Context Engineering: Why Briefing AI Matters

Better context leads to better thinking.

Over the past year, as I’ve worked more deeply with generative AI tools, I’ve come to a simple but powerful realisation:

The quality of your output is only as good as the quality of your briefing.

You can write the most technically precise prompt in the world — but if you don’t give the AI enough background, story, framing, or clarity about what really matters, it’s like briefing an eager graduate assistant with no life experience.

They’ll jump to help — but they’ll often miss the point.

That’s why I believe context engineering has overtaken prompt engineering as the most important skill for leaders, consultants, and educators working with AI. And it’s why I now use two complementary models — CPQQRT and CRAFT — to frame not just what I write to AI, but how I think before I write.

Prompt Engineering Isn’t Enough

Prompt engineering still matters. It’s how you communicate with a large language model, and thoughtful prompts can dramatically improve outcomes.

But here’s where many people get stuck:

• • They chase “magic prompt templates”

  • They treat AI like a vending machine: insert clever wording, get shiny content

  • They forget that AI lacks lived experience, ethical reasoning, or intent

The result? High-speed output with low-quality insight.

“This isn’t prompt magic. It’s just better thinking upstream.”

What Is Context Engineering?

Where prompt engineering focuses on what you say, context engineering focuses on what the system understands before you say it.

It’s the practice of embedding:

• • Relevant background or goals

  • Constraints and non-negotiables

  • Tone, format, and audience expectations

  • Examples, analogies, or stories

  • Timing, urgency, or relevance

Put simply, context engineering mirrors how great leaders brief their teams — not just with instructions, but with the full picture.

“Think of context engineering as creative leadership — guiding the AI to align with your intent, tone, and audience.”

A Simple Before-and-After

Instead of prompting:

“Write a project summary.”

Try this:

“You’re an experienced program manager. I’m briefing you on a community health initiative for a regional council in Australia. Summarise the key outcomes from this 6-month report for non-technical stakeholders, using clear language and short paragraphs.”

This isn’t about clever tricks — it’s about intentional thinking and strategic briefing.

Model 1: CPQQRT — Brief Like a Leader

When I coach leaders on delegation, I teach a model called CPQQRT — a Rio Tinto framework I worked with extensively while leading organisational development at SOHAR Aluminium in Oman.

CPQQRT is a powerful structure for briefing humans — and it works just as well with AI.

• • C – Context: Why this task matters. What’s the backstory?

  • P – Purpose: What’s the goal? What does success look like?

  • Q – Quality: What are the minimum standards? What’s acceptable or not?

  • Q – Quantity: How much is needed? Are there cost or scale expectations?

  • R – Resources: What’s available? Time, money, knowledge, tools?

  • T – Timeframe: What are the deadlines or delivery windows?

Use CPQQRT to prepare your thinking before you even open ChatGPT. You’ll write fewer prompts — and get better results.

Model 2: CRAFT — Structure the Prompt

While CPQQRT helps you think like a leader, CRAFT helps you shape your actual AI prompt.

Created by Brian Albert of Lawton, CRAFT is a simple structure for writing clearer, sharper, more intentional prompts.

• • C – Context: Provide relevant background

  • R – Role: Tell the AI who to act as (e.g. consultant, writer, coach)

  • A – Action: What do you want it to do?

  • F – Format: What structure should the output take?

  • T – Target Audience: Who’s this for? What tone or detail is needed?

“AI isn’t useless. You’re just asking it weak questions.”
— Brian Albert, Lawton

Use CRAFT when you’re ready to type. Use CPQQRT to get clear before you do.

These Models Work Together

You don’t have to choose between context and prompt engineering. That’s a false choice.

• • Prompt engineering is the technique.

  • Context engineering is the thinking that informs it.

CRAFT helps you express your request.
CPQQRT helps you understand what needs to be expressed.

Together, they form a thinking system for working with AI.

Working with AI Is a Thinking Partnership

The best analogy I’ve found?

Working with AI is like briefing a smart, sycophantic graduate assistant with no life experience.

They’re quick, articulate, and eager to help. But they won’t challenge you. They won’t push back. If you give them half the story, you’ll get half the value.

That’s why context matters more than cleverness. It’s also why the responsibility always sits with you.

The AI may generate the words — but you own every one.

Five Takeaways for Leaders Using AI

1. Brief the AI like you’d brief a team. Set the scene, define success, and highlight constraints.
2. Use CPQQRT to think upstream. It clarifies your intent before you even type.
3. Use CRAFT to write your request. Role, action, format, tone — make it clear.
4. Treat the AI as a collaborator, not a tool. Think aloud, build iteratively, revise together.
5. You remain responsible. The AI supports, but does not replace, your judgment.

Final Thought: The Future Belongs to Contextual Thinkers

Prompt engineering opened the door. Context engineering is what invites the brilliance in.

As I prepare for my PhD on algorithmic systems and leadership, I’m convinced: The future of AI collaboration isn’t about speed. It’s about quality, ethics, and clarity of thought.

Models like CPQQRT and CRAFT don’t just help you use AI. They help you lead in an AI-enabled world.

And that’s the work that matters most.

Suggested Next Step

Before your next AI prompt, take 2 minutes to walk through CPQQRT.

Then write your prompt using CRAFT.

You’ll think more clearly — and AI will work better with you.