Harness Engineering and Graph Engineering: two practices for reliable AI agents
Pavan_Belagatti · x · 2026-11-14
The author outlines two agentic engineering practices for building reliable systems:
Graph Engineering: instead of stuffing everything into one massive prompt, design work as a connected system of smaller explicit tasks — each with a purpose, defined input/output, and a route to the next step. This gives agents structure, makes decisions inspectable, and enables parallel work. Key concepts: nodes/routing, state & memory, dependency management, human approval guardrails, observability.
Harness Engineering: AI coding agents are great at generating code, but code generation is only a small part of real software engineering. Beyond the model you need tools, memory, context engineering, sandboxing, orchestration and a serving layer ("Model = Harness + everything else").
Accompanying diagrams illustrate how both feed into an Agentic Engineering Platform.
More from coding & agent
- GitHub course with 24.5k stars teaches harness engineering for AI coding agents — tom_doerr · 2026-11-14
- Your company 'second brain' is just silos with an AI on top — alex_verem · 2026-11-14
- Modal Endpoints land in Nous Research's Hermes Agent via one-line plugin install — AAAzzam · 2026-11-14
- Cmpnd releases dspy-wsp: $5-10 of GPT-6 edits model weights, lifts every decision model tested — dbreunig · 2026-11-14
- AmphoraDB launches serverless databases for agent swarms, paid per statement in stablecoins — banteg · 2026-11-14
- Ex-quant's local AI agent negotiated 1,000+ influencer outreach in 9 days — Shruti_0810 · 2026-11-14