AskUI
    DownloadsLoginGet Started
    A laptop, tablet, phone and small industrial display connected on a dark workbench
    PLATFORM

    One app.
    Write, run, schedule, prove.

    Validation, documentation and operation are the same app. The CLI runs the same engine in CI.

    How it works

    A computer-use agent works your software the way a tester does.

    No selector, no recording, no object map. For every step the agent repeats one cycle: which is why a suite survives the UI changes that break selector-based automation.

    01Read

    Take a screenshot of the device and see what a tester would see.

    02Decide

    Interpret the step against what is actually on screen right now.

    03Act

    Click, type and scroll, using only the tools the project permits.

    04Verify

    Compare the result against the step's expected result, and record it.

    “The step's expected result is the contract; the path is only the execution log.”

    How AskUI works
    Automation targets

    If a person can reach it, the agent can drive it.

    The agent works from the screen, so the target does not have to cooperate. It needs no API, no test hooks, and in the hardest case nothing installed on it at all.

    Desktop

    Windows, macOS, Linux and Windows Server, driven over gRPC.

    Native apps, thick clients, anything with a window.
    Nothing installed

    HDMI capture plus USB or Bluetooth HID, so the target needs no agent at all.

    HIL benches, head units, kiosks, sealed appliances.
    Many machines

    One agent driving several machines in step, in one flow.

    A simulation environment and an operator HMI, together.
    Machine HMIs

    Line panels and industrial control screens, reached the way an operator reaches them.

    Where no selector has ever existed.
    Android

    Real devices over adb, including device racks.

    POS handhelds, scanners, phones.
    iOS

    Simulators over idb.

    Companion apps beside the cockpit or the till.
    Web

    Any browser, through Playwright when structured signals are there.

    Fast where the DOM helps, screen-driven where it does not.
    Citrix and VDI

    A remote session is just a screen, so the agent works inside it.

    No instrumentation, nothing installed in the image.
    UNATTENDED

    Nobody logged in? Still runs.

    AgentOS installs as a Windows SYSTEM service, so a machine with no session open is still a machine the agent can drive: it survives an RDP disconnect, reaches the logon screen, and works a background session overnight.

    Service install
    agentos · os service modewindows server 2019+
    RDP disconnect recovery       available
Login screen automation       available
Ctrl+Alt+Del                  available
Background sessions           available
Signed binaries · silent install  available
    The parts

    Four components, one engine.

    AskUI DesktopAuthor, run and review: projects, devices, reports.Docs AskUI CLIThe same runs, headless, for CI and schedules.Docs AgentOSGives the agent eyes and hands on a machine: screen, keyboard, mouse.Docs AskUI HubWorkspace, members, tokens and billing.Docs

    The model behind the “decide” step runs through the AskUI hub by default, or through your own provider: Anthropic, any OpenAI-compatible endpoint, or self-hosted.

    AskUI Desktop

    The whole job, in one window.

    AskUI Desktop showing a Markdown test case open in the editor with a Run button
    The test is a Markdown file.

    Steps in plain language, preconditions and postconditions. No selectors to maintain when the UI moves.

    Step constructs
    THE PROJECT

    Your testware is a folder in your Git repo.

    Every artifact is a plain file: cases, plans, keywords, the prompts that describe your system, the tooling the agent may use. Diff it, review it, branch it. Nothing important lives only in our database.

    Project structure
    my-project/git
    tests/
  rules.md  setup.md  teardown.md
  login_test.md
  checkout/
    pay_with_card.md
plans/        smoke.md
procedures/   login_to_ui.md
prompts/      report_format.md
utils/        tools.json  mcp.json
devices.json  schedules.json
    tests/Suites and cases. A file is a case; a folder is a suite with its own setup and teardown.
    plans/Test selection: what makes up the smoke set, the regression pack.
    procedures/Keywords. Write a sequence once, call it from any case with parameters.
    prompts/What you would tell a new tester on day one about the system.
    utils/The permitted tooling: built-in tools, MCP servers, custom C# tools.
    devices.jsonThe test environments.
    schedules.jsonThe execution schedule for recurring runs.
    agent_workspace/Evidence per run: logs, reports, screenshots. Not versioned.
    A run

    Phases in, evidence out.

    THE ORDER OF A RUN
    1. setup.mdEntry criteria first. A failing setup marks the tests it guards as broken, so they never run against a bad state.
    2. the casesEach case is one autonomous agent execution, streaming into the live log.
    3. teardown.mdRuns last, even after failures.
    4. rules.mdStanding instructions that apply throughout, accumulating per level.
    How a run executes
    WHAT EVERY RUN LEAVES
    A verdictPASSED · FAILED · WARN · SKIPPED · BROKEN
    A screenshotper step, as the agent saw it
    The transcriptevery tool call and decision
    The reportin agent_workspace, per run
    Run report
    EXTEND

    Give the agent more hands.

    SQL over ODBC, HTTP, shell and file I/O are built in. Add MCP servers or your own C# tools, and keep credentials out of the transcript.

    The AskUI Desktop utils screen showing encrypted secrets
    Tools MCP Secrets
    HEADLESS

    One command in CI.

    Gate a release, or schedule the nightly report.

    ci · nightlytoken: release-train
    $ askui run tests --plan nightly

214 tests · 4m 12s
exit 0  all executed tests passed
    CI/CD integration Pipeline examples Scheduling
    Deployment

    Four ways to run it. The same app in all four.

    How much of the platform sits on your side is a deployment choice, not a different product. Nothing about authoring or running a task changes between them.

    01Hub

    Sign in and go. Inference is routed and metered by us.

    Inference
    AskUI-routed
    Activation
    Online
    02Hub + your model

    Your Anthropic or OpenAI-compatible endpoint, our hub for workspace and billing.

    Inference
    Your provider
    Inference fee
    None from us
    03Licence key

    Validated offline. The app never contacts our hub at all.

    Hub contact
    None
    Activation
    Offline key
    04On-premise

    The hub inside your perimeter, with unmetered agents and hardware control.

    Hosting
    Yours
    Agents
    Unmetered

    Air-gapped estates run the licence-key or on-premise shape, where the app never contacts our hub and inference can stay inside your network.

    Security, procurement and the paperwork
    PlansScoped to your setup, with a trial for your team to start.See plans EnterpriseOn-premise, air-gapped, your own model.See enterprise CustomersMeasured results from delivery teams in production.See customers
    NEXT STEP

    See it on your own systems.

    We scope the trial with you and run it on your real environment. A person answers, within one business day.

    Get Started
    Scoped with you firstA short call about targets, scale and deployment.
    Terms agreed before the startScope and conversion terms in writing, up front.
    Nothing leaves your perimeterOn-premise and air-gapped deployment. ISO 27001, GDPR.