Insights from the field

Judging clinical conversations is a lot harder than it sounds. Even the strongest "off the shelf" AI models struggle with the nuance and empathy required to evaluate goals-of-care conversations well. These conversations hinge on moments most general-purpose models can’t reliably detect.

For each clinical conversation, we transcribe the audio, score it against different rubrics, and generate several different outputs to help the clinician better understand and care for their patients. Each of these steps and outputs is a separate job utilizing an AI model, sometimes multiple, and each of these jobs has its own stakes. Finding the right model and tool that’s scoped to the task can be difficult.

Most end-to-end tests are very simple. Click the button. Assert that the expected text appears. Fill the form, submit, check the toast. The whole discipline rests on two assumptions: that you can drive the app with keystrokes and clicks, and that you know exactly what it should produce. Neither of those assumptions held for us.

We've hosted MedGemma in three different places. The first was too expensive to leave running. The second wouldn't stay running. The third is the one we should have started with.