Concept

Context Engineering

Curating the conventions, decisions, contracts and constraints an agent sees — the largest lever on whether agentic output is acceptable.

An agent is only as good as the context it is given. Context engineering is the discipline of capturing the conventions, architecture decisions, contracts, examples and constraints an agent needs — once, in shared, versioned artefacts (such as AGENTS.md) baked into templates — rather than re-prompted by each developer from scratch.

It is becoming a foundational architectural concern: the primary asset of an AI-native organisation is increasingly its context layer, not its codebase. Depth: Context Engineering: Context Is the New Architecture and The Memory Hierarchy of an Agentic Team: Choosing Between Convention Files, Retrieval, Graphs and Fine-Tuning.