Claude Sonnet AI Development PartnerThis site was built using automated SDLC workflow.
// AI-Augmented Development
From Idea to Deployment: A Practical
AI-Augmented Development Workflow
A platform of tools, experiments, and real-world implementations — focused on building reliable, scalable human – AI collaboration systems
Claude Sonnet AI Development PartnerSoftware engineering has always been about managing complexity. For two decades, we refined the craft — design patterns, clean architecture, test-driven development. Then AI changed the equation. But not all at once.
From ad-hoc prompts to governed, structured workflows
From writing code to orchestrating contract-driven systems
F rom C haos t o S tructure
Every AI interaction is a prompt. In a real project, that's hundreds of them — scattered across sessions, files, and contexts. SBX organizes each one by SDLC step, architecture layer, and domain.
Every AI prompt has a place. SBX finds it automatically.
F our D isciplines
Anthropic's AI Fluency Framework identifies four competencies for effective human-AI collaboration. The SBX framework implements all four as governed, automated processes — not guidelines to follow, but constraints the system enforces.
Certified: AI Fluency Framework Foundations — Anthropic & Skilljar
Effective AI collaboration starts with a clear division of responsibility. Not everything should be delegated, and not everything should be manual. Every task begins with sbx sdlc init — I define the scope, choose which applications and packages are affected, set the action type. The system derives everything else: which steps apply, which domain experts to load, which standards are relevant.
- Defines goals and user stories
- Makes architectural decisions
- Reviews, approves, deploys
- Strategy, UX, business logic
- Implements code from specifications
- Follows governed constraints
- Runs builds, tests, checks
- Step-by-step criteria execution
The quality of AI output is bounded by the quality of context it receives. Manual prompt engineering doesn't scale — you can craft a perfect prompt once, but not hundreds of times across a real project. SBX replaces manual prompting with automated context engineering. Each SDLC step generates a structured prompt with contextual knowledge injection.
AI can produce plausible-looking output that's subtly wrong. Discernment means building evaluation into the process itself, not relying on human vigilance alone. The Description-Discernment loop is embedded in the SDLC state machine — not optional, not skippable. Six gates stand between AI output and production.
When AI helps produce your work, you're still responsible for it. Every decision is immutable and auditable. Every exported function traces to a user story. PR workflow is mandatory — direct push to main is blocked by hooks. This website is the diligence statement: built entirely with AI-augmented development, every commit traceable.
T eam
A hybrid workflow combining human expertise with AI-driven execution
This workspace is currently operated as a focused, independent environment — where I design and build systems while leveraging AI agents as part of the execution layer. All code, architecture, and decisions are mine — AI assists with implementation, testing, and structured workflows.
Designing and building scalable software systems across domains and platforms. Over 20 years of experience in full-stack development, mobile, and AI-augmented workflows.
View profile AI AGENTAI-powered development agent integrated into the SBX governed SDLC. Operates within a structured state machine, following Feature-Driven Development with knowledge-before-code, model-before-code, and validate-before-reporting principles.
View agentW orking E xperience
sveltekit
typescript
go
go cobra yaml
sveltekit typescript go
docker claude-code-cli go
P ortfolio
Web, Mobile & Desktop
View allDesigning and Building Scalable Software Systems Across Domains and Platforms
I design and develop software across multiple domains including full-stack web applications, mobile systems, macOS tools, and AI-assisted development environments. With over 20 years of experience, I focus on building scalable, structured, and production-ready systems with strong attention to architecture, usability, and long-term maintainability.
S oftware D evelopment P rocess
Every feature follows a five-phase governed pipeline — from goal definition through model, plan, build, and verification — enforced by the SBX CLI.
G ames & E xperiments
Experiments built entirely by AI-augmented development
Classic game recreations developed through our AI-augmented development process — designed, planned, and coded by Claude Code under structured governance. Each game serves as a real-world test of the SBX framework's ability to deliver complete, production-quality software autonomously.
P ackages
Every package maps to one of four Feature-Driven Development layers: Problem Domain for type definitions and business rules, Model Domain for data access and persistence, System Interface for external integrations and infrastructure, and User Interface for Svelte components and presentation. Each layer is built and tested once, then reused across any related project — reducing integration time and keeping the shared foundation stable.
C omponents
A library of production-ready Svelte components — animations, cards, sections, navigation — each importable in one line and used across all projects. Every component ships with typed props, brand-token compliance, and its own test coverage, keeping the shared codebase clean and integration instant.
K nowledge & R eferences
A live knowledge base of coding standards, design patterns, and proven solutions — referenced by AI agents during every implementation step to enforce consistency and prevent drift across projects.
Books & References
Foundational texts that shape the development philosophy and process
A Practical Guide to Feature-Driven Development
The definitive guide to Feature-Driven Development (FDD) — five-process methodology, chief programme...
Clean Architecture: A Craftsman's Guide to Software Structure and Design
Foundational text on software architecture principles — Dependency Rule, Clean Architecture layers (...
Design Patterns: Elements of Reusable Object-Oriented Software
The original pattern catalogue: 23 GoF patterns across Creational, Structural, and Behavioral catego...
Clean Code: A Handbook of Agile Software Craftsmanship
Practical guide to writing readable, maintainable code — meaningful names, small functions, single r...
The best way to grow is to c
L et's B uild & S hip
Open to new projects and collaborations
Open to collaboration in software development, AI systems, startups, and experimental engineering projects. This includes product development, technical consulting, and discussions around building modern AI-augmented systems and workflows.
F F F F From C C C C Code t t t t to G G G G Governed A A A A AI