Chat basics

Steinkauz chat lets you talk to many AI models in one place. You choose the model (or use guided model selection), send messages, and get streaming replies. You can switch models at any time within a conversation or start a new one.

Everything you do in chat runs in your active context. Switch in the organization switcher to work as Personal or in a different organization. See Individuals & Organizations.

Starting a conversation

Open the chat interface from the main navigation.
Confirm the correct context is active in the organization switcher.
Optionally pick a model from the model selector. If you are not sure which to use, see Guided model selection.
Type your message and send. Replies stream in as they are generated.

Stopping and switching conversations

Replies continue generating on the server until they finish or you stop them.

Leaving a conversation (switching to another chat, opening a new one, or navigating away) only disconnects your view. Generation keeps running in the background, so you can browse other sessions without canceling the reply.
Stop generating cancels the current reply. Use this when you want to halt the model mid-response.
If you return to a conversation that is still generating, chat can resume the live stream so you see the reply as it continues.

Multiple models in one place

You are not limited to a single provider. You can use a Claude model for one reply and an OpenAI or other model for the next. Each message can use the model that is currently selected.

Tools in chat

During a conversation, the model can use tools when they are enabled, for example:

Image generation — Create images via supported image providers.
Web search — Search the web for up-to-date answers.

You can enable or disable tools in the chat header within what your tool policy allows. Organization owners and admins (or you in Personal context) configure which Native Tools and Tool backends are available in Settings → Native Tools.

Data routing and the shield control

Steinkauz enforces data routing policy on every send. The shield next to Share in the chat header shows the conversation’s effective data sensitivity and lets you choose Auto or Manual sensitivity mode:

Auto — The session floor follows your context default and can rise when you attach sensitive files or select providers that require a higher floor.
Manual — You fix a sensitivity level; only providers allowed by your routing matrix for that level appear in the model picker.

If a send would violate the routing matrix, Steinkauz blocks it before inference and explains how to fix it.

Configure the routing matrix, default sensitivity, and provider environments in Settings → Routing policy and Settings → Providers while the relevant context is active. See Data routing policy.

Your conversations are saved in your active context. In organizations, each member sees only their own threads in the sidebar. Owners and admins do not get a shared inbox of other members’ chats; they use Usage & Activity for oversight.

To rename a conversation, open the conversation menu in the sidebar and choose Edit title. You can set the title (up to 50 characters) and emoji. New conversations may also receive an automatic title depending on your workspace Title generation settings.

To let someone view a conversation without Steinkauz access, use Conversation sharing to create a shareable link.

Usage and costs

Usage counts against your plan’s inference budget (Gateway) or your provider accounts (BYOK). On Gateway organization plans, each billable member has their own budget. See Usage, costs, and activity details.

Assistant replies expose quick usage metadata and a link to full activity details from the message actions menu. View all activity for a conversation from the session activity panel in the chat top bar.