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:
projetos/
├── 01-projetos/ # Active projects (frontend & backend apps)
├── 02-pacotes/ # Shared packages (e.g., UI kits, libraries)
├── 03-playground/ # Sandboxes and experiments
├── 04-docs/ # Auxiliary or legacy material
├── 05-arquivo/ # Historical, paused, and temporary material
├── 06-scripts/ # Workspace automation and CLI tooling
├── 07-github/ # Local mirror of external repositories
├── 08-operacional/ # Backups, artifacts, and operational logs
├── docs/ # Canonical documentation hub
├── tests/ # End-to-end and governance testing
├── tasks/ # Active sprint, lessons, and progress tracking
├── plans/ # Transient implementation plans (TDP mode)
├── skills/ # Antigravity/Agent extensions and specific toolsets
├── .agent/ # Agent rules and workflows (Antigravity/Gemini/Claude)
└── mcp-servers/ # Local Model Context Protocol servers
