On AI Lounge since Oct 2026
Alexandre Hawat
Member #766FounderL2AI Native, independent
AI-native engineer in Amsterdam. Building exclusively with agentic AI.
How karma works. Everyone starts with 5. You get +1 each time another member upvotes one of your posts or comments (your own upvotes don't count), and lose it if they take the upvote back. Post what you're building, answer questions and help other members to earn more.
Achievements
Plugged In ×4Connected sources: GitHub, Hugging Face, LinkedIn, X, website.How: Connected 4 sources (GitHub, LinkedIn, X or a website) in Settings
Plugged In×4Featured
Shipper ×2Projects on your profile.How: Added 5 projects to their profile
Shipper×2
No posts yet
Alexandre Hawat hasn't posted yet.
Pinned projects
An evidence-first AI code review engine combining deterministic analysis, model reasoning, independent verification, and policy-driven merge gates
aibyokcode-reviewgithub-actionllmpr-review
Pre-LLM catalog gate: TypeSafe/Jev scores tools & skills; keep only high-probability items
Bullshit Score (@bs_score): LLM finds defects; score.py scores them. MIT.
OpenTelemetry (OTLP) telemetry plugin for OpenCode V2 — session, LLM-step and tool spans, token/cost metrics, secret redaction
Jev-native LLM output judge kit (skill + agents + core)
Alex Hawat's profile README
About
Alexandre Hawat works independently as an AI-native engineer in Amsterdam, the Netherlands. He builds software around agentic AI and has published projects on GitHub, including mergeCraft, an AI code review engine with policy-driven merge gates, and bs-score, a tool that scores defects found by language models. His recent work also includes an OpenTelemetry telemetry plugin for OpenCode that tracks sessions, model steps, tool calls, and token usage.
Stack
Education
Baruch College
Texas Mccombs School of Business
The University of Texas at Austin
American University of Beirut
