<
8000
div
id="partial-discussion-header"
class="gh-header js-details-container Details js-socket-channel js-updatable-content js-discussions-title-container"
data-channel="eyJjIjoiZGlzY3Vzc2lvbjo4NDQ3OTQyIiwidCI6MTc1MDYyNTQ1Nn0=--f6433721addb2edcf79ba6ab178684bc2688c7ee540388330e8f805e5fc622a9"
data-gid="D_kwDOOSaYQ84AgOfG"
data-url="/google/adk-python/discussions/1364/title"
>
Jun 13, 2025
·
0 comments
New agent evaluation features in dev UI #1364
wyf7107
announced in
Announcements
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
We are excited to share some awesome new features for agent evaluation in the dev UI, enjoy!
Evaluation Configuration: you can now configure custom threshold for the metrics used for each eval run, allowing more control for the evaluation criteria:
Evaluation Case view & edit: Each eval case added can now be viewed and edited. Right now we only support edit of text responses from Agent. This allows you to customize the response to fit your needs:
Thank you for your continued support and love for adk!
Beta Was this translation helpful? Give feedback.
All reactions