DEV Community

Auditing AI usage trackers Series' Articles

Back to Zhuojun Li's Series
A missing `model:` line was half my AI agent overspend — auditing 34 days of multi-model Claude Code
lizhuojunx86 profile

A missing `model:` line was half my AI agent overspend — auditing 34 days of multi-model Claude Code

#agents #ai #claude #monitoring
Comments 3
3 min read
An append-only audit log caught two accounting bugs in a 216-star usage tracker
lizhuojunx86 profile

An append-only audit log caught two accounting bugs in a 216-star usage tracker

#ai #llm #observability #opensource
Comments
6 min read
The vendor documents this bug. A 30k-star repo shipped it anyway.
lizhuojunx86 profile

The vendor documents this bug. A 30k-star repo shipped it anyway.

#ai #llm #codereview #opensource
Comments
12 min read
My routing policy and my traces disagreed 96 times. Never once on the main thread.
lizhuojunx86 profile

My routing policy and my traces disagreed 96 times. Never once on the main thread.

#ai #llm #opensource #devops
1
Comments 7
14 min read
I measured his app with his own code. He measured my claim with his own corpus.
lizhuojunx86 profile

I measured his app with his own code. He measured my claim with his own corpus.

#ai #llm #opensource #testing
1
Comments
10 min read
My checker scored one component compliant and another deviant. Neither had a rule behind it.
lizhuojunx86 profile

My checker scored one component compliant and another deviant. Neither had a rule behind it.

#ai #llm #opensource #devops
1
Comments 1
5 min read
"Your cache hit rate is low" — true, and worth $0.16
lizhuojunx86 profile

"Your cache hit rate is low" — true, and worth $0.16

#ai #llm #python #observability
3
Comments 14
8 min read