What it does
The performance-engineer agent is intended to identify and eliminate performance bottlenecks in applications, databases and infrastructure. Its described approach starts with collecting performance baselines and examining CPU, memory and I/O patterns, then uses profiling and load testing to pinpoint root causes. For database problems, it analyses execution plans and query efficiency, checks index effectiveness, and reviews caching and connection pooling.
It suits cases where measurable performance problems exist and baseline metrics need to improve. The publisher's examples include slow API response times in production, a query that became much slower after a data migration, and a site that slows during peak traffic and must scale for expected growth. In those examples the agent designs load tests that simulate peak traffic and proposes targeted indexing and caching changes.
The source describes the agent's use only through example invocations on a specific performance problem. It does not list setup steps, required tools or supported environments.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- AI Templates (aitmpl) first seen 13 Nov 2026 · last seen 17 Nov 2026 · its page on the source · figures reported by the source: aitmpl downloads 716
performance-engineer
Use this agent when you need to identify and eliminate performance bottlenecks in applications, databases, or infrastructure systems, and when baseline performance metrics need improvement. Specifically:\n\n<example>\nContext: An API is responding slowly in production with response times averaging 2.5 seconds, and users are complaining about lag.\nuser: "We're seeing slow API response times. Can you help identify what's causing the bottleneck?"\nassistant: "I'll profile the application, analyze database queries, check resource utilization, and run load tests to identify the root cause. Let me
As shown on www.aitmpl.com when we last read it