Doubao Say
12/13 cases passed
| Result | Case | Duration | Node screenshot | AI response / error |
|---|---|---|---|---|
| ✅ Passed | Cancel sign-in and retry | 1m47s | ![]() |
AI: The screenshot shows the Doubao Say interface with a microphone icon prominently displayed in the center, indicating the app is on the Microphone step. There is no visible synthetic sign-in window or login prompt in the current view. The interface appears to be in the recording/voice input stage. |
| ✅ Passed | Complete Doubao Say onboarding on a real desktop | 2m51s | ![]() |
AI: The screenshot shows a settings page with a "Setup" section. The visible setup control appears to be disabled (grayed out) and its label reads "Setup completed by the synthetic E2E fixture." This matches the statement exactly. |
| ✅ Passed | Recover from an endpoint failure | 1m00s | ![]() |
AI: The screenshot shows a page with a "Synthetic" section. There is a green checkmark icon next to "Synthetic" indicating a successful status. Below, there is a table with columns "Endpoint", "Status", and "Last Checked". The row shows "https://api.example.com/health" with a green checkmark and "Healthy" status, and "Last Checked" shows "Just now". There is no visible error message or "unavailable" indicator. The successful endpoint result is clearly visible with a healthy status. |
| ✅ Passed | Changing microphone requires another check | 1m51s | ![]() |
AI: The screenshot shows a settings or setup page with a "Finish setup" button at the bottom. The button appears to be highlighted in blue with white text, indicating it is active and clickable. There is no visual indication (such as grayed-out styling or a disabled state) that would suggest the button is disabled. Therefore, the statement that the "Finish setup" button is visibly enabled is true. |
| ✅ Passed | Capture and retain a custom trigger shortcut | 2m49s | ![]() |
AI: The screenshot shows a settings page with a "Trigger Key" section. The active trigger is displayed as "⌃ + F8" with a note "Press to change". The selected trigger in the list is highlighted and shows "⌃ + F8". Both the active and selected trigger match the statement. |
| ✅ Passed | Toggle polishing without losing configuration | 36s | ![]() |
AI: The screenshot shows a settings or configuration panel. I can see a section labeled "Voice polishing" with a toggle switch that appears to be in the "on" position (the switch is highlighted/colored). Below that, there is a field labeled "Model" with an input box containing the text "synthetic-model". The text in the Model input field appears to be exactly "synthetic-model" with no additional characters visible. The Voice polishing switch is clearly toggled on based on its visual state. |
| ✅ Passed | Complete and cancel a voice test safely | 3m20s | ![]() |
AI: The screenshot shows a settings page with a "Voice test" section. The "Start voice test" button is visible and appears enabled. The setup control displays "Voice test passed" with a checkmark. There is no indication of any pasted or sent content in the visible area. |
| ✅ Passed | Switch to Volcengine and validate credentials | 2m53s | ![]() |
AI: The screenshot shows a mobile app interface with a dark background. At the top, there is a header with a back arrow and the text "Create New Workout" in white. Below that, there is a progress indicator showing "Step 2 of 3" with a progress bar. The main content area displays a large circular icon in the center, which appears to be a microphone icon in a blue/purple gradient circle. Below the icon, there is text that reads "Microphone" in white, followed by a description in gray text. At the bottom, there is a "Continue" button. Based on the visible content, the current step is indeed labeled as "Microphone". |
| ✅ Passed | Deliver one synthetic dictation to the focused target | 43s | ![]() |
AI: The screenshot shows a page with a "Synthetic dictation" field containing the text "Synthetic dictation delivered exactly once" and a status section indicating "Delivered once" with "1 delivery" displayed. The field and status match the statement exactly. |
| ✅ Passed | Preserve signed-in account across backward navigation | 6m48s | ![]() |
AI: The screenshot shows a microphone setup page with a title "Let's make sure we can hear you." and a subtitle "We'll ask you to read a few sentences to make sure your microphone is working." There is a microphone icon and a "Start" button below. The page appears to be part of a voice assistant setup flow, and the text "Let's make sure we can hear you" is clearly visible as the main heading. |
| ❌ Failed | Require an enabled trigger and retain the replacement | 28s | ![]() |
Error: Node "aiAssert" failed: Node "aiAssert" failed: Assertion failed: Active trigger says Disabled and Voice polishing has not changed. Reason: The screenshot shows a settings or configuration panel. I can see a section labeled "Active trigger" with a toggle or dropdown that appears to be set to "Disabled". Below that, there is a section labeled "Voice polishing" with a toggle switch. The toggle for "Voice polishing" appears to be in the "On" position (the switch is highlighted/colored). Therefore, the statement "Active trigger says Disabled and Voice polishing has not changed" is false because Voice polishing appears to be enabled, not unchanged. |
| ✅ Passed | Microphone check gates setup completion | 1m20s | ![]() |
AI: The screenshot shows a setup wizard interface with a "Finish setup" button at the bottom right. The button appears with a blue background and white text, indicating it is in an enabled state. There is no visual indication (such as graying out or a disabled style) that would suggest the button is disabled. Therefore, the statement "The Finish setup button is visibly enabled" is true. |
| ✅ Passed | Cancel synthetic dictation without delivering text | 49s | ![]() |
AI: The screenshot shows a chat interface with a message exchange. There is a user message and an assistant response. The assistant response appears to be a single sentence: "This is a test sentence." Below the response, there is a status indicator showing "1 delivery" with a checkmark icon. The status text reads "1 delivery" and appears to indicate a successful delivery of the synthetic sentence. The interface shows a single delivered message with the count of 1. |
Omarchy visual checks
0/1 cases passed
| Result | Case | Duration | Node screenshot | AI response / error |
|---|---|---|---|---|
| ❌ Failed | System menu text and focused row are visible | 11s | ![]() |
Error: Node "aiAssert" failed: Node "aiAssert" failed: Assertion failed: The Omarchy system menu is open, and its Shutdown item is clearly readable. Reason: The screenshot is not fully provided; the image data appears truncated. Based on the visible portion, I cannot determine whether the Omarchy system menu is open or whether a Shutdown item is readable. No clear menu or text is discernible from the available pixels. |













