Enhancing Application Modernization Experience with AIDLC

Embed

Start on current slide

Slide 1

Slide 1 text

© 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. T R A C K A / T R A C K B Enhancing Application Modernization Experience with AIDLC Kim Kao Manager, Solutions Architecture Amazon Web Services

Slide 2

Slide 2 text

Slide 3

Slide 3 text

Slide 4

Slide 4 text

Slide 5

Slide 5 text

Slide 6

Slide 6 text

Slide 7

Slide 7 text

© 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. 28 million developers of the world An unprecedented change is coming to my industry because of AI. I don’t know how to be prepared!

Slide 8

Slide 8 text

Slide 9

Slide 9 text

© 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Helping developers write code faster 2023 Completing development tasks end-to-end with human in the loop Generating larger pieces of code and answering questions AI is changing software AUTO-COMPLETE 2024 ASSISTANTS 2025 AGENTS

Slide 10

Slide 10 text

© 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. The promise of agentic development Agents can take on and complete increasingly challenging tasks autonomously Autonomy Agents handle the heavy lifting of increasing test coverage, documenting code, optimizing performance, fixing security vulnerabilities Higher quality Developers and agents work together to get more done True Collaboration

Slide 11

Slide 11 text

© 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. AI coding tools excel at small tasks but can fail with complex projects Scaling AI development Getting a project from proof-of-concept to production while maintaining quality control becomes increasingly difficult Code quality Existing tools make it difficult to collaborate with and manage agents Limited control Challenges with AI development

Slide 12

Slide 12 text

© 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. AI orchestrates the development process with planning, task decomposition, architectural suggestions etc. Developers retain the ultimate responsibility of validation, decision- making and oversight. AI-Driven Development Lifecycle (AI-DLC)

Slide 13

Slide 13 text

Slide 14

Slide 14 text

© 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. AI-Driven Development Lifecycle (AI-DLC) 1. Build Context on Existing Codes 2. Elaborate Intent with User Stories 3. Plan with Units of Work 4. Domain Model (Component Model) 5. Add architectural components 6. Generate code & Test 7. Genrate IaaC & tests 8. Deploy in production with IaaC 9. Manage incidents Each Step Builds Richer Context for the Next Inception Construction Operation

Slide 15

Slide 15 text

Slide 16

Slide 16 text

© 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Construction : Mob Construction Mob Construction Future Developer Teams Building in Parallel & Collaborating The “Persona” of Future Developers ü Moving up the value chain (“tickets to code” to “business ambitions to code”) ü Iterating at the speed of judgement ü Continuous flow, maximum developer satisfaction ü Transcend the rigid specialisation silos ü An order magnitude more effective

Slide 17

Slide 17 text

© 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Vibe coding Spec-driven development Kiro helps developers and engineering teams ship high quality software with AI agents Solution: Spec-driven development Vibe coding ships the prototype, traditional SDLC practices ship the product PLANNING DESIGN IMPLEMENTATION TESTING & QA DEPLOYMENT MAINTENANCE ISSUES FOUND

Slide 18

Slide 18 text

Slide 19

Slide 19 text

Slide 20

Slide 20 text

Slide 21

Slide 21 text

Slide 22

Slide 22 text

Slide 23

Slide 23 text

Slide 24

Slide 24 text

Slide 25

Slide 25 text

Slide 26

Slide 26 text

Slide 27

Slide 27 text

Slide 28

Slide 28 text

Slide 29

Slide 29 text

Slide 30

Slide 30 text

Slide 31

Slide 31 text

Slide 32

Slide 32 text

© 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Take away • Embrace the new boundaries among different roles • Leverage AI to boost up learning journey • Embrace multiple viewpoints for solutions design • Judge, Act, Refine plan to the moon

Slide 33

Slide 33 text

Slide 34

Slide 34 text