How AI got me 3 promotions: the ultimate guide for EAs (w/ Zapier’s EA)

1. 0:00 – 2:48

   Introduction to Cortney

   1. CHCortney Hickey0:00

      I think from EAs I hear like, "Oh, AI doesn't think the way I do." I'm like, "It can, though. It can," [chuckles] as long as you can figure out the system behind why you're doing things and be able to articulate that.

   2. CVClaire Vo0:10

      I think this is going to be one of the most practical, time-saving, and stress-saving episodes of How I AI we have ever had. This agent does everything you want and then more, and over time you can make it more intelligent. It's serving as this kind of second brain for me, where, yes, I have all this, and part of my superpower as an EA is remembering all of these things about people, but this is making sure that it's not all in my head, and I can really refresh my memory quickly on all the contexts, rather than diving through the CRM, my email, Slack, and looking at all these things separately. If you are doing a repeated task every week, spend time that week automating that task. I definitely am a believer that AI can only enable us in this role. I think it's a when, not an if. We will have to be folks that adopt these tools. [upbeat music] Welcome back to How I AI. I'm Claire Vo, product leader and AI obsessive, here on a mission to help you build better with these new tools. Today we have Cortney Hickey, EA to the CEO at Zapier, and yes, of course, she uses AI to automate all of the admin tasks related to meetings, and document preps, and feedback, but she's also gonna show us some unique ways that you can use AI to reinforce your cultural values and operating principles. This is a really great one for anybody thinking about organization at scale, operations at scale, and culture at scale. Let's get to it. This episode is brought to you by WorkOS. AI has already changed how we work. Tools are helping teams write better code, analyze customer data, and even handle support tickets automatically. But there's a catch: these tools only work well when they have deep access to company systems. Your copilot needs to see your entire code base. Your chatbot needs to search across internal docs, and for enterprise buyers, that raises serious security concerns. That's why these apps face intense IT scrutiny from day one. To pass, they need secure authentication, access controls, audit logs, the whole suite of enterprise features. Building all that from scratch, it's a massive lift. That's where WorkOS comes in. WorkOS gives you drop-in APIs for enterprise features, so your app can become enterprise-ready and scale upmarket faster. Think of it like Stripe for enterprise features. OpenAI, Perplexity, and Cursor are already using WorkOS to move faster and meet enterprise demands. Join them and hundreds of other industry leaders at WorkOS.com.

2. 2:48 – 4:43

   Overview of meeting prep automation with Zapier Agents

   1. CVClaire Vo2:48

      Start building today. Cortney, welcome to How I AI. I am really excited about this episode because I think this is going to be one of the most practical, time-saving, and stress-saving episodes of How I AI we have ever had. So I'm just pumped to have you on. Can you just tell us a little bit about why you've chosen to dive headfirst into using AI in your role, aside from the place that you work?

   2. CHCortney Hickey3:21

      Yeah, so I work for Zapier, which is an automation and AI orchestration company, so of course, it's part of our company ethos. But I am just personally super passionate about using AI because I think it can help work myself out of the boring, repetitive, manual parts of my role so I can do more interesting work. And so I truly believe that it's not a if you have to use AI in this type of role, it's a when. So I like to be ahead of the curve. I like to learn by doing, and so I've spent as much time as I can over the past couple of years really diving into this and seeing how I can change the shape of my role with this new tech.

   3. CVClaire Vo4:04

      And what I like is we're gonna start off on a workflow and use case that I think everyone can relate to, which is meetings stink, or not meetings stink, but meetings could be better used in most organizations. They're expensive. You have a lot of people in them, and I think, like, prep and follow-up are so valuable and aren't really done well by organizations. So I'd love for you to walk us through a couple of your meeting-related workflows.

   4. CHCortney Hickey4:34

      Totally, yeah. I mean, as an EA, the-- my life runs off of the calendar, so that was naturally one of the first places I dove into with AI.

