agents-optimize

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

optimize

优化

Measure and improve your AgentCore agent's quality through evaluation, monitoring, and observability.

通过评估、监控和可观测性来衡量并提升你的AgentCore agent的质量。

When to use

使用场景

You want to know if your agent is giving good answers
You want to set up continuous quality monitoring in production
You want to add a quality gate to your CI/CD pipeline
You want to understand agent behavior through logs, metrics, and traces
You want to set up CloudWatch dashboards or X-Ray tracing

Do NOT use for:

Debugging a specific broken agent (wrong answers, errors) → use
```
agents-debug
```
Production security hardening (IAM, auth) → use
```
agents-harden
```

你想了解你的agent是否能给出优质回答
你想在生产环境中设置持续质量监控
你想为CI/CD流水线添加质量门
你想通过日志、指标和追踪来了解agent的行为
你想设置CloudWatch仪表板或X-Ray追踪

请勿用于：

调试特定故障的agent（错误回答、报错）→ 使用
```
agents-debug
```
生产环境安全加固（IAM、认证）→ 使用
```
agents-harden
```

Input

输入

$ARGUMENTS

can be:

An eval goal: "add a quality gate", "set up monitoring"
An observability goal: "set up CloudWatch dashboard", "understand my traces"
A specific evaluator: "llm-as-a-judge", "code-based"
Empty — the skill will guide based on project context

$ARGUMENTS

可以是：

评估目标："add a quality gate"、"set up monitoring"
可观测性目标："set up CloudWatch dashboard"、"understand my traces"
特定评估器："llm-as-a-judge"、"code-based"
空值——本技能会根据项目上下文提供引导

Process

流程

Step 0: Verify CLI version

步骤0：验证CLI版本

Run

agentcore --version

. This skill requires v0.9.0 or later.

运行

agentcore --version

。本技能需要v0.9.0或更高版本。

Step 1: Read project context

步骤1：读取项目上下文

Read

agentcore/agentcore.json

to understand existing evaluators, online eval configs, and agent setup.

agentcore/agentcore.json

is not found:

"This skill requires an AgentCore project. Use
agents-get-started
to create one."

读取

agentcore/agentcore.json

以了解现有的评估器、在线评估配置和agent设置。

如果未找到

agentcore/agentcore.json

：

"本技能需要AgentCore项目。请使用
agents-get-started
创建一个。"

Step 2: Determine the workflow

步骤2：确定工作流

Developer intent	Action
Measure quality, add evaluator, run eval, CI/CD gate, online monitoring	Load `references/evals.md` and follow its workflow
Set up observability, CloudWatch, X-Ray, logs, metrics, dashboards	Load `references/observability.md` and follow its workflow
Understand or reduce AgentCore costs	Load `references/cost.md`
Both — "I want to understand and improve my agent"	Start with observability setup, then add evals

开发者意图	操作
衡量质量、添加评估器、运行评估、CI/CD质量门、在线监控	加载 `references/evals.md` 并遵循其工作流
设置可观测性、CloudWatch、X-Ray、日志、指标、仪表板	加载 `references/observability.md` 并遵循其工作流
了解或降低AgentCore成本	加载 `references/cost.md`
两者兼顾——"我想了解并优化我的agent"	先设置可观测性，再添加评估器

Step 3: Follow the loaded reference

步骤3：遵循加载的参考文档

The reference file contains the full procedure. Follow it step by step.

参考文档包含完整的操作步骤，请逐步执行。

Cross-references

交叉参考

After setting up evals, suggest
```
agents-harden
```
for production readiness
If eval results reveal agent issues, suggest
```
agents-debug
```
for root cause analysis
If the developer needs to add capabilities first, suggest
```
agents-build
```

设置评估器后，建议使用
```
agents-harden
```
确保生产环境就绪
如果评估结果显示agent存在问题，建议使用
```
agents-debug
```
进行根因分析
如果开发者需要先添加功能，建议使用
```
agents-build
```

Output

输出

Depends on the workflow — see the loaded reference for specific outputs.

取决于工作流——请查看加载的参考文档获取具体输出。

Quality criteria

质量标准

Evaluator configuration uses only valid CLI flags
Online eval sampling rate is appropriate (not 100% in production without discussion)
CI/CD quality gate has a clear pass/fail threshold
Observability setup includes both tracing and logging
The developer understands the eval data delay: ~10 seconds put-to-get, end-to-end — one ingestion step covers both trace reads and eval queries; there is no separate indexing wait

评估器配置仅使用有效的CLI参数
在线评估采样率合理（生产环境中未讨论的情况下不设为100%）
CI/CD质量门有明确的通过/失败阈值
可观测性设置同时包含追踪和日志
开发者了解评估数据延迟：端到端约10秒的写入到读取延迟——一次 ingestion 步骤同时覆盖追踪读取和评估查询；无需单独等待索引完成