AI-assisted engineering workflows | Backend systems, tooling, and scoped automation
I build software with a strong bias toward explicit contracts, predictable delivery, and reviewable automation. I am currently studying Systems Development at SENAI PR, with a focus on backend systems, developer tooling, and AI-assisted workflows that stay useful under real engineering constraints.
- Explicit contracts over implicit behavior.
- Validation should be part of the workflow, not a cleanup step.
- Automation is only useful when scope, permissions, and failure modes are clear.
- Reliable delivery depends on repeatable systems, not improvised heroics.
I use AI tooling as part of a disciplined engineering loop rather than as a substitute for judgment. The objective is faster iteration with small diffs, legible decisions, and concrete validation at every meaningful step.
Typical approach:
- Explore with research-first tooling and map the problem space.
- Plan with explicit constraints, success criteria, and validation paths.
- Implement in small, reviewable changes with local verification.
- Escalate to specialist agents only when the task genuinely benefits from them.
- Close with concrete checks and a clear record of tradeoffs.
Core surfaces:
| Surface | Role |
|---|---|
| Gemini CLI | Research, exploration, and first-pass synthesis |
| Claude Code | Deep reasoning, structural review, and hard debugging passes |
| Codex | Local implementation, refactors, validation loops, and focused edits |
| Antigravity | Scoped sessions, routing, and bounded decomposition |
| MCP | Explicit connectivity between project context, services, and tools |
- Petshop Small Breeds Premium - full-stack system with admin operations, auth flows, booking requests, and deployment discipline.
- Voice Note AI - Windows-first dictation workflow with Azure Speech-to-Text, safe text injection, and adaptive suggestions.
- Clean Express API - API structure centered on validation, consistent errors, and explicit architectural boundaries.
- Backend TS Foundations - Node.js and TypeScript practice focused on consistency, contracts, and delivery fundamentals.
- TradingView Indicator - Pine Script experiments for structured technical analysis and trading automation.
I use MCP surfaces where they improve context transfer, reduce manual friction, and keep tool boundaries explicit.
| Category | Technologies |
|---|---|
| Languages & Runtime | JavaScript (ES6+), TypeScript, Node.js |
| Frontend | React, Next.js, Tailwind CSS, shadcn/ui |
| Backend | Express.js, REST APIs, Clean Architecture |
| Databases | SQLite, PostgreSQL, Prisma |
| Infra & Delivery | Docker, Linux CLI, Git, GitHub, Vercel |
- Strengthen end-to-end projects with auth, observability, and deployment discipline.
- Publish sharper backend baselines with better contracts and operational safeguards.
- Keep refining AI-assisted workflows without relaxing verification standards.
- Keep profile and project documentation aligned with active delivery work.
A live view of my current local workspace architecture, optimized for agentic development:
workspace/
├── 00-inbox/ # Transient intake and triage
├── 01-projects/ # Active repository clones
├── 02-areas/ # Long-term responsibilities
├── 03-resources/ # Reference material & shared assets
├── 04-archives/ # Inactive logs, specs, and history
├── governance/ # Policy, checklists, ADRs, prompts
├── scripts/ # Operational infrastructure
├── AGENTS.md # The Agent Protocol
├── CLAUDE.md # Agent-specific adapter
├── GEMINI.md # Agent-specific adapter
└── README.md # Workspace main guide
