> ## Documentation Index
> Fetch the complete documentation index at: https://docs.getnexor.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Test in the playground
The playground, also called **Chat in Nexor**, is where you live the experience before any lead does. You talk to the agent exactly as a lead would, see what it says, and fix what you do not like. In onboarding calls, this is the moment the customer takes the keyboard. Do the same: run your own scenarios, not just a hello.
## Open it
Open the playground from the agent's page. The agent replies using its current configuration: goal, identity, business rules, variables, pipeline, and knowledge base.
Everything here is simulated. No lead is created, no message reaches a real contact, and live conversations are not affected.
## Run your real scenarios
Test the cases you wrote in your [worksheet](/docs/en/guides/getting-started/define-your-use-case), plus the ones every agent must survive:
| Scenario | Play the lead who... | Check that the agent... |
| ------------------ | -------------------------------------------------- | ---------------------------------------------------------------------------- |
| Happy path | Fits your criteria and cooperates. | Collects every required variable and reaches the winning stage. |
| Objection | Says it is too expensive, or not now. | Uses the objection handling you wrote and does not cave or invent discounts. |
| Off-topic | Asks something unrelated to your business. | Redirects politely without making things up. |
| Wrong fit | Clearly fails your qualification criteria. | Discards or closes without pushing. |
| Wants a person | Asks to talk to a human. | Escalates the way you defined and captures what the team needs. |
| Knowledge question | Asks a detail that lives in your files or website. | Answers from the knowledge base, or says it does not know. |
## Propose a change and see it applied
The most useful minute in any onboarding is when the customer says "I would like it to do X instead," and watches the configuration change. Do it yourself:
For example, the agent asked for the budget before explaining what the product does.
Open the NexorGPT panel or page and describe it: "Explain the product in one line before asking for budget." Confirm the before/after card.
Click **Train your agent** and wait for training to finish. The playground uses the prompt from the last completed training, so an untrained edit is invisible here.
Repeat the exact scenario and confirm the new behavior. If it is still off, refine the wording of the matching business rules section rather than adding a new rule elsewhere.
Change one thing at a time between tests. When two edits go in together and the result is wrong, you cannot tell which one caused it.
## Test on WhatsApp before connecting a number
Eligible accounts can open **Test my agent**, scan a QR code, and talk to the agent from their own WhatsApp. The session stays isolated and does not contact real leads. Use it to feel the timing and formatting of real messages.
## Test connected agents
If you have built several agents that transfer leads between them, start the conversation with the first agent and drive it toward the transfer condition. Confirm that the next agent picks up with the conversation history and the fields you chose to copy. See [Connected agents](/docs/en/guides/getting-started/connected-agents).
## What "done" looks like
You are ready to move on when:
* every scenario in the table above behaves the way you expect;
* you have made at least one change from NexorGPT and seen it take effect after training; and
* you can tell, for any wrong answer, which block of the agent you would edit.
## Next
Go to [Operation and channels](/docs/en/guides/getting-started/operate-and-connect-channels) to decide when the agent reaches out and where.