> For the complete documentation index, see [llms.txt](https://docs.lleverage.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.lleverage.ai/run-operations/agent/call-with-agent.md). # Call with Agent Use Call with Agent for a live voice conversation during operational work. **Call with Agent** lets you talk with the Agent in a live voice conversation instead of exchanging text messages. Use it when a task is easier to discuss than type—for example when clarifying an exception, talking through a decision or giving the Agent nuanced context. ## Start a call You can start a call from the web Agent. The live conversation stays connected to Agent work: the Agent can reason, use available capabilities and continue the task while you talk. ## The Agent can propose a call From an ordinary web Agent session, the Agent can propose a call when the work reaches a point that is better handled as a conversation. The proposal includes a **Call** action. The live call starts only after you choose it. A Skill can deliberately instruct the Agent to propose a call at a particular decision point. ## During a call You can speak naturally and interrupt while the Agent is talking. When the Agent needs to use an interaction that belongs on screen—such as an approval, file or sign-in step—it can direct you back to the visual interface. Call with Agent is separate from **dictation**. Dictation only turns speech into a text message in the composer. Call proposals are currently a web-Agent interaction; the same Skill instruction does not create a call proposal in Slack or Teams. --- # 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.lleverage.ai/run-operations/agent/call-with-agent.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.