System prompts

System prompts let you shape how an AI model responds in the EidoStack Playground. A system prompt is sent before your chat messages and can define a role, response language, tone, output format, or other lasting instructions. Change these instructions to explore model behavior while keeping the actual task in your user prompt.

Set the default instruction for new chats

1. Open workspace settings and select System Prompt.

2. Enter the instruction in Global System Prompt > Default Instruction.
3. Create a new chat when you want that instruction to be inherited.

The global prompt is a starting value for new chats. Updating it does not rewrite the instruction stored in existing chats, so earlier conversations and experiments retain their original setup. Leave it empty when each chat should begin with no shared instruction.

Use clear, specific instructions. For example, ask for a particular JSON structure while providing the task and data in the user prompt. Avoid testing a response format without giving the model enough information to complete the task. Avoid putting secrets, provider keys, or personal data into a system prompt.

Override the instruction for one chat

1. Open the chat.
2. Select Sys Prompt in the prompt toolbar.

3. Edit the text, select Save, and send the next prompt.

The popover labels this as a custom instruction for that chat only. Use Clear to remove the chat-level instruction, then select Save. The character count is informational; EidoStack does not turn it into a quality or token-budget guarantee.

A chat-level system prompt lets one conversation use a different role, response format, or set of rules from your global default. When comparing model responses, keep the instruction consistent unless you intentionally want to test its effect.

Use separate instructions in comparison mode

When Compare is enabled, the toolbar displays Model A and Model B, each with its own Sys Prompt control. You can use these controls in two ways:

• Use the same instruction on both sides to compare model behavior under the same conditions.
• Deliberately give each side a different instruction when evaluating a prompt or instruction strategy.

Document which design you chose before interpreting the result. If Model A and Model B receive different system prompts, the outcome is a combined model-and-instruction comparison, not a model-only comparison.

Keep prompts maintainable

Put reusable instructions in the global default, chat-specific guidance in the chat-level prompt, and the immediate task in the composer. This separation helps you reuse prompts and understand which instruction changed when a model gives a different response.

System prompts are sent to the selected provider as part of the model request. Review the data before sending it and use only information that you are authorized to share with that provider. Pair the instruction with the appropriate Context memory strategy when the task also depends on earlier conversation turns.