Performance

Latency, throughput, and execution efficiency.

Performance is the operational counterpart to cost: how fast the system moves, how often it succeeds, and how much work gets through the lane.

latency
throughput
success rate
efficiency
agent performance
Health lens
Measure whether work is flowing.

The performance page answers whether the system is getting faster, steadier, and easier to operate.

Runtime metrics

Measure the work path, not just the UI.

The site describes the metrics teams actually watch when they ask whether the system is healthy.

Latency

How long a turn or action takes from request to result.

Throughput

How much work moves through the system in a fixed period.

Success rate

How often tasks complete without manual intervention.

Queue health

How much work is waiting versus actively moving.

Efficiency

A good control plane makes bottlenecks visible.

Execution quality matters because slow or noisy systems make every other part of the control plane harder to trust.

Hotspots

Which teams, tasks, or runtimes get stuck the longest.

Recovery

How quickly the system recovers after drift, failure, or backlog growth.

Capacity

Whether the org has enough room to absorb new work.

Signal quality

Whether metrics are readable enough to guide action.

Search terms

Keep performance separate from pricing and from task management.

Performance pages capture the operational intent that buyers often search before they buy.

Performance keywords
performance
latency
throughput
success rate
efficiency
capacity

Performance is about the health of the system and the quality of its work path.

Cluster pages

Split performance into efficiency and latency.

The performance hub branches into the specific metrics pages operators care about.