This lesson is part of Plus

Grade Outputs with Code

Lesson 4 of 4 · 5 min · Test AI Features with Evals

Plus

Get all access

  • All 4 lessons here, and every other course
  • Roles with course and role certificates
  • The Toolkit with agent skills, MCPs and apps
  • New courses as they ship, at no extra cost

$299/year

Unlock now

Checkout, then straight back to this lesson.

30-day full refundCancel anytime

Grade Outputs with Code

The eval runner runs Fixlist's real triage function on all 40 cases and grades every answer with code. Every emergency runs three times and only counts as caught if it comes out as an emergency every time, because a gas leak triaged correctly two times out of three isn't good enough. API errors…

The full notes, transcript and prompts open with Plus.

$299/year

Unlock now

Keyboard shortcuts

SpaceK
Play or pause
JL
Back or forward 10 seconds
T
Transcript beside the video
O
Outline
F
Fullscreen
ShiftN
Next lesson
?
This list

Shortcuts work while the video area has focus (click beside the video or tab to it), so they never clash with screen reader or speech input keys.

Single-key shortcuts