Tag: AI

All the articles with the tag "AI".

• Code Review Tools Have a Pricing Problem

  Code review vendors planned for a 2x increase in volume. Agent-driven development is delivering 100x. Per-seat unlimited pricing breaks when a single seat generates 1,000+ PRs per day.

• Assisted, Native, Industrialized

  Developers moved from assembly to FORTRAN and never went back. The same thing is happening to the act of writing code itself. Four modes of AI development—suggestions, assisted, native, industrialized—each a step change that only reverses when the platform breaks underneath you.

• Runbook

  AI agents run faster than you can watch them. The bottleneck is DevLT: minutes of developer attention per trusted change. Runbook turns the MX Creative Console into a physical instrument that optimizes for DevLT.

• xchecker: Spec Pipeline for LLMs

  Keep your code monster under control with xchecker: a Frankenstein spec harness that stitches Rust safety to LLM creativity in an auditable flow.

• Proactively Augmented Generation (PAG): Stop Paying LLM Prices for Repo Search

  Background indexing is a solved problem. LSPs have done it for years. Then AI tooling regressed to synchronous grep. PAG applies well-understood techniques to the LLM context window as a first-class budgeted resource, using cheap traditional tools during the dead time your dev loop already has.