GreenPT Docs

Playground

Test your agents before deploying to visitors.

The Playground is your testing environment for agents. Use it to verify responses, fine-tune instructions, and ensure your agent is ready before deploying to visitors.

What is the Playground?

The Playground lets you have conversations with your agents exactly as your visitors would, but in a safe testing environment. You can:

  • Test how agents respond to different questions.
  • Verify that knowledge is being used correctly.
  • See source citations and reasoning.
  • Experiment without affecting live visitors.

Using the Playground

Getting started

  1. Navigate to Playground in the sidebar.
  2. Select an agent to test.
  3. Optionally select a channel (to test channel-specific settings).
  4. Start typing questions.

Testing conversations

Ask questions your visitors might ask.

TypeExample questions
Basic info"What are your hours?"
Specific details"Do you have wheelchair access?"
Complex questions"I'm visiting with kids under 5, what do you recommend?"
Edge cases"Can I bring my dog?"
Off-topic"What's the weather like?"

What to look for

CheckWhy it matters
AccuracyIs the information correct?
RelevanceDoes the response answer the question?
ToneDoes it match the personality you set?
SourcesAre the right knowledge paths being used?
LengthIs the response too long or too short?
Edge casesHow does it handle questions it can't answer?

Playground features

Source citations

See which Knowledge Paths the agent used:

  • Click on a response to see sources.
  • Verify the right information was retrieved.
  • Identify missing knowledge.

Thinking process

With compatible models (like GreenR), you can see the agent's reasoning:

  • How it interpreted the question.
  • What information it considered.
  • Why it chose a particular response.

Session management

ActionWhat it does
New SessionStart a fresh conversation.
Clear HistoryRemove current conversation.
Switch AgentTest a different agent.
Switch ChannelTest channel-specific settings.

Testing tips

Start with common questions

Test the questions visitors ask most:

  1. List your top 10 FAQs.
  2. Ask each one in the Playground.
  3. Verify responses are accurate and helpful.
  4. Adjust knowledge or instructions as needed.

Test edge cases

See how your agent handles tricky situations.

ScenarioWhat to test
Unknown topicsQuestions outside your knowledge base.
Ambiguous questions"How much?" (how much for what?).
Multiple questions"What are your hours and prices?"
Follow-up questions"What about weekends?" (after asking about hours).
Complaints"I'm not happy with my experience".

Check personality consistency

Make sure the tone stays consistent:

  • Ask formal questions.
  • Ask casual questions.
  • Ask emotional questions.
  • The personality should remain consistent.

Test knowledge coverage

Verify all your knowledge is accessible:

  • Look at each Knowledge Path you've created.
  • Ask a question that should use that knowledge.
  • Confirm the agent finds and uses it.

Improving based on testing

If responses are wrong

ProblemSolution
Wrong informationUpdate the Knowledge Path with correct info.
Missing informationAdd a new Knowledge Path.
Conflicting answersConsolidate or clarify knowledge.
Outdated contentRefresh URL-based knowledge.

If responses are off-tone

ProblemSolution
Too formalChange personality to "friendly" or "casual".
Too casualChange personality to "professional" or "formal".
Too longAdd instruction: "Keep responses concise".
Too shortAdd instruction: "Provide detailed explanations".

If agent can't answer

ProblemSolution
Topic not coveredAdd relevant Knowledge Path.
Knowledge not assignedAssign the Knowledge Path to the agent.
Question too vagueAgent should ask for clarification (add to instructions).
Intentionally unsupportedAdd instruction to politely decline.

Iterating on your agent

The testing cycle

  1. Test in Playground.
  2. Identify issues.
  3. Update knowledge or instructions.
  4. Test again.
  5. Repeat until satisfied.

When to deploy

Your agent is ready when:

  • Common questions get accurate answers.
  • Edge cases are handled gracefully.
  • Tone matches your brand.
  • Sources are relevant and correct.
  • You're confident in the responses.

Common questions

Is Playground testing visible to visitors?

No! Playground conversations are completely separate. Visitors never see your tests.

Can I share Playground conversations?

Currently, conversations can't be directly shared. Take screenshots or copy text if you need to share with your team.

Why does my agent give different answers to the same question?

AI models have some natural variation. If consistency is important, lower the temperature setting in agent configuration.

How do I test channel-specific settings?

Select the channel in the Playground dropdown. This applies that channel's quick start buttons, welcome messages, and other settings.

Can I test multiple agents at once?

Not in the same session. Open multiple browser tabs to compare agents side by side.

Does Playground count toward my usage?

Playground conversations use the same AI models as live conversations, so they do count toward any usage limits. However, there's no separate limit for testing.

On this page