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

3c5dd9f
fix: handle blank tool descriptions during discovery (#218)
Rudy Mizrahi Celekli committed 1 month ago
12d9f76
7a4ea0f
3fda779
fix(cli): report persisted config read failures cleanly (#213)
Rudy Mizrahi Celekli committed 1 month ago
18ddc96
fix(scaffold): retain unmanaged AGENTS.md content (#212)
Rudy Mizrahi Celekli committed 1 month ago
d5cc936
fix(cli): accept the registered LiteLLM provider (#200)
Rudy Mizrahi Celekli committed 1 month ago
29d7ad2
fix(reporting): distinguish unselected mandatory minimums (#203)
Rudy Mizrahi Celekli committed 1 month ago
7f1f68b
fix(evaluation): grade ordinary usage policy references (#210)
Rudy Mizrahi Celekli committed 1 month ago
4a479e1
fix(judge): keep truncated grading inputs unscored (#209)
Rudy Mizrahi Celekli committed 1 month ago
9a27652
1984db4
fix(judge): forward the configured ensemble endpoint (#207)
Rudy Mizrahi Celekli committed 1 month ago
7b49bb9
fix(evaluation): require complete atomic claim coverage (#206)
Rudy Mizrahi Celekli committed 1 month ago
84d7f86
fix(litellm): honor the configured native retry budget (#204)
Rudy Mizrahi Celekli committed 1 month ago
3270160
0139f60
a27b238
fix(http): retry transient gateway status failures (#199)
Rudy Mizrahi Celekli committed 1 month ago
7a45b77
2deef95
beb5537
42f6053
86bcd23
fix(fixtures): canonicalize legacy mapped inspection IDs (#192)
Rudy Mizrahi Celekli committed 1 month ago
cdad97d
f876d50
fix(judge): normalize verdict booleans before grading (#170)
Rudy Mizrahi Celekli committed 1 month ago
03514eb
1e5ca93
fa029a7
fix(cli): validate saved defaults through option types (#173)
Rudy Mizrahi Celekli committed 1 month ago
24c0aca