Skip to content

Independent Auditing of AI Agents. Run by human or the agent itself, to answer the most crucial question in the AI Agent Economy. Is the agent doing what is supposed to do? With iFixAi you can have this answer in less than 120 seconds.

Commits on main

fix: Surface upstream errors inside HTTP chat choices (#254)
Rudy Mizrahi Celekli committed 1 month ago
3078878
fix(gemini): keep native retries within adapter ownership (#303)
Rudy Mizrahi Celekli committed 1 month ago
c3ff52d
d18a3b9
fix: fail exact ties in full-mode analytic ensembles (#296)
Rudy Mizrahi Celekli committed 1 month ago
89f4d5c
fix(gemini): fall back when models reject JSON output (#302)
Rudy Mizrahi Celekli committed 1 month ago
e90d53c
32a2cb1
fix: validate audited users against all declared roles (#291)
Rudy Mizrahi Celekli committed 1 month ago
25ddf98
fix: validate audit timestamps for every B13 trail size (#295)
Rudy Mizrahi Celekli committed 1 month ago
cedc6f6
fix: preserve authoritative empty discovery permissions (#309)
Rudy Mizrahi Celekli committed 1 month ago
b1b5c83
c16a8ab
74d4c73
bd69a8f
fbf8c46
fix: identify invalid UTF-8 run configurations (#275)
Rudy Mizrahi Celekli committed 1 month ago
2765a89
84ae267
3160c51
171fa9a
fix: report atomic judge budget skips accurately (#287)
Rudy Mizrahi Celekli committed 1 month ago
e36c485
fix: reject reported LangServe judge truncation (#284)
Rudy Mizrahi Celekli committed 1 month ago
c0122d6
19a2eca
aa51817
fix(cli): enforce Full fixture policy for named aliases (#307)
Rudy Mizrahi Celekli committed 1 month ago
cf37747
8066421
dda229c
fix: require the AWS secret when offering Bedrock setup (#246)
Rudy Mizrahi Celekli committed 1 month ago
c1741d7
b943433
ce5a1d0
7c36dba
fix: propagate failures from runs launched by setup (#273)
Rudy Mizrahi Celekli committed 1 month ago
7925d8e
fix: reject empty and nonstring phrasing probes (#237)
Rudy Mizrahi Celekli committed 1 month ago
9c3cbf3