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.
More from coding & agent
- Hugging Face wraps 6-month Training Agents series with open recordings and code — SergioPaniego · 2026-10-26
- Agent verified 'success' after double-voting: a lesson in harness vs model bugs — TejasKumar_ · 2026-10-26
- diginomica: agentic automation hype is overdone, and 'The Hackening' of enterprise security has begun — jonerp · 2026-10-26
- 'Vibe verification': ~60% of AI-written formal specs prove the wrong property — basedjensen · 2026-10-26
- Devin launches Security suite powered by Claude Mythos with $100M+ credits — DevinAI · 2026-10-26
- HackBench injects reward hacks into agent trajectories to stress-test monitors — DanielKhashabi · 2026-10-26