people.nav_org_chart_001
validv1regressionauthoredNavigate to org chart — People Navigator (Google ADK)
UKGEPIC/people-agents · evals/cases/people.nav_org_chart_001.yaml@ 9c3d5e1PR #460 · reviewed
One asset → 1 backends— routed centrally by AAG · each grader runs on exactly one engine, so nothing is scored twice
portable-v1 · authored once
people.nav_org_chart_001
“take me to org chart”
1 concerns · 1 YAML asset · UKGEPIC/people-agents
Functional
→ ADK eval
functional@v3 · in-sync
The assertion
Deep link opened: People → Org Chart, centered on the user's team.
Golden context
expected_tools · in_order
resolve_surface → navigate
Compiled → 1 targetspeople.nav_org_chart_001.functional.config all in-sync
Portable eval case
portable-v1input
“take me to org chart”
entities
overlay handles — never raw substrate IDs
employees.org_member_default→ E-11002 · via people/nav-fixtures@v1 on Calendar@2026.2expected_tools
order: in_order
- 1
resolve_surface{"intent":"org_chart"} - 2
navigate{"target":"people/org-chart"}
expected_output
Deep link opened: People → Org Chart, centered on the user's team.
metadata
pillar:peopletier:regressionnavigationsensitivity: syntheticpersona: employee
datasets
pinned compositions this case belongs to
kind
drives grader packs
FunctionalTool trajectory, response match, and semantic regression bulk.
Graders
inherited from AAG packs via kind: — each routedFunctionalfunctional@v3inherited→ ADK eval
tool_trajectoryin-order tool match
response_semanticLLM judge
response_lexicalROUGE-1
Routed, not replicated. Each grader goes to exactly one backend. Nothing is forced onto a backend that cannot express it, and the same case is never scored twice for the same thing.
Routing
concern → backend · centrally owned by AAG| Concern | Backend | Why this backend |
|---|---|---|
| Functional | → ADK eval | Native to the agent runtime — owns the regression bulk (trajectory, ROUGE, semantic judge). |
Compiled output
1 routed targetsArtifacts generated per routed backend (full compiled view shown on the hero case, hr.policy_carryover_004):
FNpeople.nav_org_chart_001.functional.config→ ADK evalin-sync