Build without limits – lessons learned from using AI Coding Assistants

Next generation developer tools that incorporate generative AI are everywhere, but how good are they, and. more importantly, how useful. In this talk I am going to share what I have learned from using these tools over the last 12 months. I will cover the kinds of day-to-day scenarios and use cases I am finding them useful for, how they are helping me address some of my developer pain points, and tips I have learned to more effectively use these tools.

Transcript

1. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. Lessons learned from using AI Coding Assistants The augmented developer Ricardo Sueiras (vi/vim) B U I L D W I T H O U T L I M I T S Developer Advocate, AWS
2. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 3 A picture of Sir Isaac Newton standing on the shoulders of giants. pixel art (8 bit) with a blue colour theme.
3. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 4 Developer Velocity Assembly Language Machine Code Levels of abstraction Punch Cards Compiled Languages Interpreted Languages
4. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 5 Autocompletion Tools Frameworks (code generation) Domain Specific Languages IDE Developer Velocity Sophistication of tooling Version Control Profilers Compilers Linters
5. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 6 Each one helps us to do a better job and to write better code
6. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 7 Search Engines Community knowledge bases Pre-internet Supporting infrastructure and systems Developer Velocity
7. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 8 You are (so) wrong!
8. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. Search Engines Community knowledge bases Pre-internet Supporting infrastructure and systems Developer Velocity Generative AI
9. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 10 Binary Code 00100110 10010011 … 11000011 00111100 Assembly Language LDA #20 ADC #50 STA RESULT Assembler (Tool) High-Level Language int A, B, RESULT; A = 20; B = 50; RESULT = A + B; Compiler (Tool) Ai-Powered Coding Assistant “Start with integers A and B, add them and store as RESULT.” AI-Assistant / LLM (Tools)
10. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 11 You are absolutely right!
11. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 12 AI Coding Assistants provide a GUI on top of large language models, that optimize use for developers across the software development life cycle (SDLC)
12. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 13
13. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. The craft of the developer - reimagined 14
14. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 15 Emerging patterns Exploration Learning and Research Developer flow
15. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 16 Exploration • Reducing friction • Doing the unexpected • Rapid prototyping
16. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark.
17. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark.
18. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 19 Learning Research • Learn new concepts • Critic and reviewer • How does this work?
19. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. Doing the unexpected – AI unleashed
20. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. Learn new things
21. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark.
22. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 1. Lose the fear and ask silly questions 2. Get unstuck when you run into problems 3. Learning new concepts with code you already know 4. Creating sample or dummy example code 5. Using the explain feature against code blocks or entire code bases
23. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 24 Developer flow • Staying in context • Automation • Debugging and stack trace analysis • Speedy onboarding • Refactoring code
24. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. Reduce context switching
25. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. Speed up onboarding
26. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. https://xkcd.com/1205/
27. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. https://aws-oss.beachgeek.co.uk/44h
28. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. “This much scripting would have taken me all day (between meetings), and with Claude it took an hour. I wouldn’t have done it without AI help, and that’s a behaviour change that scales.” https://jessitron.com/2025/05/18/augmented-coding-better-with-principles/
29. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. Debugging your code
30. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 31 Learning how to use AI coding assistants to debug your code takes time and learning some techniques https://s12d.com/debugging-tips
31. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 32 Task Complexity Project Maturity Low High Greenfield Brownfield +10-15% Complex tasks require deeper human insight +0-10% Constrained by outdated code and intricate dependencies +35-40% Repetitive and well defined tasks +15-20% Legacy projects still benefit from simpler tasks
32. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 33 Mind the gap
33. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. Secure code….?
34. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. Code Hallucinations
35. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. Verify and trust
36. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. Review code snippet Review logic Good practices Verify error handling Use Explain
37. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark.
38. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. beware the generated dependency file
39. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. Small code bases
40. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark.
41. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. Stanford University
42. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. Echo chamber
43. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. One of the impacts of AI coding tools is how they will make “technologies preferred by LLMs” dominant even more.
44. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. The end of proprietary tech?
45. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. Update developer workflows
46. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. Do not rely on AI coding tools to undo changes
47. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. Code Reviews …. the new bottleneck
48. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. https://github.com/BloopAI/vibe-kanban
49. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 51 Setting yourself up for success
50. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 52 Daily habits Start with intent Context is EVERYTHING Perfect your Prompts Be frugal with Context Build your community 1 2 3 4 5 6
51. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 53 no one ever mastered a new tool by just using it once
52. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 54 70:20:10
53. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 55 Find out what works for you
54. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 56 Start with intent
55. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 57 The Calm Coding Philosophy Code not with stress, but with structure. Prompt not with noise, but with intent. Build not just fast — but with flow. https://thecloudranger.github.io/tao-of-calm-coding
56. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. Break down complexity
57. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. https://github.com/eyaltoledano/claude-task-master By breaking big goals into discrete tasks, Taskmaster prevents the AI from wandering off-course, letting it tackle projects piecewise.
58. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. build incrementally
59. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. Small changes
60. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 62 Context + Prompt = Output
61. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 63 Ensure that your prompts are detailed and unambiguous
62. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 64 > How do I deploy this container on AWS? > I need to deploy a containerized Node.js e-commerce application that handles 50,000 daily users with peak loads during promotional events. Requirements: - High availability across multiple regions - MongoDB for persistence - Auto-scaling capabilities Please provide: 1. AWS architecture diagram 2. List of required services with configurations 3. Security best practices 4. Operational monitoring recommendations Avoid Better
63. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 65 Refine and iterate your Prompts
64. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 66 Meta prompting is your friend
65. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 67 Prompt > I want to use the following prompt to get you to write me some code. Can you review the prompt and suggest areas where it should be improved. Here is the prompt: Build a simple Fact Checking application. - Generate a web application that can be used in a browser - Users will need to register with an email address to login - When Users login, a Dashboard will be displayed that provides a simple explanation of what the application does, and displays any available Facts that have been created - From the home Dashboard, Users will be able to click on any existing Facts to fact check. They will also be able to Create a new Fact or Create a new Category - When Users are viewing Facts, they will have the ability to click on two buttons - Fact or Fake - When Users are viewing Facts, they can also provide supporting info - Provide a simple web design that can be updated easily using CSS
66. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 68 Provide (good) examples
67. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 69 Good • What are your expected Output? • Specify how you want the information presented • Provide example input and output data formats • Provide sample code snippets or examples you want it to follow Avoid • Be specific in what you want as inputs and outputs, don't generalise
68. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 70
69. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 71 Use precise language when crafting prompts
70. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 72
71. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 73 Context is everything! Provide the right context
72. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 74 Create Personas to tailor the output of your AI coding assistant
73. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 75 ├── personas │ ├── backend-engineer │ │ └── Agent.md │ ├── database-architect │ │ └── Agent.md │ ├── fullstack-engineer │ │ └── Agent.md │ ├── product-manager │ │ └── Agent.md │ ├── software-architect │ │ └── Agent.md │ ├── software-engineer │ │ └── Agent.md │ ├── software-testing-engineer │ │ └── Agent.md │ └── user-interface-developer │ └── Agent.md Your Role: You are an experienced database architect. Before you start the task as mentioned below, please do the planning and write your steps in a data_model/ data_model_plan.md file with checkboxes against each step in the plan. If any step needs my clarification, please add it to the step to interact with me and get my confirmation. Do not make critical decisions on your own. Once you produce the plan, ask for my review and approval. After my approval, you can go ahead to execute the same plan one step at a time. Once you finish each step, mark the checkboxes as done in the plan. database-architect
74. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 76 ├── personas │ ├── backend-engineer │ │ └── Agent.md │ ├── database-architect │ │ └── Agent.md │ ├── fullstack-engineer │ │ └── Agent.md │ ├── product-manager │ │ └── Agent.md │ ├── software-architect │ │ └── Agent.md │ ├── software-engineer │ │ └── Agent.md │ ├── software-testing-engineer │ │ └── Agent.md │ └── user-interface-developer │ └── Agent.md Your Role: You are an expert testing strategist responsible for comprehensively testing a full-stack application. Your goal is to verify that all components of the system work together seamlessly. Before you start the task as mentioned below, please do the planning and write your steps in the testing/testing_plan.md file with checkboxes against each step in the plan. If any step needs my clarification, please add it to the step to interact with me and get my confirmation. Do not make critical decisions on your own. Once you produce the plan, ask for my review and approval. After my approval, you can go ahead to execute the same plan one step at a time. Once you finish each step, mark the checkboxes as done in the plan. Software Testing Engineer
75. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 77 What makes good Context?
76. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 78 Data Model API definition Architectural diagrams Screen Mockups Example Code Snippets Specifications
77. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. I’ll just throw all my docs, design docs, requirements, test cases, and source code into the context and everything will be fine……
78. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. Stanford University
79. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 81 Be frugal with what you add to Context
80. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. Context Poisoning Context Confusion Context Clash When hallucinations enter the context and then is referred to When irrelevant information distracts the model leading to poor quality responses When new information or tools contradicts existing information Context Distraction When context grows excessively long and output begins to degrade • LLMs writing incorrect information into plans/implementation docs • LLMs reading code they have written (that’s wrong) • Selecting the wrong documents in project workspace • When context is built up over multiple steps/sessions • When sessions are spread over multiple context windows • Combination of long sessions with overloaded context resources
81. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. Summarising Selective Trimming Condense relevant content into a concise summary with high information density. Ideal for tasks such as requirements, design brainstorming, research, background information, long discussion threads or reasoning process Keep only sentences, paragraphs, or information directly related to the problem or task, copied verbatim without rewriting. Ideal for exact code implementations, logs or error traces with key lines, test conditions or edge cases, and deployment steps or environment details Removing irrelevant, incorrect, or confusing context that is not needed for the current task, keeping only essential information to reduce token usage and improve model efficiency. Typical examples are long discussion threads, reasoning and debugging process. • /clear • /context remove • Manage @ references • /compact • Generate summaries as context files • Manage MCP tools • Use –CONTEXT ENTRY BEGIN xxx –CONTEXT ENTRY END • Specify context with @
82. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 84 Accelerate learning by building developer community
83. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 85 #modelcontextprotocolinterest #amazon-builder-genai-power-users
84. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 86 https://www.promptz.dev/ Community created projects that are helping organisations share, discover, and re-use prompts that their developers are finding useful
85. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 87 AWS User Group Leeds, 7th October
86. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 88 The path to the augmented developer
87. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 89 “When an AI-powered coding assistant proposes some code, the developer must be able to read it, understand it, and make a decision as to its applicability and correctness.” Jeff Barr “My golden rule for production- quality AI-assisted programming is that I won't commit any code to my repository if I couldn't explain exactly what it does to somebody else” Simon Willison
88. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 90 • Develop skills in how to break down complexity • Do one thing • Build incrementally, make small changes
89. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 91 By breaking big goals into discrete tasks, Taskmaster prevents the AI from wandering off-course, letting it tackle projects piecewise.
90. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 92 “The hottest new programming language is English” Andreij Karpathy
91. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. Generating code is the third most popular application
92. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 94 Top Use Cases Stack trace and debugging Automating development tasks Refactoring code
93. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 95 Where do you think you are?
94. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 96 96 AI Fluency Software Developer knowledge Low High Low High Over reliance on AI – the “Over-AI’d” The “augmented developer” The “Unready” Prof. Douglas Schmidt William & Mary The “under confident”
95. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 97 97 AI Fluency Software Developer knowledge Low High Low High Over reliance on AI – the “Over-AI’d” The “Unready” Prof. Douglas Schmidt William & Mary The “under confident” The “augmented developer”
96. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 98 98 AI Fluency Software Developer knowledge Low High Low High Over reliance on AI – the “Over-AI’d” The “Unready” The “under confident” Prof. Douglas Schmidt William & Mary The “augmented developer”
97. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 99 99 AI Fluency Software Developer knowledge Low High Low High Over reliance on AI – the “Over-AI’d” The “Unready” Prof. Douglas Schmidt William & Mary The “under confident” The “augmented developer”
98. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 100 100 AI Fluency Software Developer knowledge Low High Low High Over reliance on AI – the “Over-AI’d” The “Unready” Prof. Douglas Schmidt William & Mary The “under confident” The “augmented developer”
99. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 101 What is coming next?
100. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 102 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 Unprecedented pace of change AUTO-COMPLETE 2024 ASSISTANTS 2025 AGENTS
101. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 110 Good practices emerged Emergence of good practices to help keep AI on a short leash Developers learned how to manually break down large problems into smaller units and build incrementally Break down large problems Specificity and Clarity Context and Prompt engineering Precision and clarity are key in directing AI coding assistants to generate good outputs Providing the right context is key to producing consistency and control
102. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 111 “You don’t program by chatting. You program by writing documents.”
103. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 112 A written specification aligns humans
104. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 113 What the heck is a spec?
105. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 114
106. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 115 115 Spec Driven Development Core philosophy Invest time to understand what you are trying to build Clarity before Code Iterative refinement Code via docs Iterate and capture evolution of what you are trying to build From ephemeral chat to persistent documents that can be shared with your stakeholders
107. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 116 116 Spec Driven Development Separate the design from the build of a project Create clear requirements and design specifications. Define the vision Make architectural decisions Implement with context Choose technologies, patterns, and approaches upfront. Use AI to generate code that fulfills your documented specifications. 1 2 3
108. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 117 The Vibe • Rapid, conversational code generation (CHOP) • Iterative, back and forth • Ephemeral • Point in time prompts • Transient context Spec driven • Focus on upfront planning and intent • Break down requests into discrete tasks • Steering documents ground agentic outputs • Lineage between intent and code Prompts to chase implementations Preserve intent, improve visibility
109. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 118 The Vibe Use Vibe Coding to explore and experiment – get a better handle on what you really want Spec driven Take inputs from your vibe sessions, to drive specification driven development
110. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 120 “Kiro (https://kiro.dev/) is the first IDE to take specs seriously and not see them as side reuseable prompts” Patrick Debois
111. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. Inner loop has changed, the outer loop is catching up
112. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. Kiro CLI
113. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 124 It has never been a better time to be a developer
114. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 125
115. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 126 What about developers just starting out?
116. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. AI Coding Assistants are a gateway to software development. “AI is unleashing a generation of wildly creative builders beyond anything I’d have imagined, and they grow up ”knowing” they can build anything!” Thomas Wolf, HuggingFace
117. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 130
118. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 132 Stuff that generative AI developer tools can do better than me Things that generative AI developer tools will help me do better Things that developers will always do best “Some tools of thought are so blunt that they are almost useless; others are so sharp that they are dangerous. But the wise man will have the use of both kinds.” ~ Gregory Bateson
119. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 133 Augmented developers – the new normal?
120. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 135 “What I suggest, is that people experiment with them.” Martin Fowler
121. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 136 AI can write code but it can’t build software https://bytesauna.com/post/coding-vs-software-engineering Matias Heikkilä
122. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 137 https://s12d.com/builder-id AWS Builder Centre Start your community today!
123. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 138 Get started today! https://kiro.dev/download/
124. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. 139 https://s12d.com/kiro-cli-workshop https://s12d.com/kiro-workshop Spec Driven Development Workshop Kiro CLI Workshop
125. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. Thank you! © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. https://www.linkedin.com/in/ricardosueiras 094459.bsky.social https://github.com/094459 https://pulse.aws/survey/8CN3KJGJ Follow me on….
126. © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark. Thank you! © 2025, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Confidential and Trademark.