> 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/context-memory-and-learning.md). # Context, memory and learning Common questions about Agent context, Memory and learning. ## What does the Agent know about our organisation? It can use maintained Project context such as Skills, connected systems, files, Knowledge and Memory, plus built-in general process knowledge where relevant. Customer-specific sources should win over generic guidance when they conflict. ## Does the Agent remember previous conversations? It can retain useful context through Memory. Memory is selective rather than a complete transcript, and it should not replace systems or documents that own authoritative business truth. ## Does the Agent learn automatically when I correct it? Corrections can contribute useful context and feedback, but a recurring operating rule should normally become a reviewed change to the Skill, data, Knowledge or Workflow that owns the behavior. A published Skill does not silently rewrite itself after one conversation. ## How do I teach the Agent how our company works? Use real examples. Explain the desired outcome, correct mistakes and identify authoritative sources. When a method becomes repeatable, turn it into a Skill. ## Will the Agent hallucinate or make things up? Like any AI system, it can reach an unsupported conclusion if the evidence or rules are insufficient. The practical controls are good sources, explicit authority rules, human boundaries and verification of important outputs. ## Should different teams use separate Projects? Usually when their context, systems, operating methods or access are materially different. Projects help keep those boundaries understandable rather than growing one undifferentiated Agent. See [What the Agent can use](/run-operations/agent/agent-context.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/context-memory-and-learning.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.