Loading Run...
INITIALIZING
Best Composite Score
verified
—
Evaluation weighted score
Trials Evaluated
scatter_plot
0 / —
Total LLM Cost (USD)
payments
$0.00
Accumulated across trials
Web Search Fallbacks
travel_explore
0
Adaptive RAG search-tool uses
Execution Model
memory
Grid Search
Atomic Trace Drained
trending_up
Cost Accumulation Over Trials
Cumulative USD
show_chart
Stage Timing Trends Over Trials
Hover points · click for details
speed
Best Configuration: Mean Latency by Stage
Average per evaluation query
01. Query Expand
—
02. Query Embed
—
03. Vector Search
—
04. Reranking
—
05. Relevance
—
06. Web Search
—
07. Generation
—
08. Hallucination
—
monitor_heart
Error Rate Observability
Loading…
Error Rate
—
Recovered
—
Unrecovered
—
Answer Refusals
—
Refusal Rate
—
—
Waiting for observed operations…
Recent sanitized errors and terminal trial groups
No errors recorded.
Terminal trial error groups
No terminal trial failures recorded.
military_tech
Top Architecture Result
No successful trials completed yet.
table_rows
Updates live · click a heading to sort
Live Trials Telemetry Stream
| Sample Progress | Elapsed | Inspect | |||||||
|---|---|---|---|---|---|---|---|---|---|
| Waiting for trials to execute... | |||||||||