Lets you try a deployed chat model in Foundry without writing code, adjusting the system message, temperature, past messages included and maximum response length.
Read more: Microsoft Learn
In the Ultra Transcenders books
Each book explains Chat playground in context, with comparison tables and the common traps.
Terms in this definition
- Agent instructions
System message of an agent defining its role, objectives, tone and boundaries; it also steers, though not deterministically, when tools get called.
- Model temperature
Sampling setting between 0 and 2 controlling how random the output is. Lower values yield focused, repeatable responses and higher ones more creative text; tune this or Top P, but not both.
- Past messages included
Playground control deciding how much earlier conversation travels with each request. A larger number adds context at the cost of extra tokens.
Related terms
- Completions playground
Older Foundry playground where you typed a prompt and got text back, tied to the legacy Completions API and models like gpt-35-turbo-instruct. Use the chat playground with the Responses or Chat Completions API for anything new.