An AI engineer known for popularizing “vibe coding” says one of the most effective ways to use AI is not by feeding it templated prompts.
In a new interview with LinkedIn co-founder Reid Hoffman, Parth Patil says many users approach AI assuming they already understand the problem they are trying to solve, which often limits the quality of the output.
Patil says his most powerful technique falls under meta prompting, where the goal is to use one prompt to help uncover the right prompt.
“I think one of the most powerful prompting techniques is in the area of meta-prompting. It’s the prompt that helps you find the right prompt. A simple one that I use almost every day is I go to a language model, and I’ll say, ‘Here’s my problem.’ Describe the problem. And then I’ll say, ‘Interview me until you have enough context to help me with this problem.’ And then we’re going to begin.”
He says the approach forces users to slow down and shift from solution seeking to problem definition, which often surfaces issues they had not considered at the start.
“I think a lot of people initially go to AI thinking they know what the answer is. And I think a better way to go to AI is, let’s describe the problem and maybe a set of solutions will emerge once the AI collects that context and draws it out of you.”
Patil says he relies on what he calls the “interview me” prompt whenever he starts a new project, using short back-and-forth exchanges to refine scope and assumptions before any real work begins.
“Just interview me, and then we’re going to begin. And so I do that for any project that I’m starting from scratch. And it might just be a 10 turn back and forth, and I realize, oh, this consideration, I wasn’t even thinking about that.”
Patil compares the technique to how strong employees operate, noting that good AI behavior mirrors good human collaboration.
“The AI will ask those intelligent follow-up questions, kind of like any good employee isn’t just going to start doing the work. They ask the clarifying questions up front, and then that brings out a higher quality problem scope.”
Once that groundwork is done, Patil says the results feel fundamentally different.
“And then when the AI begins, it becomes much more magical.”
Disclaimer: Opinions expressed at CapitalAI Daily are not investment advice. Investors should do their own due diligence before making any decisions involving securities, cryptocurrencies, or digital assets. Your transfers and trades are at your own risk, and any losses you may incur are your responsibility. CapitalAI Daily does not recommend the buying or selling of any assets, nor is CapitalAI Daily an investment advisor. See our Editorial Standards and Terms of Use.