> 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/understand-lleverage/key-terms.md). # Key terms The main Lleverage terms, explained in the context of real operational work. ## Operational process A recurring piece of business work such as sales-order intake, supplier follow-up, invoice matching, production planning or master-data maintenance. This is the best starting point for understanding Lleverage. Product constructs exist to execute this work. ## Project A **Project** is the product boundary around a related area of operational work. It brings together the Agent, Workflows, Skills, Connections, data, files, knowledge, Memory and access needed for that area. ## Solution A **Solution** is delivery/customer language for the operational outcome being implemented. It is not currently a first-class runtime object. A Solution can be implemented with several product constructs inside one or more Projects. ## Agent The **Agent** is the flexible foreground work surface. Use it when the route depends on what is found, when inputs are messy or incomplete, or when an operator is actively working through the task. ## Workflow A **Workflow** is a defined execution path for repeatable work. It is used when the sequence and controls can be configured in advance. Workflows often run in the background and can pause for configured human input. ## Workflow app A **Workflow app** is an operator-facing interface to a published Workflow. It lets someone start or participate in configured work without opening the Workflow builder. ## Request A **Request** is a configured human handoff created by a Workflow. It asks an assigned person for a decision or input before the Workflow continues. This is separate from a question or approval inside an Agent session. ## Skill A **Skill** is a reusable capability for the Agent. It captures how a particular kind of work should be approached and can bring together instructions, tools, systems, knowledge, data, files or Workflows. ## Connection A **Connection** gives Lleverage authorised access to an external system or service. The Agent, Skill or Workflow determines how that access is used for the work. ## Table A **Table** stores maintained structured working data that Agents and Workflows can use, such as mappings, rules or reference values. ## File A **File** can be input to the work, evidence used during execution, maintained project material, or an output created by Lleverage. ## Knowledge **Knowledge** is maintained reference material the Agent can retrieve, such as procedures, policies, manuals or internal guidance. ## Memory **Memory** is persistent project context that can help across Agent sessions. It should not replace authoritative business records or maintained reference sources. ## Monitoring **Monitoring** is the builder-facing surface for inspecting executions and traces: what ran, what happened, where it stopped, and what evidence was produced. ## Control **Control** contains the administrative configuration around a Project, including access, Connections, schedules, credentials and related settings. ## Foreground execution Work a person is actively participating in, such as a live Agent session, a Workflow app interaction or responding to a Request. ## Background execution Work that continues without a person driving each step, typically through a configured Workflow. A single operational process can move between foreground and background execution as needed. --- # 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 dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.lleverage.ai/understand-lleverage/key-terms.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. 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.