← Financial Cloud Cloud Cloud Club · Amarathon 2025 Recap

Vertex Macro|Financial Cloud Cloud · AWS Amarathon 2025

Vertex Macro|Amarathon 2025 Recap 35:From Vibe to Viable with spec driven development

Speaker: Ricardo Sueiras

Session: 35

Session
Summit Dev Lounge2026 Re:cap
01 Encode Architecture as Steering for AI Agents
02 Agent Harness Is the Real Engineering Moat
03 Ask Observability Data in Plain Language
04 Serverless AR Game with Bedrock AgentCore
05 Multi-Agent Quant Backtesting on AgentCore
06 Blog to Slides in Three Minutes with Kiro
AWS Community Day Hong Kong 2025 Re:cap
02 AWS Compliance with Terraform
03 Beginner to Builder An AWeSome Cloud Journey
04 Team-First Serverless Engineering with Laravel & Bref
05 Event Opening - AWS Community Day Hong Kong 2025
06 Agent-to-Agent: Building Interoperable AI on AWS
07 Utilize another telemetry data for faster improvement with AI agent
08 Graduating from Vibe Coding: Spec-Driven Development with Kiro
09 Automated Testing using MCP & AI Agents
10 Modernizing Telecom Security ML Powered Approach
11 Rethinking GenAI Agent: RAG & MCP
12 Disaster and Emergency Response with TAK and AWS
13 Rethinking Serverless Application Workflows from a Testing Perspective
14 Practical AWS FinOps for Cloud Success
15 AI-Powered Global Pure-Alpha Macro Trades on AWS: Revolutionizing Risk-Adjusted Asset Returns
FSI Recap
01 Modern Trade Lifecycle: Trading to Settlement
02 Goldman Sachs: Fast Track your applications onto Cloud - AWS Re:cap Q1/2023
03 Zurich Insurance Group: Building an Effective Log Management Solution on AWS
04 FSI Meetup 2025 Q4 - Brex Database Disaster Recovery
05 FSI Meetup 2025 Q4 - A Graviton Migration Success Story
06 FSI Meetup 2025 Q4 - Stifel Modern Data Platform
07 FSI Meetup 2025 Q4 - Financial Transaction Data Reconciler PayPal
08 FSI Meetup 2025 Q4 - Scaling Resilience
09 Maximizing AI Inference Cost Efficiency: Strategic Adoption of AWS GPU Instances
10 Advanced Agentic AI Design Patterns
11 Build New Modern Apps on AWS
AWS re:Invent 2025
01 Coinbase re:Invent Recap (IND3312)
02 Building the Future Trading Platform Leveraging AI and AWS
03 Trading Innovation: Jefferies' AI Assistant on Amazon Bedrock (IND3315)
04 How FSI Revolutionized HFT Analytics with Agentic AI (GBL302)
05 Improving Distributed Systems with Amazon Time Sync Featuring Nasdaq
06 Amazon Aurora HA and DR Design Patterns for Global Resilience (DAT442)
07 Building Agentic AI: Amazon Nova Act and Strands Agents in Practice (DEV327)
08 Deep Dive into Amazon Aurora and Its Innovations (DAT441)
09 Deep dive on Amazon S3 (STG407)
10 Nasdaq: Build Resilient Infrastructure for Global Financial Services (HMC327)
11 What's New with AWS Lambda (CNS376)
12 Spec-Driven Development with Kiro (DEV314)
13 Amazon's finops: Cloud cost lessons from a global e-commerce giant (AMZ308)
14 Tick to trade latency trading platforms on aws
Government data
01 The AI Era: The Boundary Between Development and Design Is Disappearing
02 On-Device Multimodal AI and Smart-City Practice
03 Large-Model Capability Evaluation and a Method for Landing AI Projects
04 Controlled End-to-End Automation of Government Development with Cloud Agents
05 A New Software Ecosystem for the Agent Era, Seen Through Multi-Agent Systems
06 AI-Driven Macro Quantitative Research and Smart Governance
07 Authorized Operation of Public Data and Smart-Government Practice
08 Putting Data Assetization into Practice: Rights, Compliance, Engineering Governance, and Digital-Government Cases
09 AI for Mental-Health Public Welfare: Governance, Architecture, and Practice of a Trustworthy Platform
Amarathon 2025 Recap
01 A Developer’s Roadmap to Architecting for Agents
02 Amazon Bedrock Data Automation
03 Multi-Agent on AgentCore
04 Building Agentic AI Nova Act and Strands Agents in Practice
04 Accelerating Migration Projects with Kiro using Spec-Driven Development
06 From Matching to Understanding: Personalized AI Search Practice Driven by AgentCore Memory
07 Observe to Optimize – LLM Observability to AIOps Turning real-time insights into intelligent automation
08 Deploying TEAM and Building the Best Engineering Team
09 Five Hard Lessons from Five Years of So-Called Serverless Databases
14 What if AI does my job How Q Developer CLI and Kiro have changed my daily routine
16 Velocity with Vigilance: Security Essentials for Amazon Bedrock Agent Development
26 Run OSS LLMs on a Single H100 Smarter, Cheaper, Faster
28 A Modern Unified Metadata Architecture: New Approaches to Breaking Down Data Silos
29 Serverless MediaOps: Automating Video Workflows with AI on Amazon Web Services
30 Architecting for Efficiency and Reliability with Performance Testing at Scale
31 Connecting the World Through Open Source: Practical Journey of Technology, Community and Global Developer Relations
33 Building Streaming Iceberg Tables for Real-Time Logistics Analytics
34 Accelerating Large-Scale Robot Strategy Training: An Automated Closed-Loop Architecture Based on Kiro, Trainium, and EKS
35 From Vibe to Viable with spec driven development
36 Making Cloud Cost Analysis Smarter: Building FinOps Intelligent Agents with Strands and AgentCore
37 Transform Conversational Agentic AIOps for K8s Using CNCF Kagent, K8sGPT, and Nova Sonic

