Agents predicted where our app would break, then checked it on video
Before a usability test of the Fortunest investing app, an agent walked the app and modelled where a new user would stall. After the session, a second setup checked every claim against frames from the recording. Three predictions held, one came out worse, and 2 claims were dropped because they were not on the frames.
How it works
- An agent walks the live app and builds a task model
- It marks the steps where a new user is likely to stall
- A test session runs with a real user
- The AI reads the recording and the transcript
- The AI checks each claim against video frames
- Claims not on a frame are dropped and logged
Why it’s worth knowing
The second setup threw out 2 of the first setup's claims because the video did not show them.
Where it’s from
Summarized from a public post on aiguild.blue. See the original ↗