3. 4:43 – 10:21

   How the meeting prep agent works

   1. CHCortney Hickey4:43

      And so let's jump into one of my favorite workflows that I've built, and this is within Zapier Agents. So our agents product, uh... Within Zapier, we have a bunch of different products, all the way from super deterministic automations that run the same way every time with little creativity to these agents that can do tasks that involve more reasoning and, uh, have a lot more freedom to operate. So you could build this in a Zap, but I wanted to, like, paint the, you know, change the color of the sky with this agent for myself. So this is an example of one I use personally, but you can replicate this for anyone you work with, but this is essentially my weekly meeting prep agent, which on Fridays I used to have maybe, let's say, two hours blocked, 30 minutes to, like, do a retro on that week and anything I need to change, but then, like, spending an hour or so really diving into the next week and what I need to be prepared for. So-... The way this agent works, and it's kind of developed over time, but it, it has a few steps it goes through. And the key thing is this is scheduled to trigger every week. I have it due at, at Friday, eight AM, but you can have it whenever. And basically, it goes through my calendar for the upcoming week. It identifies all meetings that require prep. So personally, I don't need to prep much for routine one-on-ones or team stand-ups or recurring internal meetings, but I do have more and more external meetings on my calendar now that I'm doing more out in the world with, with AI and automation and teaching folks how to do the same. So basically, I have it be a bit of a research buddy at first. So first it just pulls my calendar, then it goes and does all of the research for me. So this, uh, takes anyone without a Zapier email and does a, a web search, basically. It researches their current role, their industry experience, anything, um, anything noteworthy that I might wanna know about them. And then it does this cool thing, which also goes and checks in our CRM, which we use HubSpot at Zapier, but you can, you can put in any, uh, you know, of our eight thousand integrations here and, and use your CRM. But for each external participant, it goes and then looks at what their relationship is with Zapier. So it looks at email address first, then by company name, figures out what-- if they're in a deal, if there's any recent sales team notes, if there's any interaction I should know of. And then it also goes and searches internal comms history, so within my Gmail to see our private prior relationship, if any, within Slack to see if there's any call-outs to their company. And so it's, it's doing all these things that I would do manually, and then it's delivering me two outputs in the end. So one of them is tasks for my actual prep with all this in it. So I like it to create a task in Todoist, which is my to-do list app with the-- within a certain project of meeting prep. It pulls in all of this information with this intelligence from the agent and, and tells me to prep for it and puts it on my calendar for two hours before the meeting start time. So you can see what that looks like in real life, you know, here. Here's a couple meetings I have next week, and they're automatically queued in my Todoist. But the second thing it does is delivers this weekly digest to Slack. So this is... And you could do this day by day, too, if you have a ton of meetings, but again, I'm, I'm mostly internal, so I have it create a structured digest, which includes all of the meetings and intelligence, um, any error handling I might need to know, like if the agent couldn't find someone or if there's anywhere I should do a manual follow-up. And then it does this, like, it, it pulls its own-- uses its own creativity to create these insights for me about, uh, what I should pay most attention to for this upcoming week. So I can pull up a, uh, real example here. So I just ran this, this morning, just for this example, but it's going... looking at the next week. It's pulling all of the key meetings that require prep- preparation. It's saying: "Okay, so we have a team onboarding with Fellow. We're changing our AI note-taking app." And so it did some intelligence on who we're meeting with for this. It's te- we're confirming that this is a new vendor relationship. We've pur- we've previously purchased this meeting management. They're our implementation specialist. And then, you know, here's, here's more context on this. So it's like, it's, it's serving as this kind of second brain for me, where I-- yes, I have all this, and part of my superpower as an EA is, is remembering all these things about people, but it-- this is making sure that I don't-- it's not all in my head, and, and I can really refresh my memory quickly on all the context rather than diving through the CRM, my email, Slack, and looking at all these things separately. So one place is, is key. And then, um, it pulls in this, like, key prep recommendations at the end, which is where the agent d- gets a little bit creative here. So it's saying, I should review my previous Carve session. This is a, uh, EA automation session I do every once in a while. It tells me to prepare some new demos, tell me to familiarize myself with Fellow before the onboarding session, and check with our head of marketing for PR priorities before the agency call. So I love that it, you know, does exactly what I need to do. Like, you know, gives me all these preps in my Todoist, and it does those actions, but it also kind of serves as, like, a double-check. Maybe there's something I haven't thought of. Maybe I didn't think I needed to update my deck, and it gives me something new. So I think what's great about this agent is it does everything you want and then more. And, and over time, you can make it more intelligent. So as you, as you learn how this works, and so

