Home / Articles / If somebody built a company on code review / Versions / v1.4.0
If somebody built a company on code review: what changed in v1.4.0
From v1.3.0 (2026-10-05, 0ad26f6e6) to v1.4.0 (2026-10-05, dc11503b4), paragraph by paragraph.
0 paragraphs added, 0 removed, 3 changed in place, 129 unchanged. About 5 words added and 0 removed. Insertions are marked like this, deletions like this; unchanged runs are folded to one line; figures appear as their file names.
← v1.3.0 · all versions · v1.5.0 →
5 unchanged paragraphs, under In short
• One technology can read every layer. People moved between strategy and source code by instinct, and it neverdid scaled,not scale, because nothingno one tool could process every altitude in one pass. A language model can, from a board objective to a syntax tree, in one path or delegated to sub-agents. That is what makes a graph at every layer buildable, and buildable close to reality, and it is why the companies that spent fortunes trying this before could not.
13 unchanged paragraphs, under One technology, every layer
Most of what follows is something good engineers have always done by instinct. A senior reviewer reads a diff and sees the story it breaks; an architect looks at a pull request and sees a boundary crossed; a product owner reads a commit message and knows the feature it does not finish. The move between altitudes, from what the business wants to what the code does, has been made in people's heads for as long as there has been code review, sometimes deliberately, mostly by instinct. What hasdid nevernot scaledscale iswas doing it explicitly, because nothingno one tool could process every layer. The tools that read syntax trees could not read a strategy document, and the people who read strategy documents did not read syntax trees, and the layers in between were held together by meetings.
49 unchanged paragraphs, under From art to science, The grammar is fractal, the layers are yours, Build the graph from the top, before the code exists…
This is where the company sits. In the two moves. From explorer to villager, when a guess becomes a product and needs a review it never had, and the graph has to be built for the first time from code that was written to be thrown away. From villager to town planner, when a product becomes a commodity and the review becomes a set of checks that run without anyone, and the graph has to be good enough to be the checks. The trap on both sides is the same, and the May 2026 article on how vibe coded apps actually ship names it: teams discover that a model's mistakes are too risky and swing to the other extreme, reviewing everything by hand, which the volume of generated code makes impossible,impractical, and both extremes come from not knowing which stage the code is at.
62 unchanged paragraphs, under Review is not saying no, Replicate reality first, Constraints keep it in control, the five whys make it cheaper…