当前位置:首页 > 报告详情

使用 Kiro 加速多步骤软件开发生命周期 [重复].pdf

上传人: 明**** 编号:1013637 2025-12-21 22页 246.87KB

1、 2025,Amazon Web Services,Inc.or its affiliates.All rights reserved.2025,Amazon Web Services,Inc.or its affiliates.All rights reserved.D V T 3 2 1-RAccelerate multi-step SLDC with KiroKiran ReidDeveloper Agents and Experiences,AWSDerek ChilesDeveloper Agents and Experiences,AWS 2025,Amazon Web Servi

2、ces,Inc.or its affiliates.All rights reserved.AgendaAgentic software development workflowAgent compositionHands-on:Configuring Kiro CLI Custom AgentsHands-on:Building Flappy KiroWhats Next?2025,Amazon Web Services,Inc.or its affiliates.All rights reserved.2025,Amazon Web Services,Inc.or its affiliat

3、es.All rights reserved.Agentic Software Development Workflow 2025,Amazon Web Services,Inc.or its affiliates.All rights reserved.RequirementsDesignWrite CodeTestPackageDeployOperateObservePlanSoftware Development Lifecycle 2025,Amazon Web Services,Inc.or its affiliates.All rights reserved.Requirement

4、sDesignWrite CodeTestPackageDeployOperateInceptionConstructionOperationObservePlanAI-powered development with AI-DLC 2025,Amazon Web Services,Inc.or its affiliates.All rights reserved.2025,Amazon Web Services,Inc.or its affiliates.All rights reserved.Agent composition 2025,Amazon Web Services,Inc.or

5、 its affiliates.All rights reserved.An LLM agent runs tools in a loop to achieve a goal.-Simon Willison 2025,Amazon Web Services,Inc.or its affiliates.All rights reserved.An LLM agent runs tools in a loop,while building context,to achieve a goal.2025,Amazon Web Services,Inc.or its affiliates.All rig

6、hts reserved.InputTool SelectionTool ExecutionReasoning(LLM)ResponseAn LLM agent runs tools in a loop,while building context,to achieve a goal.Context 2025,Amazon Web Services,Inc.or its affiliates.All rights reserved.InputTool SelectionTool ExecutionReasoning(LLM)ResponseContextAn LLM agent runs to

word格式文档无特别注明外均可编辑修改,预览文件经过压缩,下载原文更清晰!
三个皮匠报告文库所有资源均是客户上传分享,仅供网友学习交流,未经上传用户书面授权,请勿作商用。
主要内容概括: 1. **Agentic Software Development Workflow**:文章介绍了基于代理的软件开发工作流程,强调从需求到部署的每个阶段。 2. **AI-Powered Development with AI-DLC**:提出使用AI驱动的开发流程(AI-DLC),利用大型语言模型(LLM)代理进行多步骤推理和工具循环。 3. **LLM Agent Functionality**:LLM代理通过选择工具、执行操作、进行推理和响应来循环工作,同时构建上下文。 4. **Kiro CLI Custom Agents**:介绍了Kiro CLI自定义代理,包括模型选择、提示、资源文件、钩子和服务器配置。 5. **Hands-on Activities**:提供了配置Kiro CLI自定义代理和构建Flappy Kiro的实践操作。 6. **Recap and Resources**:总结AI优先的方法和AI-DLC工作流程,并提供GitHub上的AI-DLC工作流程链接。
Kiro CLI揭秘" Kiro CLI实操指南" Kiro CLI定制化体验"
客服
商务合作
小程序
服务号
折叠