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.