Start your first chat

Your first chat introduces the EidoStack AI Playground. Select a model, enter a prompt, and explore its response. You can use the Playground for everyday questions, coding tasks, and technical discussions, or turn a chat into a repeatable model experiment by reviewing the answer, tokens, and estimated cost.

Before you begin

Make sure the browser vault is unlocked and that the selected provider has a saved API key. You also need at least one enabled model. If either requirement is missing, the prompt area explains what is blocked and offers a path to Providers settings.

If you have not connected a provider yet, follow Configure your first AI provider. If you have already used EidoStack, the main chat route opens your most recent chat; use New Chat when you want a separate conversation or a fresh experiment.

Create a chat and select a model

1. In the left sidebar, select New Chat.

2. In the prompt toolbar, select the current model name.

3. Search for a model or use the provider filters, then select a model that belongs to a provider with a saved key.
4. Optionally select Sys Prompt to add an instruction for this chat, or use Context Memory to choose how earlier messages will be supplied.

New chats inherit your default model, context settings, and global system prompt at the time they are created. Changing a setting in the chat toolbar affects that chat; it does not retroactively alter another chat. For model visibility and selector controls, see Select and manage models.

Send your first prompt

Enter a question or task you want the model to handle. You can ask for an explanation, request help with code, or specify an output format. If you plan to compare models, include clear constraints so you can judge the differences.

For example, ask the model to review a short security policy and identify three risks with practical mitigations. You can then reuse the same prompt with another model to compare its approach.

1. Enter the prompt in the composer.

2. Select the send arrow.

3. Follow the streamed response as it arrives.
4. When the response finishes, read the answer. If you are testing a specific behavior, check it against your requirements before looking at usage metrics.

Use the square stop button while a response is generating if you need to stop it. A partially generated answer can still remain in the conversation. If a request fails, EidoStack presents the error in the chat with a Try again action for the same request.

Inspect the result

Responses render as formatted Markdown, and the hover controls let you copy a message. The metadata below a completed response includes the model name, date, token count, and estimated cost when those values are available.

Open the usage button in the prompt toolbar to see the chat’s input and output token totals, estimated cost, context-window capacity, and, when more than one model has been used, a breakdown by model. These numbers show how much of the model's context and API usage the request consumed. They help you explore efficiency, but they do not measure answer quality.

Continue exploring in the Playground

The chat remembers its selected context strategy and system prompt. You can ask follow-up questions, adjust the instructions, or try a different model. Use New Chat for an independent task or to test the same prompt without previous conversation history. For meaningful model comparisons, keep the prompt and context consistent.

To explore two responses side by side, select Compare in the composer and follow Compare model responses. For all chat controls, streaming, and retry options, read Use the chat workspace.