Getting better results from AI is less about knowing secret prompting tricks and more about your communication skills.

With today’s AI assistants, I think a simpler way to look at prompting is:

Prompting is explaining what you need well enough for an intelligent collaborator to help you

Imagine you’re giving a task to a very capable new colleague. They know a lot. They work fast. But they don’t automatically know what is in your head, your project, your company, or your situation.

So instead of searching for the perfect prompt formula, focus on a few useful habits.

1. Start with the outcome

Don’t just tell AI what topic you’re interested in.

Tell it what you are trying to achieve.

Instead of:

Tell me about microservices.

Try:

Help me understand the main trade-offs of microservices because I need to discuss whether they make sense for a medium-sized product team.

That little bit of why gives the AI much more direction.

A useful mental model is:

<aside> 💡

What do I need + why do I need it + what should this help me do?

</aside>

2. Give context that actually matters

AI assistants are getting very good at filling in gaps, so you don’t need to write your autobiography before every question.

But relevant context still matters a lot.

For example:

• who the audience is