skills.rest
aws
awsOFFICIAL
Explore all skills by this author →
WebsiteGitHub

agents-optimize

Configure evaluators, observability, and cost governance for AgentCore agents.

2.3k|234|Updated Apr 23, 2026
Search Tags:#monitoring#observability#ci-cd#evaluate#cost-management#agentcore
One-click install
npx skills add https://github.com/aws/agent-toolkit-for-aws --skill agents-optimize
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agents-optimize
Source: https://github.com/aws/agent-toolkit-for-aws/tree/main/plugins/aws-agents/skills/agents-optimize
Command: npx skills add https://github.com/aws/agent-toolkit-for-aws --skill agents-optimize

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Measure and improve AgentCore agent quality through evaluators, online monitoring, observability, and cost governance to enable reliable, efficient AI deployments.

Core Features & Use Cases

  • Configure built-in and custom evaluators to quantify agent performance across traces, sessions, and tool usage.
  • Set up online monitoring and observability pipelines (CloudWatch logs, X-Ray traces) for real-time quality signals.
  • Analyze and manage runtime costs (compute, memory, tool calls) to optimize cost efficiency across deployments.

Quick Start

Outline your quality goals and I will guide you through setting up evaluators, observability, and cost controls.

Frequently Asked Questions about agents-optimize

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I set up evaluators to measure AgentCore agent performance?▼

Configuring AgentCore evaluators involves reading agentcore.json prerequisites and loading reference guides to deploy built-in and custom evaluators. This quantifies agent performance across traces, sessions, and tool usage.

What is the best way to monitor AgentCore traces and logs in production?▼

Setting up online observability pipelines with CloudWatch logs and X-Ray traces provides real-time AgentCore quality signals. This monitors traces and logs across development and production runtimes.

How can I manage and optimize runtime costs for AgentCore deployments?▼

Applying cost governance configurations analyzes compute, memory, and tool call expenses to manage AgentCore runtime costs. This optimizes cost efficiency across your development and production deployments.

Does this observability workflow require an agentcore.json file?▼

Yes, the workflow enforces reading an agentcore.json file to verify prerequisites before loading reference guides. It then deploys online-eval and observability configurations as needed.

Can I use custom evaluators for online monitoring of agent sessions?▼

Yes, you can configure custom evaluators for online monitoring of agent sessions. The system deploys these configurations to quantify agent performance and tool usage in real-time.

Related Skills

Explore More Software Engineering Skills→
awsaws
2.3k

agents-deploy

Validate and diagnose AWS AgentCore deployments with pre-flight checks and dry-run previews.

Official
Advanced
AndreKuraitAndreKurait

agents-optimize

Configure evaluators, observability, and quality gates for AgentCore agents.

Community
Advanced
awsaws
2.3k

aws-observability

Plan, configure, debug, and optimize AWS observability across CloudWatch, X-Ray, CloudTrail, and ADOT.

Official
Advanced
ManzuetiManzueti

benchmark

Capture and compare browser performance metrics to detect regressions and track trends.

Community
Advanced