Skip to main content
The Playground is an admin-only experimentation environment for quickly testing LLM models without saving conversation history. Use for prompt engineering, model comparison, System Instruction validation, etc. Access directly via /playground URL. There’s no separate sidebar link.
Playground Chat mode full screen

Playground Chat mode full screen

Only the admin role can access this. Regular users are redirected to home when accessing /playground.
All Playground conversations are ephemeral. Content disappears when you leave the page; not recorded in chat history or audit logs.

​
Mode Switching

Top tabs offer two modes.

​
Chat Mode

Compose multi-turn conversations to test model responses. Set System Instructions, switch message roles, and edit conversation history.

​
Basic Usage

1

Pick a model

From the model selector dropdown in the right Settings sidebar (click the gear icon), pick a model to test. The user’s default model is auto-selected. If no default is set, manual selection is needed.
2

Set System Instruction (optional)

Expand the System Instructions section at the top and enter a system prompt. Specify the model’s role, constraints, response style, etc.System Instructions area
3

Enter message and run

Type a message in the bottom input and click Run. The model generates a response with real-time streaming.

​
Message Role Management

In Chat mode, you can freely structure each message’s role (User/Assistant).
Entering a message with the User role

User role (1/2)

Entering a message with the Assistant role

Assistant role (2/2)

Useful for few-shot prompting tests. Alternate User and Assistant messages to compose an example dialog, then Run on the final User message.

​
System Instruction

  • Collapsible header for efficient screen space
  • Shows first-line preview when collapsed
  • Edits apply from the next Run (no effect on previous responses)

​
Completions Mode

Test the model’s continuation of a single text input. Focus on pure text generation without conversation structure.
Completions mode

Completions mode

1

Pick a model

Click the model name at the top, then pick a model from the dropdown that opens.
2

Enter starting text

Enter the starting text to complete in the text area.
3

Run

Click Run — the model generates continuation text in real time. Generated text appears appended to the input text.
Completions mode doesn’t use System Instructions. The input text is passed to the model as-is.

​
Common Features

​
Streaming Response

Both modes support real-time streaming via Server-Sent Events (SSE).
  • Response is displayed token by token in real time
  • Click Cancel during generation to stop immediately
  • Text area auto-expands to fit content

​
Model Selection

  • All models enabled in admin settings are available
  • Auto-picks the user’s default model
  • Model name in the dropdown; model ID at the top of the input box

​
Use Cases

Combine System Instruction and few-shot examples to iteratively test optimal prompts. When satisfied, apply the prompt to an Agent or Prompt.
Sequentially test multiple models with the same prompt to compare response quality, speed, and cost. Chat mode’s easy model switching enables fast comparison.
Pre-test System Instructions before applying to agents. Verify consistent responses across various user inputs.
In Completions mode, check text generation quality for document drafts, code snippets, translations, etc.

​
Chat vs. Completions