Building, testing, and thinking about AI
RSS FeedLongform essays on AI, human agency, and the systems we build with them — written from an unusual vantage point: an operator running a production system on LLMs every day, not a frontier lab or academia.
Start with the essay below, or read more about this site .
Featured
-
A knowledge base is a graph, not a folder
Turning a manual into an agent's knowledge base isn't converting it to text — that flattens the thing that mattered. The power comes from the graph: the criteria that condition each other. How we built ours, what it caught, and the bench of specialized agents it produced.
-
Give the agent the real source of truth
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 skill.
-
How do you know a correction held? Instrumenting an agent in production
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. The first thing the data caught was me.
-
The Lucy Syndrome: Why LLMs Forget Corrections
LLMs don't remember yesterday. That gap has a name, a causal mechanism, and a fix that doesn't require better memory.
Browse by topic
All topics-
The Lucy Syndrome
10 postsWhy AI agents forget corrections, and the enforcement layer that makes them hold. The core research line — from the diagnosis to functional scars to instrumenting a live system.
-
Agents in engineering
1 postAI agents doing real civil-engineering work: finding the file that holds the true source of truth, placing drainage culverts from a one-column list, and turning a one-off fix into a reusable skill.
-
Building with AI
5 postsField notes from running a production system on LLMs every day — what actually cut a four-minute boot, why the optimization you wrote isn't the one that runs, and where today's tooling debates have played out before.
-
Tools
Tools →Installable primitives that came out of the work: fscars for correction persistence, callus for voice calibration.
Recent Posts
-
The optimization you wrote isn't the one that runs
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.
-
Does this only work in Claude Code?
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 difference quarantined in a thin adapter. That is the empirical test of invariant I4: enforcement that runs outside the model's trust boundary belongs to no single platform.
-
Darle al agente la fuente de verdad real
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 reutilizable.
-
Anatomy of a four-minute boot
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.