GLOSSARY

What is Context Engineering?

Table of content
Definition

Definition

Context engineering is the practice of selecting, structuring, retrieving, and delivering the information, memory, tools, constraints, and examples an AI system needs to perform a task well.

TL;DR

  • Context engineering decides what information an AI system receives at execution time.
  • It is broader than writing a good prompt.
  • Context can include documents, memory, retrieved data, tools, examples, system instructions, and product state.
  • Good context should be relevant, current, scoped, and internally consistent.
  • Complex AI products increasingly depend on context quality as much as model capability.

What does context engineering mean?

Imagine asking an AI agent to redesign a billing flow.

The model might need the current screens, design system, account permissions, pricing rules, recent research, analytics, technical constraints, and the user’s requested change.

Context engineering is the system that decides which of those pieces are relevant, how they are represented, and when they are supplied.

Context engineering vs. prompt engineering

Prompt engineering focuses on how the instruction is expressed.

Context engineering includes the prompt but also retrieval, memory, source selection, tools, state, and permission-aware filtering.

What can context include?

  • current user request
  • conversation history
  • persistent memory
  • retrieved documents
  • database records
  • design-system components and tokens
  • analytics
  • tool outputs
  • implementation constraints

What makes context good?

Relevant

More context is not always better. Irrelevant data can distract the model.

Fresh

Outdated facts can create confident mistakes.

Scoped

The system should respect product, organization, role, and permission boundaries.

Traceable

Important claims should remain connected to their source where possible.

Non-conflicting

When sources disagree, the system should surface or resolve the conflict rather than silently combining them.

Why does context engineering matter for product design?

Existing-product design depends on details that cannot be inferred from a generic model: component usage, product rules, previous decisions, user behavior, and implementation constraints.

Strong context turns generation from “make a plausible screen” into “make a candidate that fits this product.”

Common mistakes

Stuffing everything into context

Relevance and prioritization matter.

Ignoring context freshness

Stale decisions should not silently override current product truth.

Mixing private and shared knowledge

Context systems need clear access boundaries.

The bottom line

Context engineering asks: what does the AI need to know, from which sources, at this exact moment, to make a useful and trustworthy decision?

Related terms

AI agent · AI prompt · Product context · Multimodal AI

Relevant Figr resource

Read Context Is the New Canvas for the product-design implications of persistent context.

Related Figr Projects

No items found.