Pedro Pascal found my guide on how I use AI to write 99% of my code at Airbnb. He loved it. Too bad for him it’s not about vibe coding. It’s about spec-driven development, which still takes real engineering skill.

𝗧𝗵𝗲 𝘁𝗼𝗽 𝗽𝗿𝗼𝗯𝗹𝗲𝗺𝘀 𝗮𝗿𝗲:

 • 𝗖𝗼𝗻𝘀𝘁𝗮𝗻𝘁 𝗿𝗲𝗳𝗮𝗰𝘁𝗼𝗿𝘀 (generated code is really bad or broken)

 • 𝗟𝗮𝗰𝗸 𝗼𝗳 𝗰𝗼𝗻𝘁𝗲𝘅𝘁 (the model doesn’t know your codebase, libraries, apis..etc)

 • 𝗣𝗼𝗼𝗿 𝗶𝗻𝘀𝘁𝗿𝘂𝗰𝘁𝗶𝗼𝗻 𝗳𝗼𝗹𝗹𝗼𝘄𝗶𝗻𝗴 (the model doesn’t implement what you asked for)

 • 𝗗𝗼𝗼𝗺 𝗹𝗼𝗼𝗽𝘀 (the model can’t fix a bug and tries random things over and over again)

 • 𝗖𝗼𝗺𝗽𝗹𝗲𝘅𝗶𝘁𝘆 𝗹𝗶𝗺𝗶𝘁𝘀 (inability to modify large codebases or create complex logic)

In this article, I show how to solve each of these problems by using the LLM as a a force multiplier for your own engineering decisions instead of a random number generator for syntax.