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.
More from coding & agent
- GPT-6 Astra demos: playable games, robot demos and 3D pipelines built in hours — socialwithaayan · 2026-09-16
- Proposal: hand predictable UI workflows to a local runner to cut computer-use agent costs — Iinganouo · 2026-09-16
- Tutorial: Tracing agent invocations and LLM calls with OpenTelemetry — dl_weekly · 2026-09-16
- LangChain makes every Managed Deep Agent an MCP server callable by coding assistants — LangChain · 2026-09-16
- LlamaIndex on Building SDKs with Stainless, Whose Team Joined Anthropic — llama_index · 2026-09-16
- HappyRobot CEO on what it takes for an SE to become an FDE at his $1.2B startup — ivory_tang · 2026-09-16