Chatting with Your Agent

Each project has one conversation with the agent. Open a project and start typing — that's it.

How it works

• Each message you send can trigger the agent to call tools — searching the web, reading files, writing notes, creating tasks, or whatever else you've enabled in the project.
• The agent can chain multiple tool calls together to complete a request. You'll see each step as it happens.
• Conversations are persistent — the agent remembers what you said and did in the project, across sessions. When a conversation gets long it's automatically summarized so older context stays available without slowing things down.

Getting good results

• Be concrete. "Summarize today's GitHub notifications and post an update" beats "check GitHub."
• Add project instructions for things that apply every time (see Projects). You only have to say them once.
• Use skills when you have a procedure the agent should follow — a multi-step workflow, a style guide, a specific prompt template. See Skills.
• Pick the right model for what you're doing. More capable models cost more but do better on harder reasoning. See AI Models.

Stopping an in-flight response

If the agent starts doing something you didn't want, use the Stop button in the chat. It interrupts the current run immediately.

Clearing history

You can clear a conversation's history from the project's chat menu. Useful if you want to start fresh or if the agent's gone off on a tangent.

Task conversations

When you open a task, it has its own chat — separate from the main project chat, but in the same project. Anything the agent does on a scheduled run shows up in the task's chat so you can follow along. See Tasks.