AI engineering’s next five labels: from prompts to context, harnesses, loops and graphs

Roger_M_Taylor · x · 2026-07-25

The post sketches a five-stage naming evolution in AI engineering: prompt engineering in 2022, context engineering in 2025, harness engineering in Feb. 2026, loop engineering in June 2026, and graph engineering in July 2026.

The core idea is that as agents become more capable, the real work shifts from writing better prompts to managing context, adding architectural guardrails, designing plan-execute-verify loops, and wiring multiple agent loops together through shared state.

Original post →

More from coding & agent

coding & agent channel →