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(evaluation): keep budget-skipped probes unscored (#169)
Rudy Mizrahi Celekli committed 1 month ago
33369e1
d6e2e80
0a87cd6
01cbe94
fix(cli): honor explicit overrides for configured judges (#158)
Rudy Mizrahi Celekli committed 1 month ago
1528ea7
5da85a0
fix(cli): retain exports for distinct run identities (#188)
Rudy Mizrahi Celekli committed 1 month ago
730c4ad
fix(manifest): bind resumed results to the SUT context (#187)
Rudy Mizrahi Celekli committed 1 month ago
3ce44ca
5dfbb36
fix(inspections): preserve complete B30 and B32 responses (#185)
Rudy Mizrahi Celekli committed 1 month ago
e987a45
fix(judge): count actual provider grading attempts (#182)
Rudy Mizrahi Celekli committed 1 month ago
008f862
3e96aa5
fix(judge): isolate rubric loader locks by event loop (#180)
Rudy Mizrahi Celekli committed 1 month ago
adbe570
fix(reporting): preserve JSON evidence audit metadata (#178)
Rudy Mizrahi Celekli committed 1 month ago
1e8e875
c76cb5a
fix(inspections): identify each B14 and B24 sweep probe (#176)
Rudy Mizrahi Celekli committed 1 month ago
377ef32
43a4491
fix(reporting): preserve assessed category counts (#174)
Rudy Mizrahi Celekli committed 1 month ago
c48e016
795b557
8a2b85b
fix(loaders): decode fixture and rule artifacts as UTF-8 (#165)
Rudy Mizrahi Celekli committed 1 month ago
a5c9051
fix(judge): honor configured sampling temperature (#164)
Rudy Mizrahi Celekli committed 1 month ago
26185f7
5597af5
46d50f1
fix(cli): allow explicitly keyless audit providers (#159)
Rudy Mizrahi Celekli committed 1 month ago
c7ada11
f18fc23
f04974e