primer/agent-eval

Agent eval navigation

Run results for Design System

Sets up new projects with Primer / 004-agent-setup-nextjs

Run summary

Copilot CLI
Checks
50.0%
Turns
13
Output tokens
2,819
Premium requests
1
AI credits
66.22
API time
62.2 s
Session time
77.0 s

Checks average per-check pass percentages or measurement means. Skipped outcomes and errors are excluded from values and shown separately. Usage includes implementation sessions only.

Sets up new projects with Primer / 004-agent-setup-nextjs result details navigation

Loading walkthrough image 1

Sets up new projects with Primer / 005-agent-enables-theme-switching

Run summary

Copilot CLI
Checks
0.0%
Turns
21
Output tokens
11,088
Premium requests
1
AI credits
142.849
API time
225.3 s
Session time
285.5 s

Checks average per-check pass percentages or measurement means. Skipped outcomes and errors are excluded from values and shown separately. Usage includes implementation sessions only.

Sets up new projects with Primer / 005-agent-enables-theme-switching result details navigation

Loading walkthrough image 1

Uses appropriate components by default / 001-agent-uses-button-from-primer

Run summary

Copilot CLI
Checks
0.0%
Turns
9
Output tokens
846
Premium requests
1
AI credits
51.812
API time
35.7 s
Session time
43.2 s

Checks average per-check pass percentages or measurement means. Skipped outcomes and errors are excluded from values and shown separately. Usage includes implementation sessions only.

Uses appropriate components by default / 001-agent-uses-button-from-primer result details navigation

Loading walkthrough image 1

Uses appropriate components by default / 003-agent-uses-form-from-primer

Run summary

Copilot CLI
Checks
85.7%
Turns
14
Output tokens
5,299
Premium requests
15
AI credits
29.546
API time
48.0 s
Session time
69.5 s

Checks average per-check pass percentages or measurement means. Skipped outcomes and errors are excluded from values and shown separately. Usage includes implementation sessions only.

Uses appropriate components by default / 003-agent-uses-form-from-primer result details navigation

Loading walkthrough image 1

Uses Octicons by default for iconography / 002-agent-uses-octicon-from-primer

Run summary

Copilot CLI
Checks
100.0%
Turns
7
Output tokens
765
Premium requests
1
AI credits
8.995
API time
13.8 s
Session time
21.7 s

Checks average per-check pass percentages or measurement means. Skipped outcomes and errors are excluded from values and shown separately. Usage includes implementation sessions only.

Uses Octicons by default for iconography / 002-agent-uses-octicon-from-primer result details navigation

Loading walkthrough image 1