Configure an Agent

Open an Agent to configure it alongside the live Preview pane.

Identity and type

• Name and description identify the Agent in lists, Threads, and delivery surfaces.
• Assistant Agent keeps a working environment across sessions.
• Task Agent starts each Run in a clean environment.

You can change type only before the first publish.

Runtime and model

Choose a runtime first, then select a model available through its resolved Provider key. If the model list is empty or a runtime shows Needs key, configure the matching Provider in the active App.

System prompt

Describe the Agent's role, boundaries, answer style, and when it should ask for clarification. Prefer explicit operating rules over vague personality prose. Test both normal and failure cases before publishing.

Skills

Attach reusable instruction packages from the active App. Skills are loaded for new sessions and read by the Agent when the task calls for them. A missing Skill attachment is reported rather than borrowed from another App.

MCP servers

Attach authorized Remote HTTPS MCP connections from the active App. A connection can be attached before authorization, but its tools are usable only when the connection is enabled and authorized.

Environment

Choose the reusable runtime template for packages, setup script, variables, and network-policy intent. If the Agent has no explicit Environment, the App default applies. A new session freezes the selected Environment revision.

Save and publish behavior

Draft edits affect Preview. Publishing creates a new live version for future sessions. Existing sessions do not silently switch configuration.