The engineer who learned by building: How Rilton Franzone became a legal AI specialist

2026-05-25 · Source: Dataconomy · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering · Depth: Intermediate, short

Summary

Rilton Franzone, a legal AI specialist, began his engineering career debugging production systems at 17, having learned programming from online courses at Harvard, MIT, and HKUST. He quickly became a full-time engineer, shipping features and maintaining systems. His career path emphasized usefulness over early specialization, leading him to contribute across fintech, academic research tooling, mobility, logistics, and SaaS, including building infrastructure for millions of loan applications at WithClutch and web crawlers for 400,000 ML code implementations at CatalyzeX. In 2025, Franzone joined Midpage.ai as its third engineer, developing its legal AI research agent, now used by over 300 law firms in the United States. This system ranks among the top three legal AI systems globally on VLAIR's benchmark, outperforming ChatGPT. He also led integrations with partners like Perplexity and OpenAI, and developed benchmark.midpage.ai, an evaluation framework for complex legal AI tasks.

Key takeaway

For AI Engineers building high-stakes systems, particularly in legal or professional domains, prioritize learning through practical application and continuous iteration. Your focus should be on delivering genuinely useful, reliable products that provide verifiable evidence. Implement robust evaluation frameworks like benchmark.midpage.ai to distinguish fluent outputs from truly correct ones, ensuring your systems meet critical accuracy and trust requirements.

Key insights

Learning by building and prioritizing usefulness in high-stakes domains fosters effective, reliable engineering.

Principles

• Learn by building, not theory first.
• Specialize in problem-solving, not narrow roles.
• Strong evaluation distinguishes fluent from correct AI.

Method

Assess situations independently, identify system constraints, apply technical leverage, and improve incrementally.

In practice

• Develop systems providing supporting evidence.
• Integrate AI tools into professional workflows.
• Use benchmarks to validate AI accuracy.

Topics

• Legal AI
• AI Engineering
• Benchmarking
• Production Systems
• Midpage.ai
• Evaluation Frameworks

Best for: AI Engineer, Software Engineer, Legal Professional

Related on AIssential

• The Sequence Opinion #860: Every Company’s Last eXam: Some Reflection About Practical AI Evals — Company-specific, dynamic evaluations are now essential for production AI, forming a fourth pillar alongside compute, data, and models.
• I Stopped Chasing AI Hype and Started Building Systems That Actually Worked — Focus on practical problem-solving and friction removal to build effective AI systems, not just advanced features.
• Designing lawyers: Attorney growth in the age of AI-fueled practice — AI necessitates redesigning lawyer development to preserve judgment and expertise amidst task automation.
• Presentation: Using AI as a Thinking Partner for Large-Scale Engineering Systems — AI acts as a "thinking partner" to manage cognitive load in large-scale engineering systems.
• AI Engineering Book Summary — AI engineering prioritizes integrating pre-trained foundation models via APIs over training from scratch.
• Context Engineering as Your Competitive Edge — Context engineering, integrating domain knowledge, tools, and memory, creates durable AI competitive advantage.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Dataconomy.