But raw USB access was clumsy for drawing. Pressure sensitivity, tilt, multitouch gestures—these were higher-order things that needed a proper driver stack feeding into Windows’ pointer and ink subsystems. The graphics driver package had components that implemented a HID-like interface and a filter driver to translate raw packets into pointer input. Without that, the tablet would be functional but unsatisfying: a blunt stylus without nuance.

Using the WinUSB API, her utility sent a handshake: a control transfer with a magic sequence the tablet’s community threads had hinted at. The tablet’s LED blinked—once, then twice. Atlas recognized the device anew; its name flickered into the tray: “Mara’s Tablet.” For a moment she felt like an archivist who had coaxed a lost manuscript into speech.

So she took a different route: WinUSB. The tablet enumerated as a WinUSB device; that meant that at least the OS could talk to it at a raw USB level. WinUSB was not glamorous—it exposed endpoints and transfers, bulk and interrupt pipe calls—but it was honest. It let user-mode applications send packets and receive replies without a kernel driver taking the wheel. She wrote a small, patient utility that opened the device by its VID and PID and queried its descriptors. The descriptor held a string she hadn’t expected: “ARTIST-0.9.” A firmware revision, perhaps. A hint.

She opened a command prompt and typed answers into the system: sc query, pnputil /enum-drivers, reg query. Each result was another hint. The tablet’s VID: 0x04B3. PID: 0x3050. The installer had pre-registered hardware IDs in its INF, but it hadn’t matched this particular PID. A mismatch: maybe a revised revision of the device, a regional variant, or a tiny cliff of versioning.