Skip to content
neℓson

ἓν οἶδα ὅτι οὐδὲν οἶδα

Ideas

Raw thinking, critiques, and positions still being tested.

Useful ideas do not need to wait until they are fully productized or socially polished.

Ideas 2026-05-11

Code Review Changed Before Most Teams Realized It

AI-assisted development made code generation cheaper, shifting code review's bottleneck toward context reconstruction and reviewer-oriented context engineering.

Ideas 2026-05-06

Codex `/goal` changes the developer loop

Codex `/goal` turns agent work from prompt-by-prompt steering into a goal-driven loop with completion defined up front.

Ideas 2026-05-05

From compute power to productivity

Measure AI productivity by how human judgment, compute, context, and control loops become resolved engineering work.

Ideas 2026-04-25

When agent-generated UI is usable but not yet excellent

Agent-generated UI becomes maintainable after the first usable pass is cleaned up for structure, boundaries, and extension.

Ideas 2026-04-05

Agent loops should tighten engineering feedback, not replace judgment

Agent loops create leverage only when they make verification cheaper without hiding state, ownership, or reasoning.

Ideas 2025-12-03

Edge preview environments need a control plane

Edge preview environments need a control plane that separates image caching, desired state, ingress, TLS, and runtime intent.

Ideas 2025-09-05

GitHub Actions should separate delivery from diagnosis

CI governance improves when delivery, diagnosis, telemetry, and decision loops are modeled as separate but connected planes.

Ideas 2025-06-10

A delivery loop for agentic engineering

A spec-first agent delivery loop keeps speed useful by preserving review points, validation signals, and production ownership.

Ideas 2019-10-04

What a long-running product teaches you

Long-running products preserve old assumptions in names, routes, packages, dashboards, and team habits after people forget.