4. 10:21 – 12:16

   An example of the meeting prep agent in practice

   1. CHCortney Hickey10:21

      I'll give you an example of how this actually works in reality. So this is the test that I pulled right before this call, just to give us a clean Slack output. And it walks you through step by step what this agent was thinking. It's like: Okay, I'm testing this. I'm gonna go look at the calendar. I'm gonna go research all these participants. You can click in and see even more information about what it was thinking. Um, you can see that it went in HubSpot, couldn't find someone for there, couldn't find someone. We probably didn't have a relationship with them. Oh, great, it found someone. And then, um, it tells you everything it did. So over time, if, if something's not performing as you intended or you wanna update it, you can really look at how this agent works on the back end and give it some feedback. And we have this great copilot where you can go in and say, um, you could say, like... You could go into copilot and be like: "Oh, uh, I actually would love to have a hyperlink to their LinkedIn, uh, page included in my Todoist things." You can say, for each participant, [keyboard clicking] "Can you also add a LinkedIn hyperlink within the Slack digest?" So you can kind of-... I always tell people when they're starting with an agent like this is progress over perfection. Like, I started this one with just a quick digest. It didn't ha- it didn't have our CRM connected, it didn't have that. And then over time I was like, "Oh, here's something else that might be helpful." And so like, build something basic, see how it works, learn, and then it- you know, make time to improve it over time so that you make sure it's really being i- impactful for you and, and doing all of the things it can. And, you know, these tools are getting smarter every day. [chuckles] So also keep on top of, you know, the new, new capabilities so you can start building those into agents and, and automations and things that you've built in the past. So that's a quick overview of the-

5. 12:16 – 15:45

   Creating a culture reinforcement system through meeting feedback

   1. CVClaire Vo12:16

      Yeah

   2. CHCortney Hickey12:16

      ... agent.

   3. CVClaire Vo12:16

      Something I wanna, I wanna call out for folks is I think this workflow, um, highlights a couple strategies that I think people really need to think about. One is, I tell people, "If you are doing a repeated task every week, spend time that week automating that task." And so I, um, when I had fancy jobs, um, [chuckles] had, had an EA as well, we had a very similar process where on Fridays we would actually do a retro of the past week, prep for the next week, find out, like, all the stuff we needed to prep, make sure that I knew everything that needed to happen. And instead of spending that hour doing that prep on a Friday, I highly recommend people just say, "This, this week, I'm gonna spend an hour automating, [chuckles] automating-"

   4. CHCortney Hickey13:02

      Yeah

   5. CVClaire Vo13:02

      ... "this into an agent and see if I can replace that flow." And so I think that's a really useful mindset to bring into what and when you can automate.

   6. CHCortney Hickey13:13

      Yeah.

   7. CVClaire Vo13:14

      The second thing I would say is I love agents, in particular, the sort of like natural language format of describing agents, because you can literally just narrate what you would do.

   8. CHCortney Hickey13:25

      [chuckles]

   9. CVClaire Vo13:25

      You would be like, "First, I would go to Google, and I would look at all the meetings for the next week, and I would decide which ones I need to pre- uh, prep for. Then I would go look at my email and see what the heck we're actually meeting about. Then I would dig through Sat- Slack. I would probably go look in HubSpot, and then I would, if I was doing a great job, organize it in this way, send it to myself in Slack as a reminder, and create a bunch of to-dos."

   10. CHCortney Hickey13:50

       Yeah.

   11. CVClaire Vo13:50

       Like, you can actually use that natural language to describe an agent structure, and so I think it's a really natural way for people to get started designing some of these workflows.

   12. CHCortney Hickey14:01

       Yeah, I agree. Like, I think of agents... When I first started using them, I, I kind of started thinking of them as interns almost. So they're not gonna operate and do something completely independently from the start, but if you can teach the intern your system and how you think and give it the tools it needs, then over time, your intern gets smart enough to, to run and do things on their own. And so, you know, this is something that now I, I rarely touch this agent because it works as I, as I planned consistently. Um, you know, right now, that was a good little add that I just, I just did for the LinkedIn profile, so I can quickly add them. But, you know, there's, there's not much else I have to do here, and now I've given myself that time back, and even bigger, I can showcase this to everyone at Zapier, enable them with this template, which you can share, and then everyone can have this meeting prep agent. They can, you know, they can add different things if, if this isn't their exact workflow. Like, not everyone uses Todoist or, you know, not everyone wants XYZ, but they can customize it for their own. And so I think it's like, yeah, teach, teach people how to fish and, and teach these interns your, your way of thinking, these agents, and over time you'll be surprised of, of how much you can do. I think from EAs I hear like, "Oh, you know, AI doesn't think the way I do." I'm like, "It can though." [chuckles] Like-

   13. CVClaire Vo15:20

       Yeah

   14. CHCortney Hickey15:21

       ... it can, um, as long as you can figure out the system behind why you're doing things and be able to articulate that. But yeah-

   15. CVClaire Vo15:28

       Yeah

   16. CHCortney Hickey15:28

       ... I, I love the, like, um, the dictate to Copilot too, because I do that, I'm like, "Okay, so usually I would..." And I talk to it just like that-

   17. CVClaire Vo15:35

       Yeah

   18. CHCortney Hickey15:35

       ... like as if I'm on a walk with a friend, and, and see what it comes back with. And so yeah, this is, this is like one of those things that's just a no-brainer to spend a little

6. 15:45 – 18:12

   EAs’ unique position to leverage these tools

   1. CHCortney Hickey15:45

      bit of time on, and then you- it just runs in the background.