AI is changing software

● 2023: Helping developers write code faster

● 2024: Generating larger pieces of code and answering questions

● 2025: Completing development tasks end-to-end with human in the loop

Challenges with AI development

● Scaling AI development: AI coding tools excel at small tasks but can fail with complex projects

● Limited control: Existing tools make it difficult to collaborate with and manage agents

● Code quality: Getting a project from proof-of-concept to production while maintaining quality control becomes increasingly difficult

The Vibe

● Rapid, conversational code generation (CHOP)

● Iterative, back and forth

● Ephemeral

● Point in time prompts

● Transient context


The path to spec driven development

Good practices

● Break down large problems: Developers learned how to manually break down large problems into smaller units and build incrementally

● Specificity and Clarity: Precision and clarity are key in directing AI coding assistants to generate good outputs

● Context and Prompt engineering: Providing the right context is key to producing consistency and control


Taskmaster

● A task management system for AI-driven development with Clauide, designed to work seamlessly with Cursor AI

[ 1 ] Documentation:

● Configuration Guide: Set up environment variables and customize Task Master

● Tutorial: Step-by-step guide to getting started with Task Master

● Command Reference: Complete list of all available commands

● Task Structure: Understanding the task format and features

● Example Interactions: Common Cursor AI interaction examples

● Migration Guide: Guide to migrating to the new project structure

[ 2 ] Quick Install for Cursor 1.0+ (One-Click):

● Click the copy button (top-right of code block) then paste into your browser: cursor://anysphere.cursor-deeplink/mc/install?name=taskmaster-aiconfig-eyJjIjI1biWSkI1joibnB4I

● Note: After clicking the link, you'll still need to add your API keys to the configuration. The link installs the MCP server with placeholder keys that you'll need to replace with your actual API keys

[ 3 ] Requirements:

● Taskmaster utilizes AI across several commands, and those require a separate API key. You can use a variety of models from different AI providers provided you add your API keys. For example if you want to use Clauide 3.7

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.

Chat is a bad UI pattern for development tools

● Code forces humans to be precise. That's good—computers need precision. But it also forces humans to think like machines.

● For decades we tried to fix this by making programming more human-friendly. Higher-level languages. Visual interfaces. Each step helped, but we were still translating human thoughts into computer instructions.

● AI was supposed to change everything. Finally, plain English could be a programming language—one everyone already knows. No syntax. No rules. Just say what you want.

● The first wave of AI coding tools squandered this opportunity. They make flashy demos but produce garbage software. People call them “great for prototyping,” which means “don’t use this for anything real.”

● Many blame the AI models, saying we just need them to get smarter. This is wrong. Yes, better AI will make better guesses about what you mean. But when you’re building serious software, you need a better approach.


A written specification aligns humans

● The use of EARS notation helps provide precise and structured instructions to the underlying LLMs

What is spec driven development?

● Spec Driven Development: Clarity before code, iterative refinement, code via persistent docs

● Invest time to understand what you are trying to build

● Iterate and capture evolution of what you are trying to build

● From ephemeral chat to persistent documents that can be shared with your stakeholders

Spec Driven Development

● Define the vision: Create clear requirements and design specifications.

● Make architectural decisions: Choose technologies, patterns, and approaches upfront.

● Implement with context: Use AI to generate code that fulfills your documented specifications.

The Vibe

● Prompts to chase implementations

● Rapid, conversational AI code generation (CHOP)

● Iterative, back and forth

● Ephemeral

● Point in time

Spec driven

● Focus on upfront planning and intent

● Break down requests into discrete tasks

● Steering documents ground agentic

The AI IDE for prototype to production

● Kiro helps you do your best work by bringing structure to AI coding with spec-driven development.