Graph Engineering for Normal People: 4 Prompts Fixed the 78% of Work His AI Couldn't Find

Roger_M_Taylor · x · 2026-09-15

Charlie Hills wrote a long piece on practical graph engineering in Claude Code: his AI couldn't find 78% of his work until four prompts fixed it. He breaks the trendiest concepts into four layers — Context (what's actually in the window), Harness (standing rules, tools and skills bolted on), Loop (the AI QAs itself until it passes), and Graph (where your stuff lives and what connects to what) — noting "graph engineering" only got its name this summer, though the problem is old. He lays out how the four work together as one run — the graph feeds the harness, the harness loads the context, and a failed gate loops back — and shares all four prompts with their outputs in his newsletter.

Original post →

More from coding & agent

coding & agent channel →