skip to content
promptdojo
_
[ save your spot ]
[ follow on x ]
Clustering without labels — step 2 of 7
ch 40 · unsupervised learning, embeddings, and recommenders
2/7
promptdojo
_
›
phase 08 · ai/ml engineering buildout
›
ch 40 · unsupervised learning, embeddings, and recommenders
lesson 1 of 4 · clustering without labels
step 2 / 7
A cluster contains two billing complaints and one login complaint. What should the summary say?
1
Mark it mixed and ask a human reviewer to split or rename it.
2
Call it billing and hide the login item.
3
Treat the cluster as proof all three customers had the same issue.
4
Delete clusters that are not perfect.
check
Show hint
Clustering without labels — step 2 of 7
ch 40 · unsupervised learning, embeddings, and recommenders
2/7
promptdojo
_
›
phase 08 · ai/ml engineering buildout
›
ch 40 · unsupervised learning, embeddings, and recommenders
lesson 1 of 4 · clustering without labels
step 2 / 7
A cluster contains two billing complaints and one login complaint. What should the summary say?
1
Mark it mixed and ask a human reviewer to split or rename it.
2
Call it billing and hide the login item.
3
Treat the cluster as proof all three customers had the same issue.
4
Delete clusters that are not perfect.
check
Show hint
park a thought