8000 jrlucas1 (João Raul Furtado Lucas) · GitHub
[go: up one dir, main page]

Skip to content
View jrlucas1's full-sized avatar

Block or report jrlucas1

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
jrlucas1/README.md

Hello, I'm João Raul Furtado Lucas 👋

🚀 About Me

I'm a Software Engineer based in Porto Alegre, Rio Grande do Sul, Brazil, focused on backend development and performance optimization for regulated financial systems. I build high-volume services where reliability comes down to disciplined error handling, idempotency, and retry behavior — tax-authority integrations, reconciliation, and post-trade processing.

I work extensively with AI-augmented development and agentic coding tooling, and I like diagnosing bottlenecks, tuning complex queries, and shipping real-time data processing for high-throughput environments.

🛠 Skills

Languages & Frameworks

  • C#, .NET 8, ASP.NET Core, Entity Framework Core, Dapper
  • Python, TypeScript, Node.js
  • WebSockets, REST APIs

Databases & Caching

  • SQL Server (advanced indexing, profiling, T-SQL)
  • Redis

Cloud & DevOps

  • Microsoft Azure (Functions, App Service)
  • Docker, Git, Azure DevOps (CI/CD)

Architecture

  • Clean Architecture, Domain-Driven Design
  • Microservices, Distributed Systems, Test-Driven Development

AI Engineering

  • Claude Code, Model Context Protocol (MCP)
  • LLM Integration, LangChain

🔭 What I'm Building

  • Superpowered Ralph — an autonomous coding agent that takes an idea to verified, review-ready code using a phase-based state machine and parallel sub-agents.
  • Critique Hook — a provider-agnostic adversarial peer-review layer that intercepts AI coding-agent output before changes land.
  • Timesheet Automation — a full-stack app consolidating activity from Jira, GitHub, and Azure DevOps with LLM-based work-log summarization.

📫 How to Reach Me

Pinned Loading

  1. claude-critique-hook claude-critique-hook Public

    Adversarial second-opinion for Claude Code plans — a different LLM critiques every plan Claude writes

    Python 1

  2. claude-superpowered-ralph claude-superpowered-ralph Public

  3. resume resume Public

0