Chat and Evaluation · Chat workspace
Use the chat workspace
Use EidoStack AI Playground to chat with models, stream answers, adjust prompts, and inspect usage.
Updated October 17, 2026
The chat workspace is the main interface of the EidoStack AI Playground. Select a model, send prompts, read streaming responses, and continue conversations in one place. The Playground also keeps the model, system instructions, context settings, and usage information together when you want to explore model behavior more closely.
Know the workspace controls
The prompt toolbar contains the controls that shape the next request.
| Control | What it changes |
|---|---|
| Model name | Selects the provider model used for the chat. |
| Sys Prompt | Sets or clears the instruction for the current chat; comparison mode has a separate control for each side. |
| Context Memory | Chooses how previous messages are supplied with the new prompt. |
| Usage button | Opens the current chat’s context, token, and estimated-cost summary. |
| Compare | Sends the same prompt to two configured models side by side. Free accounts use models from one configured provider. |
The model selector only lists models enabled in Settings > Models. Selecting a model without a matching provider key produces a warning instead of sending the request. Unlock the vault or save the matching key in Settings > Providers before continuing.
Send and follow a response
- Select a model in the toolbar.
- Add a chat-specific system prompt or context policy when the task needs one.
- Enter a prompt in the composer.
- Select the send arrow
and follow the answer as it streams into the conversation.
During generation, the send control becomes a square stop button 
. Selecting it cancels the active stream; any output received before cancellation can remain as a partial assistant message. EidoStack then lets you continue the conversation or start a new chat for a different task or experiment.
Completed assistant messages render Markdown and code blocks, and their hover controls include Copy.
When provider usage is available, the message metadata shows the date, model, token count, and estimated cost. A provider refusal is displayed as a distinct response state, helping you distinguish it from a normal answer while exploring model behavior.
Recover from a failed request
When a provider request or message save fails, EidoStack shows an error card in the conversation. Select Try again to resend the last request. Confirm the following before retrying:
- The vault is unlocked in this browser.
- The selected model’s provider key is saved and still active.
- The provider account has available quota and is allowed to use the selected model.
- The prompt and selected model are still the ones you intend to test.
The application sends model requests directly from the browser using the provider key. An error can therefore come from the provider, the local vault state, the network, or EidoStack’s authorization checks. Do not paste provider keys into the chat as a workaround.
Explore model behavior and usage
You can use one chat for follow-up questions and ongoing work, or run more controlled tests of prompts and models. When comparing models, keep the prompts, instructions, and context configuration consistent so differences are easier to interpret. Start a fresh chat for a clean history, or change Context Memory when the amount of previous conversation is what you want to explore.
Open the toolbar usage button to review cumulative input tokens, output tokens, estimated cost, context-window capacity, and an optional per-model breakdown. For broader time-period reports, select the usage icon in the workspace header and read Usage, tokens, and costs.
Name and revisit the chat
When automatic chat naming is enabled, EidoStack can use the selected model after the first response to create a concise title. This can consume a small additional amount of provider quota. You can rename a chat manually from the header or its sidebar options; a manual title takes precedence over automated naming.
Organize useful conversations and experiments into folders or pin them for quick access. See Organize chats and folders. When you want to assess a model systematically rather than simply chat, follow Evaluate a model.