Wade Foster

“So we did go through YC and we raised about a million and change, but that's all the primary capital we've ever taken.”

“I actually think this is way better than the morning brief. And the reason why is you could actually have the AI help you do stuff.”

“I used to spend like two hours at the end of my day, just like, You know, just trying to catch up on every little ticky tack thing that I sort of got roped into, and now that, like, two hours at the end of the day is down to, like, 15 minutes.”

“So this, if you go to Zapier's GitHub, you can get a copy of the war council, but what this does is it spins up sub agents and these sub agents take on personas. There are seven sub agents that get spun up. So seven personas. Some of them are standing members.…”

“Every Sunday morning now I wake up with a list of, you know, 10 customers that I want to get in touch with. And it's got proposals for what I should say and what I should do and why I should do it and all that sort of stuff.”

“Well, I would say like any high stakes decision, the AI is weighing in on now. Like, you know, there's sort of a seat at the table and, you know, the exec meeting and the board meetings and all that sort of stuff where we're asking the AI to like, Surface thos…”

“Well, so you could, but the thing is, you're only gonna be able to keep up with, what, 20 agents? Cause it's gonna keep assigning you tasks and more things to do and more things to do. And so there still is like a, there still is like a limit.”

“Yes. I feel pretty confident that that is the direction we're heading to.”

“I am not an engineer. I have, like, written zero lines of production code in my entire life.”

“I still think that I write better emails than these tools do, but it usually does a good enough draft that I can just tweak a few things and be like, great, you know, send it for me.”

“I just know that I've got an amazing coding agent in Cursor, inside of Cursor, and in this case, I'm using GPT-Five.”

“I find myself every single day, first thing in the morning, I just talk to the agent and I say like, hey, what work have I done recently where I should build new workflows and build new agents and build new stuff? And it will start proposing them to me and say…”

“I review every single job offer that goes out inside of Zapier still.”

“And that was a task that used to take me You know, 30 minutes per every candidate. And now it's down to like five.”

“Once you start automating a few things, you find that your own brain starts to get better at spotting opportunities because you're like, oh, I remember this other thing I did that was kind of like this. I can probably do this in the same way or the same versio…”

“My approach is I usually do it the manual way first. It's like, I'll usually just like, you know, pop open a new chat, and I'll just start yapping at it. And then if I find myself doing the same thing kind of over and over again, then I'll build like a skill f…”

“The agent is actually choosing what products to buy on behalf of a human. And so you're no longer advertising to the human. You are trying to get the agent to say, pick me. And that is often a very different skill set than marketing to a human.”

“Agents care a ton about, like, clean documentation, like, fast webpages, so, you know, it's like, the thing I'm seeing a lot of folks do is serve up a separate version of their webpage that is meant just for the agent, and so that content is, like, plain text.”

“I got off the call, and I have cursor hooked up to granola, And so the meeting was recorded with Granola, and so I said, hey, Granola, our, go, go fetch that meeting I just had with Ryan, and in it he describes the war council he built. Build that for me. And …”

“I could see skills kind of having, like, a business model like that, where it's like, you could buy, you know, buy one for five bucks, 10 bucks, there would be a bunch of free skills out there. You know, it's, it feels kind of like a very commodity thing at a …”

“It's hard for humans to say no to, like, candidates that are good. It gets harder to say no as the interview goes along. So, like, two people before you said yes, now are you gonna be the person that says no? So you get more of that. And also humans I find are…”

“I find it to be a really helpful tool at keeping the panel honest, keeping me honest on a decision where I can find myself sort of like feeling one way or the other, and then you talk to it, and it like really grounds the decision, and you're like, then you ha…”

“One thing I've found is that like Opus is like more enjoyable to just like talk to and go back to it. Like sort of is an easier conversation list, but like when I'm having it work on hard problems, it sometimes just like bugs out. It doesn't do as good of a jo…”

“Wade, the founder, likes the, what is it, the five dysfunctions of an organization, of a team. I forget the name of the book. Anyway, he likes it so much that that, at the end of each internal meeting, Everyone's individual contribution to the meeting gets ana…”

“Digital marketing agencies, they're like, this is the place where I've seen most automation agencies spin up because there is so much just low hanging fruit that can help any business be more, more successful.”

“I have found that AI is an exceptionally good coach. It is infinitely patient. It is neutral. It just observes what it sees and it tells you what it thinks it has observed.”

“And so for our exec team meetings, we have these recorded. And so we'll take the transcript automatically. We'll send it to a prompt. That is based on the five dysfunctions of a team. So if you haven't read five dysfunctions of a team, it's, it basically descr…”

“If you go read X, if you go read LinkedIn, you would think that everybody is deploying agents Everywhere. Here, look at this crazy agent I've done that has solved all these magical problems for me. Mostly that is hype.”

“So what are the folks that are actually deploying like automation at scale doing? They're finding ways to mix and match deterministic workflows with agentic workflows and do those together.”

“I think a reason a lot of folks are taking this approach of inserting the human at the last mile is the more agentic these workflows, the more imperfect it is.”

