Recap Series
- Session 01: A Developer’s Roadmap to Architecting for Agents
- Session 02: Amazon Bedrock Data Automation
- Session 03: Multi-Agent on AgentCore
- Session 04: Building Agentic AI Nova Act and Strands Agents in Practice
- Session 04: Accelerating Migration Projects with Kiro using Spec-Driven Development
- Session 06: From "Matching" to "Understanding": Personalized AI Search Practice Driven by AgentCore Memory
- Session 07: Observe to Optimize – LLM Observability to AIOps Turning real-time insights into intelligent automation
- Session 08: Deploying TEAM and Building the Best Engineering Team
- Session 09: Five Hard Lessons from Five Years of So-Called Serverless Databases
- Session 14: What if AI does my job How Q Developer CLI and Kiro have changed my daily routine
- Session 16: Velocity with Vigilance: Security Essentials for Amazon Bedrock Agent Development
- Session 26: Run OSS LLMs on a Single H100 Smarter, Cheaper, Faster
- Session 28: A Modern Unified Metadata Architecture: New Approaches to Breaking Down Data Silos
- Session 29: Serverless MediaOps: Automating Video Workflows with AI on Amazon Web Services
- Session 30: Architecting for Efficiency and Reliability with Performance Testing at Scale
- Session 31: Connecting the World Through Open Source: Practical Journey of Technology, Community and Global Developer Relations
- Session 33: Building Streaming Iceberg Tables for Real-Time Logistics Analytics
- Session 34: Accelerating Large-Scale Robot Strategy Training: An Automated Closed-Loop Architecture Based on Kiro, Trainium, and EKS
- Session 35: From Vibe to Viable with spec driven development
- Session 36: Making Cloud Cost Analysis Smarter: Building FinOps Intelligent Agents with Strands and AgentCore
- Session 37: Transform Conversational Agentic AIOps for K8s Using CNCF Kagent, K8sGPT, and Nova Sonic
Session Notes
What I Do
- Overview of the author's professional activities and responsibilities.
- Detailed sections covering various aspects of the author's work:
- Amazon Reference
- Technical Reference
- New Projects
- Problematic Projects
- Core Projects
- Business Initiatives
- Areas needing assistance Q Developer CLI and Kiro Saves Me, I didn't like GenAI, Q Developer CLI
- Discussion on the utility of Q Developer CLI and Kiro.
- Personal dislike for GenAI.
- Specific praises for Q Developer CLI. How They Works
- Explanation of the functioning and mechanisms of the tools mentioned.
- Amazon MCP Servers
- Super Powers
- CLI Commands
- Knowledge
- Pricing
- Git Research
- Terraform Agentic Loop (Q Developer CLI)
- Description of the agentic loop in Q Developer CLI:
- Perception
- Planification
- Action
- Learn
- Evaluation Spec Driven (Kiro)
- Focus on specification-driven development using Kiro.
- Requirements
- Design
- Task
- All Works Fine. Are they helpful for me?
- Assessment of the tools' usefulness to the author. Various use cases for the tools:
- Code
- Assessment
- Optimizations
- Problem Resolution
- Cost Calculation
- Deployments
- Documentation
- Testing
Q Developer CLI vs Kiro,
- Comparison between Q Developer CLI and Kiro:
- Immediate use: amazon Q
- End-to-end solutions: Kiro Real-world examples of tool usage:
- Creating a landing zone
- Establishing a baseline from past projects
- Improving a blog website and creating a deployment structure
- Migrating a project from another CDN to CloudFront
- Creating a migration plan
- Designing resilient architectures
- Assessing Terraform projects
- Reviewing numerous problems All things good?
- Critical evaluation of whether everything is beneficial. Lessons learned from using the tools:
- Careful review of requirements
- Need for supervision
- Opting for the easy path
- Potential for getting stuck in loops
- Amazing but sometimes unrealistic ideas
- Caution against code deletion Positive aspects of using the tools:
- Reduced time dedication
- Development of cool ideas
- Superior code explanation
- Ability to execute tasks during meetings Concluding thoughts:
- Empowering developers and engineers rather than replacing them
- Responsibility in technology usage