Reference
Glossary
Definitions for key terms used across AskUI documentation.
| Term | Definition |
|---|---|
| Access token | A credential that authenticates the CLI or an external integration with the AskUI Hub. Every token belongs to exactly one workspace and has an expiry date. See Workspaces. |
| AgentOS | The runtime layer that gives the AI agent direct OS-level control: keyboard, mouse, screen capture, and system functions. Runs on Windows, macOS, and Linux. |
| Annotation | A marked region around a UI element with metadata including its name, text content, and bounding box coordinates. |
| Bounding box | A rectangle defined by coordinates that describes the location and size of a UI element on screen. |
| Companion Mode | An AgentOS control mode where AgentOS runs on an external device (e.g. Raspberry Pi) and controls the target through hardware interfaces. No software installation on the target is required. |
| Conversation log | Every message of a run, one after another, live and afterwards. The raw record of the run, not a report. Stored as conversation.json. See Conversation log. |
| Credentials | The combination of a workspace ID and an access token for the same workspace. |
| Developer Report | The self-contained HTML file of one run, report.html, with every execution, its tokens, and its cost. Formerly the HTML report. For developers who debug a run. See Reports at a glance. |
| Element | A graphical user interface component: a button, text field, menu item, image, etc. |
| Execution report | The written record of one test, step by step with screenshots. A separate agent writes it after the test, following utils/format.md. See Execution report. |
| Host Mode | An AgentOS control mode where AgentOS runs directly on the target machine and controls it via OS-level APIs. |
| Inference | The process of sending a screenshot to the AI model to identify and locate UI elements. |
| Management Report | One report over many runs in a date range: pass counts per test, test period, devices, and the software version you name. Opened from the Runs page. Built without an AI model, exported as PDF, JSON, or JUnit XML. See Management Report. |
| Project | A folder structure created by AskUI Desktop containing tests, context files (ui.md, rules.md), procedures, and plans. The unit of work for authoring and running tests. |
| Procedure | A reusable multi-step sequence (e.g. "log in") stored in procedures/ and invoked from test steps by name. |
| Summary report | The result table of one run, one row per test, built from the recorded test results. Stored as summary_report.md. See Summary report. |
| Test result | The status and short reason the agent records at the end of a test. It decides whether the test passed. Statuses are PASSED, FAILED, WARNING, SKIPPED, or BROKEN. |
| Workspace | The account-level container in the AskUI Hub that owns access tokens, usage events, and billing. Every AskUI account belongs to one or more workspaces. |
| Workspace ID | The unique identifier for a workspace. Used together with an access token to authenticate with the AskUI Hub. |