Context Aware Development in Kiro
summary
Kiro connects to a Strands SDK agent via an MCP server to fetch live docs so the model generates Python Strands code instead of hallucinated JavaScript, demonstrates checkpointing to roll back bad edits, creates steering docs that lock in project patterns, and deploys a dad‑joke judge to Amazon Bedrock Agent Core. The live demo shows real runs (multiple jokes) and a successful Agent Core deployment, proving the MCP+steering workflow actually produces runnable, productionized agents.
AI-written summary · about
chapters (9)
- 0:00Introduction and context
- 4:25Live demo introduction
- 5:30Building a Strands agent
- 7:56Connecting MCP server
- 10:47Generating steering docs
- 11:50Testing the agent
- 13:20Deploying to Agent Core
- 17:15Finalizing deployment
- 19:20Summary and closing
related talks
25mRethinking Feature Development with KIRO
46mRethinking Full Stack Application Development with Kiro
38mKiro: Enterprise Developer Productivity
47mThe Renaissance Developer: Building Better, Safer, & Quicker with AI-Powered Spec-Driven Development
46mRethinking Full Stack Application Development with Kiro
14mIntroducing Strands Agents, an Open Source AI Agents SDK
29mBuilding Production-Ready AI Agents
19mBuilding Agents at Cloud Scale