AI
Your AI agent said “done.” How do you know it worked? ↗
Evaluate AI agents by their final state, test retries and partial failures, and measure quality and cost per task that actually passes.
EXPLORE / ERNANI.DEV
AI agents.
Ideas born from practice. Explore the topics and find your next read.
Software systems
Who Does Your AI Plugin Work For? How to Audit MCPs and Extensions ↗
MCPs and extensions expand what AI can do. Learn to verify provenance, permissions, data destinations, and contracts while distinguishing different risks.
Software systems
Your store's next integration could be with AI: what changes for online sellers ↗
Google and Shopify point to a new shopping interface. Drawing on my integration work at Oombe, I explain why catalogs, pricing, inventory, and authorization remain central.
AI
Claude Duet: AI now wants to follow your work, even when you close the chat ↗
An analysis of continuity, integrations, and everyday decisions: what I would assess in Claude Duet and how I would design a pilot with verifiable results.
Software systems
An AI agent disabled alerts. What does that teach us about automation? ↗
Useful agents need understandable boundaries. An integration example shows how to connect proposals, approvals, and execution while keeping control of operations.
AI
The Performative Programmer in the AI Era and the Cost to Your Organization ↗
AI can make a convincing demo easier to build. Inspired by Mano Deyvin’s “performative programmer,” this article examines the review, rework, security and maintenance costs organizations can miss behind a polished presentation.
AI
AI in Rio de Janeiro's healthcare: from WhatsApp messages to diagnostic support ↗
A meeting on healthcare innovation in Rio de Janeiro connects Serena, Rio Farmes, rare diseases and oncology with the challenges of data, care and municipal modernization.
Software systems
Beautiful Website, Paper-Thin Security: The Risks of Careless Vibe Coding ↗
A polished interface is only the beginning. Drawing on real experience and technical sources, I explore the risks of selling AI-built systems without understanding their security—and how to start responsibly.
Games
GTA VI, AI, and the future of games: who will create, modify, and preserve what we play? ↗
GTA VI is the starting point for a conversation about AI, REA, PS5 jailbreaking, PC ports, and preservation. A look at the possibilities and limits of this transformation from someone who develops systems, integrations, and Unity games.
AI
VisionQuest: Vision, His AI Agents, and the Reality of 2026 ↗
Watching VisionQuest, I see parallels with the AI agents we can build in 2026: specialists working together, different personalities, a race for greater capability, and the question of who gets the administrator password.