apo
Demo · read-only
Sign in
Agent Testing
Tasks
Runs
Schedules
Observability
Traces
Toggle Sidebar
demo
Runs
Runs
demo-bch
real-agent/engineering/code-review
demo-run-c
Passed
real-agent/engineering/code-review
·
anthropic/claude-haiku-4-5
·
cli
·
8w ago
Details
▸
Task
Run
Trace home
Delete
100%
pass rate
6
passed
·
0
failed
·
6
checks
48.9s
duration
$0.0923
61.4k tok
—
reasoning
⚑ 1 check corrected
▸
⚑ model drift — 12/14 gens
▸
run notices
Checks
6
Conversation History
Deliverables
Trace home
6
/6 passed
Click to expand
Trajectory — multi-file review, ordered tool use
1
/1
Objective facts — known issues identified
1
/1
Judged quality — grounding, specificity, edge cases
3
/3
✓
source-files-present