Chat and Agent

Start a chat

1. Open Chat in the intended workspace.
2. Choose an available model in the message composer.
3. Enter your question and send the message.
4. Review any tool approval request before you approve or deny the action.

Model availability depends on your account’s access. If the model list fails to load, retry it before sending. See AI models for model selection and AI usage quotas for allowances and charges.

When image attachments are available, use the attachment control to include images with your question. If an attachment fails validation, remove it or choose a supported image before retrying.

Return to a conversation

Use the conversation history to reopen a saved chat. A conversation link reopens that thread in the same workspace when you have access. Start a new chat when you need a separate conversation.

The conversation controls let you export or delete the current conversation. The usage panel shows token and model usage for the thread. Account Usage shows your monthly allowance and the separate AI Auto-switch to Credits setting.

If a message fails to send, check the draft and its attachments before retrying. An error while loading history does not mean that your saved conversation has been deleted.

Use Agent on a compute instance

Open Agent to run a codeq session inside a compute instance. Attach to an available running instance, resume a stopped one, or launch an available profile.

Agent opens a terminal session on the selected instance. Launch and running costs follow the instance’s compute profile. Use the instance controls to stop compute when you are finished.

If the terminal session ends, use Reconnect. See Dashboard and instances for the difference between stopping and terminating compute.