Tapping any agent, whether it is a card or member pill on the Agents page or a node on the Builder canvas, slides its editor over the current screen. The drawer edge drags to resize, and the width is remembered.
Autosave: there is no Save button
Every change autosaves into the team's draft. The footer ticks through autosaving… to autosaved 12 s ago, and real callers stay on the live version until the team goes live. Opening the drawer never creates a draft; only actual edits do, so browsing is always safe.
Overview, model and voice
Overview holds the agent's name, description, type and team membership, plus Test in browser and Download config (the full configuration as JSON).
Model & voice (Model & behaviour for text agents) chooses the AI model from a searchable picker, with a temperature slider from Precise to Creative. See Models & platforms. For voice agents the same tab sets Language, Voice and Speech recognition; changing the language reloads the voices and recognisers that support it.
Conversation: greeting, context and prompt
The Conversation tab controls how calls open: No greeting, Say this exactly, or Generate from instructions. It also holds the agent's full System prompt in a Markdown editor, for wording that needs precise control.
Three option cards sit between them. Call context picks which facts the agent is told at the start of every call: the date and time, the caller's number, the number dialled. Call length sets when calls are ended; when it is unset, every call is capped at 5 minutes 5 seconds. It also sets an optional time-up message. Silence check-in has the agent ask "Are you still there?" after a chosen stretch of quiet, optionally ending the call after three unanswered check-ins.
Tools & transfers
Three sub-tabs: Functions (custom tools, including REST calls with typed parameters), API keys (named secrets, write-only once saved), and MCP servers for external tool servers. Tools connected by the team diagram appear read-only, labelled Managed by the team diagram: edit in the builder. Each editable function has a Hide the result from the agent switch: the function still runs and its result is stored with the call, but the model only hears whether it succeeded.
Voice agents add the hand-back editor and two cards: Transfer behaviour, covering the comfort tone played during a transfer, the allowed destinations for every number the agent dials (with a live Try it tester), and the consultation brief for warm transfers; and Keypad input, which sets how the caller's key presses are gathered.
Deploy and Activity
Deploy lists everywhere the agent is answering. Each row's ⋯ menu offers Embed on your site (a copyable widget snippet for browser deployments), Move to another agent, and Undeploy. The Deploy to form targets the browser, an owned number or a SIP registration; the tab is also home to the telephone test and Place an outbound call. See Outbound calling.
For voice agents an Operations section appears at the end of the tab. If the model cannot be reached sets a fallback chain, tried in order: restart the session on another agent, retry with another model, play a fixed message and end the call, or transfer to a person. The message is spoken and then the call ends, so a number is only reached if the announcement cannot be played at all. It is the only step that can answer a caller who was turned away because every line was busy. By default it is spoken in the agent's own voice; realtime models have no speech engine of their own, so name a provider and voice for the announcement if you care which one the caller hears. Call recording toggles recording for this agent's calls; it is on unless you turn it off. Recordings are encrypted at rest, and can optionally use a customer-supplied key, in which case the platform cannot decrypt them and in-dashboard playback stops working.
Activity shows the agent's most recent calls; the full history lives on the Calls page.
Hand-edit or ask the Builder?
Both write to the same draft. The drawer suits precise, known edits: this greeting text, that voice. The Builder chat suits structural change: new agents, new connections, new tools.
Delete lives in the drawer footer behind a confirm. Deleting is the one change autosave cannot undo.