LIVE
—
📊
—
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

5-min resolution

Avg Latency Trend (ms)

Execution latency for cache miss LLM requests

miss calls

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