> For the complete documentation index, see [llms.txt](https://docs.zerve.ai/zerve-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.zerve.ai/zerve-docs/agents-in-the-workspace/threads.md). # Threads Standalone conversations with Zerve's agent, for questions, research and analysis. A **thread** is a standalone conversation with Zerve's agent. Use one to ask a question, research a topic or run an analysis, without first setting up a notebook. Threads live in the Workspace. Select **Threads** in the sidebar to see yours. ## Starting a thread Type your request in the agent composer on the Workspace home page, or start a new thread from **Threads**. When you start from the home page, Zerve decides whether your request is best handled as a conversation in a thread or as work in a new notebook. A question like "What drove the move in 10-year yields this week?" opens a thread; a request like "Build a backtest of this strategy" opens a notebook. ## Agent modes in threads New threads use [Evolve Mode](/zerve-docs/agents-in-the-workspace/evolve-mode.md) by default. You can switch to Plan or Build from the mode selector in the composer, or press **Shift+Tab** to cycle through them. Zerve remembers the mode you used last. See [Agent modes](/zerve-docs/agents-in-the-workspace/agent-modes.md). You can't change mode while the agent is working. Wait for it to finish or stop it first. ## While the agent works You can send messages while the agent is working. They're queued and handled in order, and if a new message changes an earlier instruction, the agent follows the latest one. The agent may pause to ask you a question or to request approval. See [When the agent needs input](/zerve-docs/agents-in-the-workspace/evolve-mode/when-the-agent-needs-input.md). ## Learnings and sources As the agent works, it keeps [Learnings](/zerve-docs/agents-in-the-workspace/learnings.md), its persistent notes on the work, and saves the [sources](/zerve-docs/agents-in-the-workspace/sources-and-citations.md) it uses. Open them from the thread's **Learnings** and **Sources** views. ## Sharing a thread Threads can be shared with other people, like other work in Zerve. See [Sharing and privacy](/zerve-docs/administration/sharing-and-privacy.md). ## Threads and superagents Your conversations with a [superagent](/zerve-docs/superagents/superagents.md) are threads too. In a superagent conversation, you don't choose a mode or model; the superagent manages them for you. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.zerve.ai/zerve-docs/agents-in-the-workspace/threads.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.