Feature
Builder
Builder is an assistant for creating and improving agents. Tell it what you want, and it writes the instructions, adds files, sets up triggers and spaces, and tells you what it changed.
Open Builder
Click the Builder button in the bottom-right corner of any page. It opens as a panel on the right that you can resize by dragging its edge.
The panel stays open as you move around the app, including the space editor, and keeps the conversation. Builder knows which page you are on, so "this agent" means the one on your screen.
You can type, dictate with the microphone, or talk by voice with the round button. Attach files with +, by dropping them on the panel, or by pasting.
What it can do
- Create an agent, from scratch or from a template.
- Write instructions, documents, triggers, and skills.
- Look at a space and change what is placed in it.
- Read how people's sessions with an agent went, to find out what went wrong and fix it.
- Publish an agent, and open a page for you.
Builder asks before it deletes anything, publishes, or makes a space change that is hard to undo.
Create an agent
Go to Agents and choose New agent. Pick a template, or start from scratch, and Builder starts a conversation that creates the agent with you.
The agent's configuration page shows what Builder made: name, status, instructions, spaces, triggers, skills, tools, and voice. It has no chat of its own; ask Builder for changes and the page reloads with them. System prompt shows exactly what the model receives.
Conversations
Your conversations are your own, with a separate list in each organization. The history button shows past conversations, and the pen starts a new one. Builder works only in the organization you opened it in.
Builder pauses while an agent is running. From a run, you can send the session to Builder: the run ends and Builder starts a conversation about it.
Technical
- Builder is the built-in agent
builder, run as an ordinary text or voice session. Its tools are the AI connections tools, called as you, plusopen_page. It does not getlist_organizations,upload_file, orfile_transfer; the conversation's organization fills in every call. - Each turn includes the current page. In voice, the app sends the page whenever it changes.
- Attached files are saved in the organization's
uploads/folder. - Pages: New agent is
/org/<organization id>/agents/new(old/agent-builderlinks go there); configuration is/org/<organization id>/agents/<agent id>. - The Android app still uses an older voice builder: you talk, a read-only card shows the saved name, voice, instructions, greeting, and skills, and it opens a live session with the draft when ready. Those agents use the camera instead of a space and start with the spatial annotation tools. Spaces, trigger zones, and publishing stay in the web app.