Run your prompts with automatic tool calls in Playground
Adaline’s Playground offers a safe sandbox environment to test how your LLM interacts with tools.
If your tools are configured with request object, Playground will automatically invoke the tools and continue the conversation with the tool’s response.
When the LLM determines it needs external data, it generates a tool call request that appears as a distinct content block in the conversation flow. The tool call is given via the Assistant message.The tool call shows:
Name of the tool being called
Id of this tool call to track the tool call response
Required parameters and their values to be passed to the tool
If the tool is configured with request object, Playground will automatically invoke the tool and continue the conversation with the tool’s response.
Playground will invoke the tool’s request endpoint using the configured HTTP method (GET or POST), headers and pass the LLM’s requested arguments to the tool as query parameters or request body.
The tool’s response is then added to the conversation as a Tool message.Refer to Tool Request Structure on how to configure the tool with request object.If the tool is not configured with request object, you can manually add the tool call response to continue the conversation.
Follow these steps to manually implement the Tool Calling response:
1
Execute Your Prompt
Run your prompt in the Playground as you normally would.
2
Identify Tool Call Triggers
Monitor the conversation for tool call messages. These appear when your prompt logic determines that external data is needed to complete the user’s request.
3
Simulate Tool Response
Click the “Add Response” button to provide simulated data:
Enter response data in the format your tool would return.
Use realistic sample data that represents actual tool outputs.
4
Execute the prompt to completion
Click on the Run button to get the final output from the LLM.