> 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/building-and-automation.md). # Building and automation Common questions about building Skills and turning Agent work into automation. ## Do I need to know how to code? Not for most Agent and Skill work. Builders can describe the desired behavior in natural language and work with the Agent to create or improve supported platform capabilities. Understanding the business process matters more than knowing implementation syntax. ## What can a Skill tell the Agent to do? A Skill can define a reusable method: rules, checks, sources, connected actions, Workflows, human questions and the expected result. In the web Agent, Skills can also instruct the Agent to propose a Call with Agent at a suitable decision point or use supported presentation surfaces such as inline widgets and HTML artefacts. ## Can I inspect and change the logic? Yes. Skills, Workflows, context, Connections and tests are maintained platform objects rather than hidden inside a sealed chatbot. Agent-authored Skill changes go through review before a new version is published. ## Can the Agent build automations for me? For supported builder tasks, yes. A useful pattern is to first get the work right with the Agent in the foreground, then turn stable repeatable parts into Skills or Workflows. ## How much setup is needed? A bounded task with clear evidence can be useful immediately. A production process with many company-specific rules needs representative examples, the right system access, explicit boundaries and testing before you should give it more autonomy. ## Is this actually self-serve? Increasingly, yes for supported use cases: users can teach the Agent, build Skills and supported automations, connect systems and iterate through natural language. Complex integrations, unclear business rules or unusual operational processes can still require expert help. See [Skills and operating methods](/build-and-improve/overview/skills-and-operating-methods.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/building-and-automation.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.