Victordelpuerto

I moved 177 entries out of an index and the consistency check went green without looking at any of them. Over nineteen days I collected twenty-four of these across modules that never met, and they sort into seven structurally different reasons a check can

An agent knew the manual's minimum radius cold and still got the curve wrong, because the number was only the start of the question. Why a domain agent reasons better from a graph of criteria than from a persona prompt, and what that structure caught in r

I tagged sixty hook activations, concluded retrieval was fine, and wrote down a verdict. Then I measured the prompts where the hook said nothing at all, and the number flipped.

Ninety days ago I started enforcing corrections outside the model. This week I pulled the first real metrics, and it is a mixed result. The busiest hook gets ignored 62% of the time, two of my own tools disagreed about the same number, and the dashboard s

I had the optimization written and approved, and a week later it still wasn't what ran. The fix wasn't a better design. It was making the trigger deterministic and leaving the judgment to the model.

The most common objection to the Lucy Syndrome framework is that it's a Claude Code trick. It isn't. OpenAI shipped a native hook API for Codex, and the same functional scar now fires unchanged in both runtimes with identical deny semantics - the differen

Un agente de IA que llamo MARCO colocó 26 obras de drenaje en el software de diseño vial a partir de una planilla. Lo interesante no fue la velocidad, sino encontrar en qué archivo vivía el pie de talud real, y convertir esa solución en una skill reutiliz

An AI setup I call MARCO placed 26 drainage culverts into our road-design software from a one-column list. The speed wasn't the interesting part. What mattered was finding which file held the real toe of the slope, and turning the fix into a reusable skil

Where my Claude Code sessions actually spent their first four minutes, and what cut it to thirty seconds without losing any context. Hooks were three seconds of the problem. The model's diligence was the rest.

Functional scars make a correction persist. They don't tell you whether the system as a whole is getting better. So I instrumented every session - deterministic, zero-token, never blocking - and let a monthly pass turn the evidence into mechanism changes.