Context Is Everything.
AI doesn't know your situation, your audience, or your goals. Until you tell it.
After this lesson you'll know
- The 6 types of context that transform AI output
- How much context is too much (and too little)
- The "briefing document" technique for complex tasks
- How to reuse context across multiple prompts
Without context, AI has to guess. And it guesses wrong.
When you prompt "Write me a marketing email," the AI doesn't know:
- What you're selling
- Who you're selling to
- What makes your product different
- What tone your brand uses
- Whether this is a cold email or a follow-up
- What action you want the reader to take
So it fills in every blank with the most generic, average answer possible. That's not the AI being bad at its job — it's the AI doing the best it can with nothing to work with.
The 6 types of context that matter most.
Watch context transform real prompts.
Each example below shows the same task — first without context, then with each context type layered in. Watch how the output would change at every step.
NO CONTEXT:
"Write a LinkedIn post about hiring."
+ WHO (Identity):
"I'm a startup CEO who just grew from 5 to 20 people."
+ WHO (Audience):
"My audience is other founders and engineering talent."
+ WHAT (Situation):
"We just closed our Series A and are hiring 8 engineers."
+ WHY (Goal):
"I want top engineers to DM me — not just like the post."
+ HOW (Tone):
"Honest and vulnerable — not the typical 'we're hiring!' post."
+ WHAT NOT (Boundaries):
"Don't list perks. Don't use 'excited to announce.' Don't
include a bulleted job description."NO CONTEXT:
"Should I change jobs?"
+ WHO (Identity):
"I'm a mid-level product manager, 4 years at my company."
+ WHO (Audience):
"I'm asking for myself — I need an honest assessment."
+ WHAT (Situation):
"I got an offer for 30% more pay but it's at a later-stage
company. My current company might promote me in 6 months."
+ WHY (Goal):
"I want to maximize my career trajectory over 5 years,
not just next year's salary."
+ HOW (Tone):
"Be direct. I can handle hard truths."
+ WHAT NOT (Boundaries):
"Don't give me generic 'follow your passion' advice.
Give me a framework for making this decision."See the difference? Each layer of context removes another guess the AI would have to make. By the time you've included all six types, the AI is operating with almost the same information you have — and the output reflects that.
This lesson is for Pro members
Unlock all 520+ lessons across 52 courses with Academy Pro.
Already a member? Sign in to access your lessons.