   2. CVClaire Vo15:48

      Yeah. And I think, you know, EAs in particular are so well-positioned to make some of these tools for the broader organization because, you know, you're a point of leverage in a team, and if you can systematize that leverage, I think two things happen: one, you can do a higher level job supporting your exec or your team. Two, everybody else gets a little bit of, of, of a boost that you wouldn't be able to personally give them. And so-

   3. CHCortney Hickey16:19

      Yeah

   4. CVClaire Vo16:19

      ... I think, you know, everybody should think like, "Oh my gosh, I could have my own little mini, you know, assistant, or I could have my own little army of interns if I can just describe what I need them to do," and I think that's really interesting. The last thing I will say is I have a very almost exact workflow in Zapier Agents. It's called my Sunday Scaries Prep.

   5. CHCortney Hickey16:41

      [chuckles]

   6. CVClaire Vo16:41

      I do it on, I do it on Sundays when I start to feel lots of anxiety-

   7. CHCortney Hickey16:45

      Yeah

   8. CVClaire Vo16:46

      ... about now, um, what I'm planning for the next week. And the one add that I put in here is you can actually mix professional and personal stuff.

   9. CHCortney Hickey16:54

      Mm.

   10. CVClaire Vo16:55

       So I put in there, "If my mornings allow me to walk my kids to school, block off, you know, this hour to this hour," because I know I can, like, walk the kids to school, and by Sundays, you haven't booked me on an early morning, you don't get me. And so-

   11. CHCortney Hickey17:10

       Yeah

   12. CVClaire Vo17:10

       ... I can, like, add these little, you know, call out days that I don't have time scheduled for lunch. Like, call out days where I have six hours of back-to-backs with no break. Like, give me an opportunity to improve my calendar. So I do think in addition to prep, you can do a little, like, calendar optimization, too, which is really nice.

   13. CHCortney Hickey17:29

       Totally, I agree. Like, yeah, which meetings might be able to combine, uh, or get rid of that look duplicative? You know, give, give me some recommendations for optimizing my focus time. Like, totally, the sky's the limit with, with these things, and yeah, you can totally combine personal and professional calendars into this to make it a jack of all trades and, and do everything. But this one, yeah, this one for me is focus on work.

   14. CVClaire Vo17:51

       ... you know, that if you really want hyper-efficiency, you just make an agent that says, "Find all my meetings, cancel all of them," [laughs] give me my day back.

   15. CHCortney Hickey17:59

       Yeah, the, the Ron Swanson agent, I don't know if you are- watch Parks and Recreation, but, uh-

   16. CVClaire Vo18:03

       Yeah

   17. CHCortney Hickey18:03

       ... April Ludgate scheduled all of his meetings for, like, March 31st one year-

   18. CVClaire Vo18:07

       Yeah

   19. CHCortney Hickey18:07

       ... 'cause she didn't think that existed [chuckles] and then-

   20. CVClaire Vo18:09

       Yeah, exactly.

   21. CHCortney Hickey18:10

       Perfect. Schedule

7. 18:12 – 24:03

   Building an automated meeting coach

   1. CHCortney Hickey18:12

      all my meetings for March 31st. [chuckles]

   2. CVClaire Vo18:13

      You know, you have one other meeting-related workflow, which I think is really interesting, which is making sure that the meetings that you do really are high value.

   3. CHCortney Hickey18:21

      Yeah.

   4. CVClaire Vo18:21

      Um, so I'd love to- for you to walk us through what you do there.

