Local policy
Planner
300/300
Exact-cost recovery in one local invocation. No third-party agent score.
View evaluation ↗EVALUATION EVIDENCE
Observe behavior.
Check the evidence.
LIVE EVALUATION NETWORK
Public Agent Evaluations
Awaiting verified public runs
No public-agent metrics are published yet. Local research results are listed separately below.
- Targets evaluated
- 0
- Scenarios executed
- 0
- Agent turns
- 0
- Failures observed
- 0
- Reproducible failures
- 0
LOCAL RESEARCH / WFRB v0
50Layouts
150Scenario designs
1800Executed local trials
900 experimental cells repeated once. Local control policies only; no LLM or customer agent tested.
Explore evaluations ↗Windway controlled benchmark
Local policy
Random
4/300
Exact-cost recovery in one local invocation. No third-party agent score.
View evaluation ↗Local policy
Blind repetition
0/300
Exact-cost recovery in one local invocation. No third-party agent score.
View evaluation ↗WFRB v0 / LOCAL CONTROL EXPERIMENT
Experimental · Not a standard · Not peer reviewed
These charts describe local control trials. They do not measure public agents, LLMs or customer systems.
Loading verified aggregate data…
Recovery by category
Pass / fail / inconclusive
Injected failure class distribution
Evaluations over time
Deterministic replay verification
Target comparison
Customer target comparison is unavailable. These local controls do not support a cross-model ranking.
Inspect local benchmark evidence ↗Scenario heatmap
Tap or expand a cell to inspect its exact denominator. Each layout/category contains two seeded trials per local policy in one invocation.
PASS means exact-cost recovery. FAIL means that recovery criterion was not met. Replay verification does not establish reproduction of a customer-agent failure.
Read the methodology ↗ · Inspect aggregate data ↗