METRICRM
FeaturesAIPricingResources
//
Talk to us
METRICRM
ProductPricingFeaturesAIIntegrations
ResourcesUser GuideContact
LegalTerms of ServicePrivacy NoticePDPA NoticeData Processing AgreementCookie Policy
© 2026 Webbalances Solution (003096168-D). All rights reserved.Version 4.48.0
All guidesMetriAgentBuild an AI agent in Agent StudioTools, autonomy levels and guardrailsTest an agent in the simulatorPublish, roll out, roll back and stop agentsPut an AI agent on website chat and messaging appsLet AI agents answer email and portal casesApprove, reject and undo AI actions
User Guide › MetriAgent

Test an agent in the simulator

Chat with an agent as a customer and see each step it takes — nothing is sent or changed.

For: Admins

Steps

  1. 1Open the agent and use Try it on the right, or select Test simulator for the full view.
  2. 2Choose the language (or let the agent detect it), the version to test — the saved draft or a published version — and, optionally, a contact to test as. Order and invoice look-ups only find that contact's own records.
  3. 3Type as the customer. The reply shows its cited articles and whether it would be sent automatically or wait for a person's approval.
  4. 4Read the step-by-step trace: the intent and language detected with confidence and mood, the knowledge articles found, each tool call with its inputs and outputs, every autonomy check with its reasons, and the response.
  5. 5Ask for a person, change topic or write angrily to check the handover rules. Select New conversation to start again.

Good to know

  • Test mode never sends messages or changes records: actions show what would have happened.
  • Personal details are replaced with placeholders such as [PHONE_1] before anything reaches the AI model; the trace shows them that way.
  • Simulator conversations use your AI credits like other AI features.

Related guides

  • Build an AI agent in Agent StudioCreate an AI agent from a template and set its role, languages, greeting, instructions, topics and knowledge.
  • Tools, autonomy levels and guardrailsChoose what an agent may do, how much it may do on its own, and the limits that keep it safe.
  • Publish, roll out, roll back and stop agentsPublish the draft as a version, try it on a share of conversations, go back instantly and stop agents with a kill switch.
  • Put an AI agent on website chat and messaging appsLet a published agent answer customers on your website chat, WhatsApp and other messaging apps, and hand over to your team when it should.

Still need help? Contact support

On this pageStepsGood to knowRelated guides