   5. CHCortney Hickey18:25

      Totally. So there's a few things, um, on the other side of meetings that I do. So one of them is, you know, this is, uh, Wade, the CEO of Zapier. So I was basically... The way this workflow came up was we use Fathom for our meeting note-taking. So I was manually going into Fathom after each executive meeting and giving it a prompt, like, "How did we perform against, uh, the five dysfunctions of a team?" Which is a framework we use from the table group, or, "Who in this meeting could have spoke up more?" And I was giving it prompts to see how Fathom did with more reasoning and more of a loose, like, feedback, uh, creative prompt versus what were the action items, which of course, it does excellently. And over time, I was like: This is pretty useful. And so I was manually doing that in Fathom, sending it to the exec team, and Wade sent me this message. He's like: "I feel like we need to turn this meeting coaching on across the org. It's a pretty useful accountability mechanism." I think the other thing here is when feedback is maybe automated, uh, growth through feed- feedback is one of our values, so it's part of how the company runs. But when feedback is expected after a meeting and becomes a part of routine and coaching, then folks learn to expect it, and it's part of their behavior, and it doesn't make their, like, you know, that nervousness spike up when they get-

   6. CVClaire Vo19:46

      Yeah

   7. CHCortney Hickey19:46

      ... feedback come in. So I think the more feedback folks can get, the better. But I think the other thing this does is take some spit off the ball. So, uh, so you know, after meetings, I've worked at this team, this exec team for five years, so no one would be offended if I said, like, "You know, Brandon, you really, like, should have-

   8. CVClaire Vo20:05

      Yeah

   9. CHCortney Hickey20:05

      ... spoken up on that topic." I can call them out because they've given me the permission to do that. But for folks who are newer to our organization or don't have that comfort level with the team, you can build this meeting coaching across the org to... and automate it based on any meeting transcript. So, you know, I started working with him, uh, with, uh, you know, with Fellow, 'cause we're moving over to Fellow for AI note-taking, and was testing an agent. You know, I was giving Wade, you know, here's an example of the feedback it generated. It gave him speaking time, it gave him, you know, what went well. It gave him opportunities to am- amplify impact. And then he's like: "This coaching is too soft. Like, this, this is still what went well. Let's have it be tougher." So then I gave it... Mm, you know, I fixed the agent instructions to give it a better balance of being demanding and supportive, which is a term we use a lot, um, here at Zapier, of like, you have to be a demanding leader, but you also have to be supportive. So I gave him this one, which, which did, uh, did give some more growth opportunities, like address misalignment more directly, you know, challenge the decision-making speed. It seems like you have some fear of conflict. And so we worked at that, gave it a more concise version, thought it was good enough to ship, and then, so now we've, we've shipped this kind of meeting feedback automation system, um, through, through Fellow. But this basically takes all of the transcript content, meeting metadata, make sure there's some, you know, some parameters. Like, if a meeting's only 10 minutes, probably not worth the feedback, and, and make sure it's only Zapier employees. Make sure there's, you know, only sufficient context to offer valuable, specific feedback. And then for each participant, it can look up their Slack, match their email address to Slack, and then send them some, you know, some, some feedback. And I gave it context on our company values, you know, some of our meeting norms, you know, how we think about decision-making, and then these are impact behaviors ser- for, like, what we expect from folks at Zapier, and then I gave it the five dysfunctions of a team. And so I really worked on this prompt over time to help it generate this direct, constructive feedback on all these dimensions. And then, you know, you can see, uh, what the outcome is gonna be, and this is, uh, you know, clarifies it's AI-generated, it's coming from a bot. Gives, you know, very quick feedback after a meeting of one to two specific growth opportunities, and, and one to two things they can, they can do next time. So this is something that I think can, over time, really just change the way that a team works together and, and change the usefulness of a meeting. So this is a, maybe not something that was a huge part of my job, and I don't calculate this as, like, a big time-saving agent for myself, kind of like the, the meeting prep was, but this is something that's, like, really reinforcing the, the company culture and, and making folks better at their jobs. So I think this is... it's cool to build stuff like this that's more, um, that's more just enablement and accountability for folks, especially among the exec team, so you make sure that they're being, like, the best displays of, of company values and norms over time. So this is a fun one that, uh, that I had, I had a good time creating with Wade.

   10. CVClaire Vo23:13

       This episode is brought to you by Brex. If you're listening to this show, you already know AI is changing how we work in real, practical ways. Brex is bringing that same power to finance. Brex is the intelligent finance platform built for founders. With autonomous agents running in the background, your finance stack basically runs itself. Cards are issues, expenses are filed, and fraud is stopped in real time without you having to think about it. Add Brex's banking solution with a high-yield treasury account, and you've got a system that helps you spend smarter, move faster, and scale with confidence.

   11. CVClaire Vo23:53

       ... One in three startups in the US already runs on Brex. You can, too, at brex.com/howiai.

