# Agent Engineering

> Agent engineering is the discipline of building reliable AI agents — designing the tools, context, guardrails, evals, and recovery paths around the model.

**Agent engineering is the emerging discipline of making AI agents work reliably in production — the design of everything around the model: tools, context, permissions, evaluation, and failure recovery.**

The term took hold as 2026's successor to "prompt engineering," marking a real shift in where the work lives. A capable model is table stakes; whether an [agent](/glossary/ai-agent) ships comes down to harness quality — [tools that fail informatively](/guides/concepts/production-tool-calling), context that stays signal-dense, [guardrails](/glossary/guardrails) and [human gates](/glossary/human-in-the-loop) where stakes demand them, [evals](/guides/evaluation/write-llm-evals) that measure task completion rather than vibes, and observability over runs that span dozens of steps.

Its body of practice is accumulating fast — [framework trade-offs](/guides/concepts/agent-frameworks-2026), [orchestration patterns](/guides/advanced/multi-agent-orchestration), reliability review ([the checklist, as an agent](/agents/meta-orchestration/agent-reliability-reviewer)) — and the role is increasingly a job title: the person who owns why the agent failed at step 14, and who makes step 14 impossible to fail that way again.

---

_Source: https://agentscamp.com/glossary/agent-engineering — Term on AgentsCamp._