> 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/getting-started.md). # Use the Agent Run a useful first task with the Agent and learn the operating pattern you can reuse later. The fastest way to learn the Agent is to give it a real task whose result you can check. Your Project Agent page may already show starter cards for common work. Use one when it matches the job, or start your own session. ![The Agent starting point with starter cards before a session begins.](https://3370306531-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FlgSglJDQZxDZdn20CUcl%2Fuploads%2FXJyk75dMtAnz6izOkKyM%2Fagent-start.png?alt=media) ## 1. Pick a bounded task Good first tasks have accessible evidence and a clear finish line. For example: * “Compare this supplier confirmation with the open purchase order and show me the differences.” * “Check why order 4831 is blocked and tell me what is missing.” * “Read these certificates and return only the exceptions.” * “Use the current ERP and planning data to explain where this week's production plan is at risk.” Avoid starting with an irreversible action whose effect is hard to verify. ## 2. Describe the outcome Tell the Agent: * **Outcome** — what should be true when the work is finished; * **Evidence** — files, systems or records it should use; * **Constraints** — what it may not assume or change; * **Result** — what you want back so you can judge the work. For example: > Compare the attached supplier confirmation with PO 10483 in the ERP. Treat the ERP quantities and item numbers as authoritative. Do not change the order. Return the mismatches and the evidence you used. You usually do not need to prescribe every intermediate step. ## 3. Let it work through the evidence The session shows the conversation and visible activity around the run. For longer work, use Session workspace to follow progress, inspect files and understand the context around the task. ## 4. Answer when your judgement is needed The Agent may pause when information, judgement or approval is genuinely required. Answer in the same session when the question belongs to the current task. For a live conversation, use Call with Agent. If the Agent asks for something it should already know every time, treat that as a setup issue to improve rather than something operators should keep repeating. ## 5. Check the actual result Do not judge only the final prose. Check the strongest available evidence: 1. the actual business-system result or post-condition; 2. the files, records or calculations produced; 3. the visible activity and source material used; 4. Monitoring or Activity evidence where deeper inspection is needed. A confident answer reached from the wrong source is still a bad operational result. ## 6. Correct the cause and leave feedback If the result is wrong, tell the Agent what was wrong, where it appeared, which source should have been used and what you expected instead. Use response feedback for a specific answer and session feedback for the overall outcome. For recurring issues, this gives builders evidence they can inspect alongside the run. If the same correction keeps returning, the durable fix may belong in a Skill, maintained source, Memory, Connection or Workflow rather than in a longer prompt. ## What success looks like A good first milestone is: **the Agent can complete one useful operational job, use the right evidence, make uncertainty visible and stop where a person still needs to decide.** ## If you cannot start a session First confirm that you have access to the Project. Where usage-based Agent access is enabled, organisation membership and direct Agent access can be separate. You may need an Agent seat, and a configured usage limit can pause new Agent messages. See Subscription Management for the current seat and usage-limit model. --- # 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/getting-started.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.