—
Total Requests
Across all functions
—
Cache Hit Rate
— hits / — misses
—
Avg Latency (miss)
Live LLM calls
—
Est. Total Cost
Semantic cache savings
—
Error Rate
— errors
—
Cached Entries
{{ backend_label }}
Cache Hit Rate Trend
Hit percentage aggregated in 5-minute buckets
Avg Latency Trend (ms)
Execution latency for cache miss LLM requests
Recent Activity
Latest LLM calls monitored by undertow_llm
| Time | Function | Status / Cache | Latency | Cost | Prompt | Action |
|---|---|---|---|---|---|---|
| Loading live activity… | ||||||
Request Logs & Payloads
Detailed execution history with prompt/response inspection
| Timestamp | Function Name | Cache / Status | Latency | Cost | Variant | Prompt | Response | Inspect |
|---|---|---|---|---|---|---|---|---|
| Loading logs… | ||||||||
Distributed Traces
Multi-span agent chains and execution waterfall views
Loading distributed traces…
Canary & A/B Experimentation
Comparative latency, cost, and error analytics across model variants
Loading canary stats…
Avg Latency Comparison (ms)
Primary vs Canary performance breakdown
Cost Breakdown (USD)
Cumulative cost incurred per variant