/{org}/agents/{id} — a full-page,
message-by-message view with inline tool calls and approval cards.
Starting a conversation
- Open an agent from the Agents list.
- Type a message in the composer at the bottom of the chat.
- Send.
Tool calls inline
When the agent calls a tool, you see an inline card showing the tool name, inputs (collapsed by default — expand to see), and outputs once the call returns. If the tool is set to Ask, the card pauses with:- The tool’s risk badge
- The inputs the agent wants to use
- Approve / Deny buttons
Files and images in chat
When the agent or one of its tools produces a file, it appears in the conversation as an attachment card instead of raw text. Images show a thumbnail preview; other file types show a type icon with the filename and format. Use the download button on the card to save the file. Attachments in chat are display-only for now — you can’t yet upload your own files from the composer.Multiple conversations
Each conversation is independent, so you can keep several going at once — they run simultaneously without interfering with one another. Starting a new chat opens a fresh conversation; the one you were in keeps its full history and any work in progress.Resuming past conversations
Past conversations appear in Agent Conversations. Open any conversation’s detail page to see the full history; send a new message to continue from where it left off.Under the hood
- The chat uses a WebSocket connection for low-latency streaming.
- The UI is lazy-loaded, so the first open of an agent chat may take a moment.
- Messages persist even if you close the tab — reload and you’ll see what was already there.
- Messages are grouped by day with a date separator (Today, Yesterday, or the date) so longer conversations are easy to scan.
Troubleshooting
Next steps
Agent conversations
Review or resume past chats
Tool permissions
Fine-tune what the agent can do