8. 24:03 – 33:15

   Developing an executive document review system

   1. CVClaire Vo24:04

      So Cortney, what I think is great about this is people really think that culture is hard to systematically reinforce. You really think that culture has to be something that individuals or leaders have to carry through sort of soft interactions with the organization. But what you're showing here is more than, "Hey, I- can I give you, you know, skills coaching on closing a customer?"

   2. CHCortney Hickey24:29

      Yeah.

   3. CVClaire Vo24:30

      "Or can I give you communication coaching on managing stakeholders?" This is, are we embracing our operating principles, our cultural norms? Are we keeping an eye out for issues in interpersonal conflict or communication that we know teams are biased towards? And are we creating sort of a ego-protective [chuckles] system in order to continually check and keep ourselves accountable to that system? And so I think, like, take the meeting part of this aside, the ability to kind of consistently check interactions, and projects, and initiatives inside your organization with alignment on your stated cultural norms is a really powerful thing. And, you know, you mentioned Table Group. I've worked with them before, and, like, you get, you get them, like, once a quarter.

   4. CHCortney Hickey25:25

      Yeah.

   5. CVClaire Vo25:26

      All this great work for your leaders, and you're like: "Yeah, we're gonna, like, be the best team. We're totally aligned."

   6. CHCortney Hickey25:32

      Yeah.

   7. CVClaire Vo25:32

      "We're giving everybody feedback," but they're not whispering in your ear during the executive mee- I mean, I'm sure they would for a price, but- [chuckles]

   8. CHCortney Hickey25:39

      Yeah

   9. CVClaire Vo25:39

      ... during your executive meetings, you know, they're not listening into your company, you know, town halls or AMAs. And so I think this is just such a nice way to observe your organization from a third-party kind of, like, vantage point.

   10. CHCortney Hickey25:55

       Yeah.

   11. CVClaire Vo25:56

       And then, as you said, like, just normalize feedback. This is very stressful feedback for people to receive maybe from their boss.

   12. CHCortney Hickey26:03

       Yeah.

   13. CVClaire Vo26:04

       Like, "Hey, you didn't do this," or, "You didn't do that." But if you know everybody in the meeting is getting feedback, it's coming from sort of a neutral evaluation place, then you might be more open to hearing and kind of adjusting your, your behaviors based on that feedback.

   14. CHCortney Hickey26:21

       Yeah, totally. I think, I think you hit the nail on the head with, with a few of the main reasons why I like this. I think it's are we who we say we are? You know, are, are you who you say the... Are, are we what we say our culture is, and, and are we keeping that top of mind in between things like, you know, we're a fully remote company.

   15. CVClaire Vo26:39

       Yeah.

   16. CHCortney Hickey26:39

       We do only meet with Table Group once a quarter, once a half, and so we need to keep these behaviors top of mind consistently, and folks have a hard time keeping anything top of mind for that long. And so making sure this is repetitive and continuing to reinforce those things, uh, is valuable. But yeah, we've... I mean, we've got the other type of agent for, you know, sales reps, for example-

   17. CVClaire Vo26:59

       Yeah

   18. CHCortney Hickey26:59

       ... that gives them after gong calls what they could have done that's more like, "Okay, you should have brought up this ROI or this metric," or, you know-

   19. CVClaire Vo27:06

       Yeah

   20. CHCortney Hickey27:06

       ... more specific sales coaching, but I, I love the, the culture stuff.

   21. CVClaire Vo27:11

       Okay, this is great. So we have, um, schedule prep, we have culture checkpoints, which I think are awesome, but let's answer the question with AI that I'm not saying every IC manager and leader in the organization thinks about a lot, but they might, which is: Will this fly with CEO, or will this fly with executive A, or how do I know I'm not walking into [chuckles] into a tough meeting? So you've done, you've done some work to sort of stress test what your CEO might want or participate in without having to bother him. So I'd love to see-

   22. CHCortney Hickey27:50

       Yeah

   23. CVClaire Vo27:50

       ... your sort of exec replicate, uh, workflows.

