI
sourceDocumentLink: https://servicenow-prod.fluidtopics.net/r/pt-BR/intelligent-experiences

 Release :

    - australia

ft:locale :

    - pt-BR

ft:publication_title :

    - Australia Enable AI

ft:clusterId :

    - platai

bundleId :

    - platai

workflow :

    - Platform


---

# Evaluate a prompt

# Evaluate a prompt {#ariaid-title1}

* Versão de lançamento: Australia
* 
* Atualizado 12 de mar. de 2026
* 
* ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 2 min. de leitura

Use the Now Assist Skill Kit evaluation tools to evaluate the effectiveness of your skill prompts.

## Antes de Iniciar

Role required: sn_skill_builder.admin

## Procedimento

1. Navigate to AllNow Assist Skill KitHome.
2. Select the skill that you want to evaluate.
3. Select the Prompt performance tab.
4. Select the Evaluation runs tab.
5. Create a dataset from a table or data collection.  
   {#evaluate-prompt__table_iv4_kcz_ddc__entry__2}

   | Method | Steps |
   |-|-|
   | Create a dataset from a table | 1. Give the dataset a name and description. 2. Select Table. 3. Find the table that you want to use. 4. Select the maximum number of records that you want to use. 5. Add conditions. 6. Select Generate Preview. 7. Select the mappings. 8. Select Create. {#evaluate-prompt__ol_elt_nyv_2dc} |
   | Create a dataset from a data collection | 1. Give the dataset a name and description. 2. Select Data Collection. 3. Select a data collection that you created in Now Assist Data Kit. 4. Select Generate Preview. 5. Select the mappings. 6. Select Create. {#evaluate-prompt__ol_htq_zyv_2dc} |
   [Tabela 1. Create a data set]

   {#evaluate-prompt__table_iv4_kcz_ddc}
6. Select the add icon ![add icon]() for Evaluation Runs.
7. Give the evaluation run a name and description.
8. Select one or more prompts that you want to evaluate.
9. Select Save \& Next.
10. Select a dataset.
11. Select Save \& Next.
12. Expand the Quality tab.
13. Select the metrics that you want to evaluate.  
    {#evaluate-prompt__table_oqq_1mv_ddc__entry__3}

    | Evaluation method | Metric | Description |
    |-|-|-|
    | Human | Human Feedback | Human evaluation is the default option available for all prompt executions that generate a response. You can rate the response with a thumbs up or thumbs down, based on your satisfaction. You also have the option to provide more detailed feedback to explain your evaluation choice. |
    | Automated | Correctness | The correctness metric assesses the generated response's accuracy, completeness, pertinence, and writing quality relative to the given instruction. This metric helps to check that the text accurately reflects the instruction, covers all important points, remains relevant, and is well written. |
    | Automated | Correctness with Golden Response | The correctness with golden response metric uses a predefined reference to assess the generated response's accuracy, completeness, pertinence, and writing quality relative to the given instruction. This metric helps to check that the text accurately reflects the instruction, covers all important points, remains relevant, and is well written. You should use this metric whenever possible. |
    | Automated | Faithfulness | The faithfulness metric assesses whether a generated response accurately reflects the information and context provided in the given instruction. This metric helps to check that the text contains no hallucinations, fabricated facts, or unsupported conclusions, maintaining alignment with the source material. |
    [Tabela 2. Evaluation metrics]

    {#evaluate-prompt__table_oqq_1mv_ddc}
14. Select Save \& Next.
15. Review the evaluation choices that you made.
16. Select Save \& Evaluate.
17. **Opcional:** Give a human evaluation.
    1. Select Human evaluation.
    2. Select a record to use in the evaluation.
    3. Expand the prompt and read the result.
    4. Select the thumbs up or thumbs down icon ![human evaluation thumbs up or thumbs down icon]() to give your evaluation.
    5. Add more information and select Submit.
    {#evaluate-prompt__substeps_xqy_st3_gdc}
**Tarefas relacionadas**   

* [Create a skill](https://servicenow-prod.fluidtopics.net/Af8ZD_06zyFT4wcox4v0EA "Create a custom skill for Now Assist. Creating a custom skill enables you to have greater flexibility with Now Assist's generative AI capabilities.")
* [Create a prompt](https://servicenow-prod.fluidtopics.net/3K4Mw7oWnde16Gb5hkIQ~Q "After you create a custom skill, create a prompt. Creating a prompt enables you to choose what skill inputs to use, as well as the type of tool.")
* [Use prompt assistance](https://servicenow-prod.fluidtopics.net/ZZm5cCoA76wpRoLwhiC~5w "Use prompt assistance to get a jump start with your prompt development by selecting an example from the prompt library or using Now Assist to generate one.")
* [Test a prompt](https://servicenow-prod.fluidtopics.net/9qkmGmprM967_h3JofOULg "After you create a prompt for your custom skill, test the prompt template before you finalize it. Testing the prompt verifies that you’re seeing the expected prompt results before it’s activated.")
* [Finalize and publish a skill](https://servicenow-prod.fluidtopics.net/4CCY98KqcGKnQezZsLF_Yw "When you’re satisfied with your prompt, you can publish your custom skill. Publishing the skill enables a Now Assist admin to activate it.")
* [Activate a skill](https://servicenow-prod.fluidtopics.net/oZJjIVP1LalfAgGuUV_d2A "After you create and publish a custom skill, you must activate it in Now Assist Admin. Activating the skill enables you to trigger the skill within the UI.")
* [Call a custom skill from a script](https://servicenow-prod.fluidtopics.net/vTL_nmhQexkQrnOCiMkq_Q "You can use a script to call a custom skill.")