> 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/agent-faq/everyday-use.md). # Everyday use Common questions about everyday Agent use. ## What is the Agent actually for? Use the Agent for work where the route depends on what it discovers: messy inputs, exceptions, several systems or human judgement. For a fixed repeatable process that should run in the background, use a Workflow. ## What is the difference between an Agent and a Workflow? The Agent is flexible and can change its route while working. A Workflow is deliberately structured in advance. Most real processes use both. ## What is the best way to start? Pick one real task with a checkable result. Give the Agent the outcome, relevant evidence and important constraints, then verify what it produces. See [Getting started with the Agent](/run-operations/agent/getting-started.md). ## Can I talk to the Agent instead of typing? Yes. **Call with Agent** is a live voice conversation in the web Agent. The Agent can also propose a call from a normal web session. You choose **Call** to start it. Dictation is different: it only turns speech into a text message. ## Can the Agent call me by itself? It can propose a call, but it does not automatically start an unsolicited live call. You decide whether to accept the proposal. ## Can I use the Agent in Slack or Teams? Yes, when your organisation has configured the relevant Channel. Channel conversations can be pinned to a Project or use eligible capabilities from the current speaker's authorised Project scope. ## How do I know what the Agent actually did? Follow the session activity and inspect the concrete outputs. For consequential work, verify the resulting record, file or system state. See [Session workspace](/run-operations/agent/session-workspace.md). --- # 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/agent-faq/everyday-use.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.