apo
Demo · read-only
Sign in
Agent Testing
Tasks
Runs
Schedules
Observability
Traces
Toggle Sidebar
demo
Runs
Runs
demo-bat
real-agent/documents/document-qa
demo-run_c
Failed
real-agent/documents/document-qa
·
real-agent
·
Model
openai/gpt-4o-mini
Effort
—
(reported by adapter)
·
cli
·
batch demo-bat
·
Aug 29, 2026, 03:03:29 PM
Task
Run
Trace home
Delete
80%
pass rate
4
passed
·
1
failed
·
5
checks
30.3s
duration
$0.005649
31.1k tok
real-agent
adapter
Checks
5
Conversation History
Deliverables
Trace home
4
/5 passed
1 failed
Click to expand
✓
read-spec-and-searched
✗
answers-all-five-questions
expected expected finding: API version findings include API version; expected expected finding: database findings include database; expected expected finding: cache findings include cache; expected expected finding: endpoint count findings include endpoint count; expected auth method includes jwt; expected auth flow includes client[- ]credentials
✓
answers-grounded-in-spec
✓
answers-are-complete-and-useful
✓
spec-file-present