Escribiendo desde dentro del SDLC nativo de IA .

The Squirrely Anarchist and Other Agents I Have Known

The Product vs. The Work: Managing Engineering Exhaust in the Age of AI Coding Agents

The Clockwork Candidate: What Happens When Inbound Costs Nothing

Three applications, seventy minutes apart, identical echoes. Notes on the industrialization of synthetic hiring.

The Claudish Tax: What Four Months of Opus Prose Cost Us, and How to Sweep It Out

No. You Don't Need Cryptographic Hashing.

How to Corral Gemini for Agentic Coding

Forcing Claude Code to Speak Human

Part 4: Real-Time Pipeline Diagnostics

Calibrated Flake vs. Regression Triage in Automated Builds

Part 3: Governing the Inner Loop

Fast Probabilistic Guardrails for Autonomous Agents

Building on Rented Intelligence: The Receipts Behind Claude's Silent Downgrade

Part 2: High-Speed Boundary Classification

Protecting Ingress with Calibrated Probabilities

Part 1: The Missing Primitive in Agentic AI — Kicking the Tires on TypeSafe's Jev

The Missing Primitive in Agentic AI — Kicking the Tires on TypeSafe's Jev

Resolving a Council of Independent AI Reviewers into a Single Decision

Council Calibration: How Four Agent CLIs Handled a Bounded Research Task

Operational Notes: Orchestrating Multi-Agent CLI Councils Inside Herdr

Incident recap: a fully specified planning task, and how Claude Code still got it wrong

The Information Ladder in the AI SDLC

Clod Code 2.0

Or How to Burn Customer Trust

Flower Power

Why daisyUI Is Great for Modern Projects