   24. CHCortney Hickey27:54

       Totally. So yeah, a- again, on the meeting side, but this is a GPT I built within OpenAI's ChatGPT, and it's... We have this public feed in Slack, which is feed TPs, which are basically any strategic doc that need review across the company. We've kind of centralized this in a feed for transparency, accountability, and make sure folks know why we're making certain decisions. And so the folks were often coming to me for thought partnership of like: "Hey, here's my doc. Do you have any feedback on it before I share this with exec? You know, you know how Wade thinks. You've worked with him for five years. What would you think about this?" And I love doing that thought partnership stuff, and I don't wanna replace it, but again, it's not scalable, and I don't wanna be a bottleneck for someone to get their doc out into the world. And so I built a GPT that kind of thinks like, like I do and, and has some of the same materials of, like, company values and, and norms, but it helps people sharpen these TPs. And so sometimes it makes sure that, you know, folks come into a meeting with more confidence, and their opinions are stress-tested, and the right data is included, and make sure we make the most of those meetings that we're in. But sometimes the TP is so clear, uh, now that we can skip the meeting entirely, which is great as well. So you can see here, like, you know, Wade said he, he, he tried it out, caught several things that would strengthen the work. We've got, you know, Lindsay saying, "I was worried it would just tear my doc apart, but it suggested really great, simple tweaks." And so we gave it a bunch of knowledge, so I'll, I'll dive into that right now. So, um, this is the exec prep GPT. Um, I gave it a prompt here to say, "Give feedback on a TP doc," which was one of the main prompts, uh, considered, and I created a fake doc, which is a very, very poor TP, just to give an example for this. Um, so this was a TP that basically I just said, "Create a really bad EA TP doc."

   25. CVClaire Vo29:48

       [chuckles]

   26. CHCortney Hickey29:48

       Um, so this, this is like, you know, gives a really loose purpose. It, you know, doesn't have an approver. It's like-... just something we've been thinking about, doesn't have much background. So it's, it's a bad doc, so it's not, but it's not gonna give you the, the most exciting feedback. But it goes in, and again, like takes the spit off the ball of feedback and helps people, uh, you know, get more confident. But this is saying, "You know, this reads more like a jam session than a TUP. You will get better feedback if you clarify these things. Let's tighten it up." And so it gives a quick read of what you have, gives feedback on how to strengthen it, to surface trade-offs, add a recommendation, and then, you know, it gives an example of rewrite even in this case, because the doc was so loose on, on details. But it gives, you know, a couple top fixes before the bullpen, and then, which is what we call these kind of TUP meetings, and then one bold coaching question. So I, I love, uh, that it does this, and even gives you a suggested next step. Like, "Let's, let's give a tight Wade-style, one-page rewrite of this TUP- [chuckles] ... so it's bullpen ready." So, uh, I love that, and this, uh, this GPT is built off of the back of... I'll dive into it really quick.

   27. CVClaire Vo31:03

       Yep.

   28. CHCortney Hickey31:04

       But it's built off the back of, uh, you know, again, our team norms, our revenue roadmap, our strategy memo, good examples of TUPs, you know, Wade feedback tuning, a managing of to Wade doc. So it gives, like, all of this context on the back end-

   29. CVClaire Vo31:20

       Mm-hmm

   30. CHCortney Hickey31:20

       ... that can help simulate people's feedback, again, to make sure they're sharper, clearer, and better at unlocking decisions. So, uh, I love this one because it's, again, just helps enable everyone at Zapier. I love when the things that I build don't only help me, but then can have these kind of ripple effects within the organization. I think that's how you can become really an AI champion and, and transform your org, is by starting with your own wins. You know, start with your own meeting prep or whatever, but then be like, "Okay, how can I enable the next set of folks on this?"
9. 33:15 – 36:18

   Creating a centralized strategy companion in NotebookLM

   1. CVClaire Vo33:15

      useful. And what I wanna go to for our last use case is really, you've extended strategic thinking through, through the organization with another tool. So I'd love to see kind of our last, um, [lips smack] strategic alignment tool that you've built using AI, 'cause I think it's a really neat one.

   2. CHCortney Hickey33:34

      Yeah, so one thing we, we just launched about a month ago is in NotebookLM. So this is, uh, enabled through, through Google, and, uh, this is like the announcement we made in Slack to give you, uh, a high view of, of why we did this and, and what it is. But it's basically a strategy companion, which, uh, we know that folks have a hard time looking at this big-picture strategy work sometimes and then saying, "Okay, how does that impact me?" And sometimes it's just hard to find the answers you're looking for within all these different strategy docs, all-hands meetings, and so we gave folks this basically knowledge base. Uh, here, here's a screenshot of it, of, of what these look like in reality. I just, you know, cleared out the summary of our strategy-

   3. CVClaire Vo34:22

      [chuckles]

   4. CHCortney Hickey34:23

      ... to make sure I'm not, like-

   5. CVClaire Vo34:24

      [laughs]

