Three shifts, context, outcome, and role, that change how Claude responds to a request. A single hiring decision gets worked through four different ways so the difference is visible, not just described.
The video ends with a reusable template: state the perspective Claude should take, what the response needs to do, and the specific situation that matters.
You set Claude up. You connected your tools. You followed every tutorial. And you're still typing questions into it like it's Google.
That's not a setup problem. That's a communication problem. And nobody talks about it.
I've lived in South Korea for a while. I can follow a conversation in Korean, pick up the mood, and read the room. But sometimes my wife's Korean friends are all talking, they all laugh at something, and I almost get the joke. Almost. I know what it feels like to be smart enough to follow but still miss the one thing that makes it click.
That's exactly where most people are with Claude right now. The ones getting real results aren't necessarily smarter or more technical, they just approach it differently. Most people open Claude and start with the tool: what can it do? But the people getting the best results start with the problem: what do I actually need done?
What's missing isn't a better prompt. It's three things: context, outcome, and role.
After 20 years of teaching complex ideas, I've learned that confusion almost always comes from the same place: people come looking for an answer rather than looking to understand. I see the same pattern in how most people talk to Claude. They ask it questions when what it actually needs is a proper handoff.
I teach a university writing course. To prevent AI cheating, students handwrite major assignments. But I built an AI system to grade the handwriting. The irony was not lost on me.
I hit several walls building that system, correcting the AI more than it was helping me. But things changed when I stopped asking questions and started briefing it, context, constraints, what I'd already tried. Real students were being run through this system, and I'd promised results soon. It ran at 85 to 90 percent accuracy on the first run.
When you type a request straight away, Claude is guessing. It's like calling a taxi and just saying 'drive.' Before you write what you want, ask: if I handed this task to a capable new colleague who has never worked with me before, what would they need to know first? That's your context, and it goes in before the request.
The before: "Write a follow-up email to a client." The after: "I'm a business consultant. I had a call yesterday with a long-term client about renewing their contract. The call went well but they asked for two weeks to confirm the budget. I need a follow-up that's warm, gives them space, but keeps momentum going." Same task. Completely different foundation.
Most people describe what they want Claude to produce, describing the format, not the goal. The better version describes what the output needs to do: "Write me a paragraph that a non-technical senior manager can read in 30 seconds and understand what action they need to take." Now Claude knows who reads it, how long they'll spend, and what success looks like.
If you ask Claude to "look at this draft," it reads it as a general reader. If you ask it to "read this as a skeptical manager who has seen a hundred proposals and is deciding whether this one deserves ten more minutes," it reads it completely differently. The role is not a character you invent, it's the perspective you actually need.
Applying all three together didn't just improve individual outputs, the entire dynamic changed. Sessions stopped feeling like a back-and-forth and started feeling like a handoff.
Imagine you're a senior manager with two final candidates for a project lead position. One has more experience but came across as guarded in the interview. The other has less experience but impressed you. You need a recommendation to leadership by Friday.
Here's what most people type: "I have two candidates for a project lead position and I need to make a decision by Friday. One has more experience but I'm not sure about the culture fit. The other is less experienced but really impressed me in the interview. What should I consider?" Claude gives a reasonable but generic answer that could apply to anyone hiring anyone anywhere.
Now watch what happens when we add context: "I'm a senior manager at a mid-sized marketing agency. I'm hiring a project lead who will manage a team of five and report directly to me. We're in a growth phase and the team is under pressure. Sarah has eight years of experience managing large accounts but came across as guarded in the interview and asked very few questions. Marcus has four years of experience but was engaged, asked sharp questions about the team dynamic, and has managed smaller projects successfully. I need to make a decision by Friday. What should I consider?" The output is immediately more specific and starts giving you things to actually do before Friday.
Now we add the outcome, that this recommendation has to be defended to leadership if challenged. Claude now tells you exactly what argument to make for each candidate, anticipates the pushback, and tells you what information you still need before Friday.
Then we add the role: "You are a senior talent advisor who has helped executives make hundreds of high-stakes hiring decisions. You know that the most costly mistakes usually come from what people overlook, not what they consider." Claude stops analyzing the candidates and starts analyzing your blind spots, telling you what "guarded" actually might mean and what to ask on the reference calls. It ends with: "What you're looking for isn't who impressed you more in a room. It's who is most likely to still be functioning well six months from now when the growth phase is still on and the team has had two hard quarters." That's not a search engine answer. That's what a trusted advisor tells you.
Here's the template: "You are a [specific perspective]. I need this to [what it needs to do]. Here's the situation: [the specific context that matters]."
Rebuilding that context every time is time-consuming. I have a way around it: a single file Claude reads automatically at the start of every session. Before you type a word, Claude already knows your role, your priorities, and how you think.
This video points to The Professional AI Interview Kit, the practical next step after watching.