by Javier Elorduy | Oct 2, 2026 | Artificial Intelligence
RAG data engineering brings us back to one of computer science’s oldest warnings: garbage in, garbage out. Large language models did not make that warning obsolete. They made it more expensive to ignore. When a Retrieval-Augmented Generation system begins producing...
by Javier Elorduy | Sep 4, 2026 | Artificial Intelligence
Corporate AI rarely fails because it cannot find a document. It fails because it cannot see how that document connects to everything around it. A traditional RAG system may retrieve the right paragraph and still miss the contract, customer, regulation or decision that...
by Javier Elorduy | Aug 25, 2026 | Artificial Intelligence
In traditional software, a green dashboard usually means the system is alive. With generative AI, that green light can be dangerously reassuring. The model may answer in milliseconds, return no error and still give the user something misleading, irrelevant or...
by Javier Elorduy | Aug 6, 2026 | Artificial Intelligence
Let’s begin with an exercise in technical honesty. Today, building an AI assistant that answers questions about internal documentation is surprisingly easy. A junior developer can assemble a convincing demo in an afternoon with Python, an orchestration framework, and...
by Javier Elorduy | Jul 8, 2026 | Artificial Intelligence
We have normalized a dangerous lie about AI latency in business: if the answer is good enough, the user will forgive the wait. In production, they rarely do. Friction destroys adoption. If an internal sales assistant or analytics tool leaves someone staring at a blank...