“I think the answer is we're going to end up having both. I think APIs are very, are deterministic and cheap. Works the same way every single time. And so there's a whole set of use cases that Do you want it to work that way? Where MCP is a lot more flexible. T…”

“And so we have a whole automation system agent system that like takes all that stuff. It then generates a bunch of themes based on that and then generates reports based on those themes. Then the second thing we have built up is a chat bot around all that stuff…”

“Wade was the founder of Zapier, and they went from Missouri to California and have built this giant company raising only 1.5 million.”

“I was doing this bespoke onboarding for, I don't know how many people I did it for. I lost count. It probably was hundreds. You know, if it wasn't hundreds, it was definitely, you know, more than 50 people that I was just going through this process over and ov…”

“Send it to my personal PayPal account. And so that was literally how we made our first money was just a hundred bucks via PayPal.”

“Everyone's like, oh, we should make it free. So we get more usage, et cetera. And I just think that that's a really tough place to be. Cause you're going to get a lot of just like noisy feedback from people who actually really don't have this problem. Whereas …”

“Like most, most people don't have an entrepreneur who deeply cares about solving their problem. And so even if the software is not good, they'll be okay with it because like you just have a passion and excitement for it.”

“It's owned by two brothers, 50, 50, and never raised any money.”

“One of the first customers was doing that, but the app directory existed before we had a customer. It was just like, hey, we'll build this like little app directory, see if we can get people coming in through search. And if they are like, yeah, we can build a …”

“The thing that actually helps Salesforce win. It's not necessarily that the product is amazing. It's that they have this incredible distribution engine that is really difficult to compete against.”

“Product market fit is not just about the product. It's about the market too. You need these things to like coexist. And in many ways, that's what made Zapier hum is that the product and the go to market motion are inextricably linked. They work as one fluid mo…”

“We're still not an enterprise company. We still like SMB is our bread and butter. That's who we solve for.”

“How do you know if you have product market fit? And I'm always like, well, you know, because people want what you have. It's not actually that hard if people actually want what you're selling. They don't want it, then everything seems hard. Everything feels im…”

“A good business makes a lot of this stuff a lot easier. Like, if you're making good money, if you're growing, if there's plenty of opportunity to go around, there's plenty of money to go around, salaries and bonuses and things like that, everything gets way ea…”

“We had this rule, don't hire till it hurts... One, it meant we did every single job. So we understood every piece of our business. So when we hired somebody in that meant we knew exactly how they were going to be effective, what was going to help them win. And…”

“As a first time founder, like if I tried to go 10 to a hundred, I think we would have ruined a lot of stuff inside the business.”

“I think it took us till we probably had 30 or 40 people before we hired someone who had been a manager before into the company, which in hindsight was just like far too long.”

“It's way more fun and way more valuable to work with folks who have a much more dynamic problem solving skill set, where they can borrow from a bunch of different areas, and then they can start to put those puzzle pieces together in novel ways.”

“And that's like for most of Zapier's history, you know, it's a relatively small ish team. And so a lot of it is, you know, a maniacal focus focus on like the singular thing. ... Generally we were always trying to think through, like, what is the one thing that…”

“I think you get into this really tricky thing where you're just literally like paying attention to somebody else's roadmap and just being like, Hey, we just got to keep up. You know, we just got to match it one to one because oftentimes you don't actually know…”

“The more you're even aware of these phenomenon, like the more you, and the smarter you are, like the more it actually dangerous you are to these things because you actually get better at rationalizing your way through it.”

“Zapier, way from Zapier, Never believed in fundraising, and I think that's why he hit default alive with one and a half million. He's never had to raise money. He doesn't need to because he prints cash.”

“He built this system over four years ago, and today it, ah, works with 20,000 different Zapp templates. And it's largely that same MVP he built four years ago.”

“The great news with a lot of no-code solutions, things like Airtable, Webflow, even Zapier itself, allow you to build things not just quickly, but also with quality. And so it's easier than ever to build these MVPs and actually have them go the distance for yo…”

“For a long time, we asked every single one of our employees, no matter what function you worked in, to do some support, and what this meant is that all of our folks really understood the product that we were building and what was special about it, and they als…”

“Steve shares, keep the values, but change the mechanics. Companies change constantly, whether it's your code base, your org chart, your systems and processes, your go-to-market motion, all these things are going to change and evolve over time. So your organiza…”

“Now, it's all great to have, ah, you know, shared values, shared purpose, shared mission, but as your org gets bigger and bigger and bigger, it can start to feel a little more lonely, and so one of the things that Linz's team done is they've branded the suppor…”

“It can be tempting to want to throw more bodies at problems and say, ah, if we just had one more person, if we just had 10 more people, we might be able to solve this. But if you don't have a clear perspective of how they're going to help, you're going to end …”

“Some of those things that we thought through at 20 people have scaled with us to 300 to 500 and have ripple effects over where we've gone. Those sets of core values have really helped us be intentional about where we're taking the company. If you contrast the …”

“So one of the things we've done over time is said, you know what, we're gonna put in infrastructure to make sure code review's happy against some of the riskiest changes, and then we find another path to production for other types of changes.”