AI Apps Are Broken — Here's How To Fix Them

**Pete Koomen** (0:00)
We're using old software development techniques to build these features, and we're not actually taking full advantage of what AI can do. I think the promise of AI for many of us is that it allows us to build software that the user can program to do whatever they want using only natural language.

**SPEAKER_2** (0:17)
Steve Jobs describes software as a sort of, as a bicycle for the mind. This feels like, I don't know, like a rocket ship for the mind.

**SPEAKER_3** (0:30)
Welcome to another episode of The Breakdown. Today, we're lucky to have Pete Koomen, our partner here at YC. Pete was the founder of Optimizely, which built software to help companies A-B test. Pete, welcome.

**Pete Koomen** (0:41)
Thank you, happy to be here.

**SPEAKER_2** (0:42)
So Pete, you recently wrote an essay, which caused a bit of a stir, and basically told everyone on the internet who's building AI agents that they were doing it completely wrong. So tell us more about that.

**Pete Koomen** (0:52)
Sure, when I use AI in my day-to-day life, I've kind of had two radically different experiences, right? On one hand, when I use tools like Cursor and Windsurf to build software with AI, it feels like the most powerful tool I've ever used, right? It's this feeling of being able to create anything I want. Anything I can picture in my head, you know, will materialize in front of me with these tools. And it makes me so excited about AI. And then I've had a lot of other experiences. A lot of times when I'm using existing apps that I'm used to that have incorporated AI into them, where it doesn't feel that way at all. It actually feels like more of a chore, right? Like using the AI actually creates more work for me than just doing whatever it was myself. The example that I chose in my essay was to pick on the integration that the Gmail team built between their AI model, Gemini, and Gmail's interface. That this is a little draft writing agent that can create email drafts for me, given some instructions.

**SPEAKER_2** (1:59)
And the underlying Gemini model is pretty phenomenal, right?

**Pete Koomen** (2:01)
Gemini is amazing. The model itself is absolutely incredible. We've been using it a lot at YC to automate our own work. I'm so impressed with what they built. But a lot of that power, I think, is hidden behind a UI that makes it really frustrating to use. And that was really the focus of my essay. The feature that I chose as my example was this little draft writing agent that shows up in the Gmail Interface. And what it does is I can put in some instructions. So in this case, let my boss, Gary, know that my daughter woke up with the flu this morning and I won't be able to come into the office today. And it will spit out an email draft for me.

**SPEAKER_3** (2:39)
To make your life easier.

**Pete Koomen** (2:40)
To make my life easier, exactly. So here is the email draft that I got when I put that prompt into the UI. Dear Gary, I'm writing to inform you that my daughter woke up with the flu this morning As a result, I won't be able to come into the office today. Thank you for understanding. Best regards, Pete.

**SPEAKER_2** (2:58)
And if I got this, I'd be like, Pete has his brain taken over by like...

**SPEAKER_3** (3:01)
Or he's been phished. And I need to report phishing. Like something's going horribly wrong.

**Pete Koomen** (3:05)
Pete's account then hacked. Right. There's two big problems with this. The first problem is, like you're pointing out, that doesn't sound anything like me, right? If you got this email, you would assume somebody else wrote this. My account got hacked. I got phished. And then the second problem is that the draft, or rather the prompt that I used to explain what I wanted in the draft is roughly as long as the draft itself. That was my contention here, right? On one side, you have using AI makes you feel like a superhuman with unlimited powers. And on the other hand, using AI is frustrating and adds more work.

**SPEAKER_2** (3:44)
Maybe we're jumping ahead a little bit, but the ideal experience I think would be something like telling the AI, hey, my daughter's ill, like figure out my calendar today and then go through your actual calendar and then figure out each person and then write the appropriate email in the appropriate tone, right? Perhaps we're skipping all the way to the end, but...

**Pete Koomen** (4:00)
I think that's exactly right. These AI models are now capable of doing things like that, where it's actually anticipating all of the things that will need to happen as a result of my daughter waking up with the flu and helping me do those things. But that's not what we've built, right? That's not what the team has built.