Heavy Chain Engineering logo

Writing from inside the AI-native SDLC.

What I'm learning shipping agent-built software in production: debugging loops, throughput math, and the metrics that actually move.

Subscribe via RSS Opens in a new tab
AI Attribution Policy

Oct 7, 2026DesignAI

Escaping the Two Rounds of AI Slop

How Lessons from Real Designers Helped Me Build a Socratic Design Loop for Technical Minds

  1. Oct 7, 2026AISoftware Engineering

    The Squirrely Anarchist and Other Agents I Have Known

  2. Oct 5, 2026AISoftware Engineering

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

  3. Oct 2, 2026AIhiring

    The Clockwork Candidate: What Happens When Inbound Costs Nothing

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

  4. Sep 30, 2026AISoftware Engineering

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

  5. Sep 27, 2026AISoftware Engineering

    No. You Don't Need Cryptographic Hashing.

  6. Sep 25, 2026AIgemini

    How to Corral Gemini for Agentic Coding

  7. Sep 24, 2026AISoftware Engineering

    Forcing Claude Code to Speak Human

  8. Sep 23, 2026AISoftware Engineering

    Part 4: Real-Time Pipeline Diagnostics

    Calibrated Flake vs. Regression Triage in Automated Builds

  9. Sep 22, 2026AISoftware Engineering

    Part 3: Governing the Inner Loop

    Fast Probabilistic Guardrails for Autonomous Agents

  10. Sep 21, 2026AIclaude

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

  11. Sep 21, 2026AISoftware Engineering

    Part 2: High-Speed Boundary Classification

    Protecting Ingress with Calibrated Probabilities

  12. Sep 18, 2026AISoftware Engineering

    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

  13. Sep 18, 2026AI#softwareengineering

    Resolving a Council of Independent AI Reviewers into a Single Decision

  14. Sep 17, 2026AI#softwareengineering

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

  15. Sep 16, 2026AI#softwareengineering

    Operational Notes: Orchestrating Multi-Agent CLI Councils Inside Herdr

  16. Sep 14, 2026Artificial Intelligenceclaude-code

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

  17. Aug 27, 2026Artificial IntelligenceSoftware Engineering

    The Information Ladder in the AI SDLC

  18. Aug 22, 2026

    Clod Code 2.0

    Or How to Burn Customer Trust

  19. Aug 5, 2026Artificial IntelligenceSoftware Engineering

    Flower Power

    Why daisyUI Is Great for Modern Projects