---
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


---

# Test execution manually

# Manually test the execution of an agentic workflow {#ariaid-title1}

* Versão de lançamento: Australia
* 
* Atualizado 12 de mar. de 2026
* 
* ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 3 min. de leitura

Test your agentic workflow in AI Agent Studio to analyze how it functions while it executes the instructions that you defined.

## Antes de Iniciar

Role required: sn_aia_admin and either admin or at least one role required by the ACL of the agentic workflow being testing and each of the ACLs of its downstream components

## Por Que e Quando Desempenhar Esta Tarefa

After you create an agentic workflow, test it to see that it functions the way that you defined it. You can choose to run a manual test with a single instruction to test its basic functioning, or you can evaluate the AI agent's performance across multiple executions.

If you want to test multiple executions using execution logs, you can run an automated test. If you select Start automated evaluation, the agentic evaluation guided setup opens in a new browser tab. See [Evaluate an agentic workflow](https://servicenow-prod.fluidtopics.net/he2kFV6WLQwi6a4v1pckPQ "Evaluate agentic workflow and AI agents against datasets of your choice to monitor performance and evaluate against different benchmarks.") for more details about running a new automated evaluation.

When manually testing performance, you can see how the agentic workflow and its AI agents interact with the AI Agent Orchestrator and the Communicator AI agent. The Orchestration is an agent that directs different AI agents, and the Communicator AI agent facilitates the communication between the user and other AI agents.

## Procedimento

1. Navigate to AllAI Agent StudioTesting.
2. On the Test scenario tab, in the What to test section, select the Agentic workflow radio button.
3. Select Start manual test.  
   If you want to start an automated test, see [Evaluate an agentic workflow](https://servicenow-prod.fluidtopics.net/he2kFV6WLQwi6a4v1pckPQ "Evaluate agentic workflow and AI agents against datasets of your choice to monitor performance and evaluate against different benchmarks.") for more details on that process.
4. In the Test type drop-down menu, select AI agent or workflow.  
   If you want to test user access security controls, see [Test agentic workflow user access](https://servicenow-prod.fluidtopics.net/13jupdcMe~lx_XSHZwi6bg "Run a manual test to verify that only the users you want to access the agentic workflow can do so.").
5. Select an agentic workflow that you want to test by entering the name of a workflow or choosing from the drop-down menu.
6. In the Version drop-down list, select the version of the AI agent you want to test.  
   See [Version control for AI agents and agentic workflows](https://servicenow-prod.fluidtopics.net/uX9YniUtT4~UUtGCazrzfQ "Version control enables you to track changes made to instructions sent to the LLM for AI agents and agentic workflows.") for more information about creating and changing versions.


7. In the Task drop-down list, provide a concise summary of the task to be achieved.  
   Nota:  
   In the task summary, include a reference number for a specific record for better results during your testing.


8. Select Start test.  
   You're directed to the Output tab, where you see Now Assist executing the operations to test your agentic workflow.
9. Select Continue to Test Chat Response.

## Resultado

When testing an agentic workflow, you can see the AI Agent Orchestrator and AI Agent Communicator working together to organize and manage the AI agents like a team. The AI agent Orchestrator assigns the individual,
specialized agents to complete the subtasks. The AI Agent Communicator lets the AI Agent Orchestrator know the status of each agent.  
Nota:  
If you don't have the roles necessary to pass the ACLs of the agentic workflow and all of its AI agents and tools, you're notified that you don't have the necessary access and the test won't execute.

Your AI agents start to execute the test autonomously to resolve the agentic workflow by taking the input from the live agent as required.  
Figura 1. Testing an agentic workflow Figura 2. Testing an agentic workflow

* A simulated chat experience begins on the Now Assist panel between your invoking user and AI agent.
* At the top of the canvas, you can see information about the agentic workflow you're testing, including its name, version, and description.
* A diagram shows the tasks and communication of the AI agents that are working together to solve the case.
* A decision log records the thought process of each AI agent that is involved in solving the agentic workflow.  
  Nota:  
  You can view the entire decision log by selecting Download logs.

{#test-aia-use-case__ul_dc4_bdb_m2c}

You can restart the entire testing process at any time by selecting Restart.