Stop typing to Google.

Think back to the last time AI gave you an answer that was... okay. Generic. Useful in the same way a Wikipedia article is useful — correct, but not helpful for your specific situation.

Why did that happen? Most likely because you asked the question the way you'd type a Google search.

The problem: AI is not a search engine. It's a conversation partner. And a conversation partner needs context to give you a good answer.

Think of it this way: you call a consultant who is an expert in everything. If you just say "ceo letter quarterly report template" — what do they respond? "Which industry? How did the quarter go? Who is reading this? What's the tone?" They ask for context. Not because they're difficult — because they want to give you a good answer. AI does the same thing, but silently. If you don't provide context — it assumes. And the assumptions are always generic.

The five elements of a prompt that always works

You don't need to remember all five every time. But the more you include, the better the answer.

1. CONTEXT — Who are you? Tell AI who you are and what you do. "I'm the CEO of a 12-person consulting firm in Gothenburg." That's all it takes.
2. TASK — What needs to be done? Be specific about the task. Not "help me with a letter" but "write a draft quarterly letter to our board."
3. BACKGROUND — Why and what? Provide the relevant background. "We had a tough Q1 (-15% vs Q4 last year) but have a concrete plan for Q2."
4. FORMAT — What should it look like? Specify length, tone, structure. "400 words max. Tone: direct but not panicked. No bullets — flowing prose."
5. EXAMPLE — What should it sound like? If you have an example of the tone or style you want — paste it in.

The comparison that shows everything

Write a CEO letter about Q1

I'm the CEO of a 12-person IT consulting firm in Gothenburg. We had a tough Q1 — revenue fell 15% vs Q4 last year, primarily because a large project was delayed to Q2. We have strong order intake and a realistic plan going forward.

Write a quarterly letter to our board (5 people, experienced business executives). The tone should be direct and accountable — acknowledge the challenge without sounding panicked. Focus on the Q2 plan. Max 400 words, flowing prose, no bullet points.

The difference in the answers? Night and day.

There's a common mistake even experienced AI users make: they ask AI to do the job without giving it the raw material.

"Write a follow-up email to a potential client."

Which email? Which client? What was the meeting about? What do you want them to do next? What's the tone of your relationship? AI writes something. It looks like an email. It's useless.

The key is to understand: AI is only as good as the information it has to work with. Garbage in, garbage out — just better written.

Three levels of context

I run an accounting firm. A client is late on payment for the third month.

I run an accounting firm. The client Lars Andersson at Andersson & Co is late on payment for the third month — total debt 45,000 SEK. We want to keep the relationship but need to get paid. I've sent two previous reminders.

...The email should be professional but firm. Not aggressive. Give him one last chance with a concrete deadline (10 days). Don't mention that we're considering debt collection — that's the next step if he doesn't respond. Max 150 words.

The technique: paste in raw material

One of the most powerful things you can do: give AI the actual raw material and let it work with it.

Instead of "Summarize the most important things from the meeting" — do this: "Here are my notes from the meeting: [paste notes]. Write a structured summary with: 1) Decisions, 2) Action items with owner, 3) Open questions. Max half an A4."

It takes 30 seconds to paste the notes. The result is ten times better.

The same principle applies to: email threads you need to reply to, contracts you need to understand, reports you need to summarize, articles you need to analyze.

You ask for something. You get an answer. It's 70% right. And you... accept it, or start over from scratch with a new prompt.

Wrong on both counts.

AI is designed for conversation. The best answer almost never comes on the first try — it emerges through dialogue.

Three ways to improve an answer

Good foundation. Make the third paragraph shorter — it repeats itself. And the tone in the opening is too formal for our relationship with this client.

This sounds too corporate. Here's an email I'm happy with: [paste it]. Rewrite with that tone.

You mention three alternatives. Which do you recommend for a company in our situation and why?

Conversation memory is your superpower

AI remembers everything you've said in the conversation — until you start a new one. This means you can build up context iteratively without repeating yourself.

Example of an effective workflow:

1. "I'm the CEO of X. We have problem Y. Help me think through it."
2. AI reasons. You adjust: "What you're calling problem A isn't actually a problem — it's solved. Focus on B and C."
3. AI adjusts. "Now give me a concrete action plan for B."
4. "Good. Now write a draft email to the board based on what we've worked out."

Four messages. The result is tailored to your situation in a way that a single large prompt can never be.

When to start over vs. continue

Continue in the same conversation when: the answer is on the right track but needs adjustment, you want to build on what has been said, the tasks are related.

Start a new conversation when: the conversation has become long and sprawling (50+ messages), you're switching to a completely new topic, you want a "fresh" perspective without previous assumptions.