Context engineering

Garden · not yet reviewed Established: widely used Widely discussed since 2025-06

Choosing and arranging everything the AI can see, such as instructions, examples, files, past messages and connected data, so it has what it needs for the task and little that distracts it.

Also called: giving AI the right information · prompt context · briefing the AI · grounding

Connections

Understand first

Ideas this one builds on.

• Prompting (garden)
• Context window (garden)

Leads on to

Ideas that build on this one.

• Projects and knowledge (garden)
• Skills (garden)

Evolved from

How the idea changed over time.

• Prompt engineering (garden)

Related

Often used together or easily confused.

• Memory (garden)

Skills that use it

• /build-brief (garden)

Blueprints that practise it

• Hire and onboard an AI copilot for one piece of work (garden)
• Let AI ask before it plans (garden)
• Teach your AI assistant your team's jargon, one confirmed term at a time (garden)

Resources that teach it

• Introduction to Claude Cowork (garden)
• Claude Help Center: Introduction to prompt design (garden)
• Gemini API prompt design strategies (garden)
• How to Write a PRD: A Step-by-Step Guide for Product Managers (garden)
• Claude Cowork for PMs: My Self-Improving Productivity System (How I AI, with Daniel Blum) (garden)
• Compound Engineering (garden)
• Build your personal AI copilot (garden)
• Lenny's Data: free public starter pack (garden)
• How to build your PM second brain with ChatGPT (garden)
• Getting started with AI: Good enough prompting (garden)
• 12 Rules to Vibe Code Without Frustration (garden)
• Behind the Craft — Transcripts (garden)

Competency

• Describe the task

Find context engineering on the commons map ↗

You may know it from

• project management briefing a contractor A good brief hands over the plans, the constraints and the history, not just a one-line request.
• cooking mise en place Getting every ingredient measured and within reach before you start cooking.

In plain words

Your prompt is only part of what the AI sees. It also sees earlier messages in the chat, any files you attached, standing instructions you saved, things it remembers about you, and whatever its tools fetch. Context engineering is the practice of deliberately deciding what goes into that pile.

With too little context, the AI fills gaps with generic guesses. With too much, the important parts get buried, like a 90-page policy pasted in when one section matters. Give it the parts that bear on the task, in their latest version, with a note on what each one is.

This is why AI products keep adding features like projects, memory, skills and connectors. Each one is a way to get the right material in front of the model at the right moment.

Example

An HR generalist wants a draft parental-leave FAQ. Instead of asking cold, she attaches the actual policy, two real employee questions (names removed), and last year’s FAQ with a note: “match this tone, but fix the outdated eligibility rule.” The first draft is close to usable.

How it connects

• It evolved from prompt engineering, moving the focus from wording to information.
• It is limited by the context window, how much the AI can hold at once.
• Projects, memory and skills are product features for managing context.

Try it

For your next request, list what a human expert would want on their desk to do the task. Give the AI only the top three items from your list and see how the answer changes.

---

Read this card as plain Markdown: /concepts/con-context-engineering.md. Know a parallel from your own field, or a product that implements this? Add it.