   6. CHCortney Hickey34:24

      ... you know, totally revealing everything here. But what's great is that we can continue to add sources over time. So you can see we've got a, a few dozen sources in here, which are everything from the top-level strategy doc, to all-hands we've had, to transcripts from other meetings we've had around strategy, to e- every org's strategic action plan. And so folks can go and interact with these, but they can also interact with this in a chat capacity and ask it anything they want. So here's an example of it in, in real life. Uh, so you know, I'm saying, I just gave it a, a, a simple prompt of-

   7. CVClaire Vo35:01

      Yep

   8. CHCortney Hickey35:01

      ... "As an executive assistant, how can I contribute to Zapier's 2026 strategy?" And it's saying, "Oh, that's a great question. We- I think you can help with champion clarity, focus, and speed. Make sure we're spending time on the right priorities. You know, make sure that you're driving internal AI transformation." And so I love that it gives me, you know, some of that, and c- and connects back to the sources, but there's also fun things here, like this, uh ... It auto-generates a podcast, so I don't know if I'm fully sharing my computer sound here, but I'll play it for a couple of seconds. This is fully AI-generated just based off of the back of these sources, so it talks like this.

   9. CVClaire Vo35:38

      "Welcome to the Deep Dive. Today, we're, uh, really giving you the essential shortcut here, absolute alignment on the strategy."

   10. CHCortney Hickey35:45

       "Mm."

   11. CVClaire Vo35:45

       "We're pulling the core ideas straight from the Zapier 2026 m- "

   12. CHCortney Hickey35:49

       Uh, and all this is AI-generated, of, of things you can create. So it really helps make the strategy interactive instead of a static doc and static thing, and helps folks get their questions answered, again, before going to their leader or going to someone in their org. And so I love this for just enabling folks to-... be able to connect their work and be able to query this over time, and it's something that we can keep updated and, and make sure that it has the most recent information so everyone can,

10. 36:18 – 40:00

    How AI is transforming the EA role, not replacing it

    1. CHCortney Hickey36:18

       can get value out of it.

    2. CVClaire Vo36:19

       So Cortney, I love these use cases. What I keep reflecting [chuckles] on is people are like, "Oh, EAs, EAs are gonna go in this age of AI." And I'm like: Have you worked with a fabulous EA? Because the second they automate one task, they figure out 10 more that are so high leverage for the organization, culture-carrying behaviors, strategic, like communication, operational efficiency. Like, you are just demonstrating that this can happen at a next level. And so zooming back out, what we saw today was everything from helping yourself dig, dig out of a busy calendar with meeting prep, to enforcing your cultural goals and leadership norms through always-on feedback, checking feedback ahead of asynchronous meetings, so you can make sure it's aligned with both how executives wanna receive it, but also kind of the important business initiatives and goals of the company. And then finally, how you can take all this content that's always gen- I mean, I just don't know an organization that is not consistently writing strategy documents.

    3. CHCortney Hickey37:27

       [chuckles]

    4. CVClaire Vo37:27

       Just one strategy document to the next, big strategy document, little strategy document, strategy update, strategy goals. And so just creating a purpose-built repository for that information that can then be accessed in a multimodal way for people to learn, align their work, be educated, all that kind of stuff, I think is super awesome. So these were really, really great workflows. We're gonna do quick lightning round, and then we will get you out of here. I think the first thing is kind of this thing I, I said, which is a lot of people think your role is going away, or they're afraid of AI, um, taking over this role. And I think you're showing actually, you're just becoming so much higher leverage and have to be having so much more fun. So tell me, how do you respond to, to that feedback around AI, and in particular, the kind of EA role?

    5. CHCortney Hickey38:23

       I definitely am a believer that AI can only enable us in this role. I think it's a when, not an if. We will have to be folks that adopt these tools. There is simply too much [chuckles] to do. I think there's-- the, one of the biggest problems that EAs have is we always have more work that we wanna do than we have time for, and so that's what it's consist-- I'm consistently hearing, "I don't have enough time. I don't have enough time." Like, this is how we can do that, and I, I mean, to... I don't like talking about myself very much, but to humble brag and tie this back to real impact, I've, I've gotten, uh, three promotions since I've been here-

    6. CVClaire Vo39:01

       [chuckles]

    7. CHCortney Hickey39:02

       ... at Zapier, and been able to work myself out of multiple roles. And, you know, I think that this is how you can do that. You can be this really great AI partner for your company and make sure that you're at the forefront, and take out all that busy, manual, repetitive work off your plate, so you can do the human stuff, the fun stuff, the stuff you like to do, the stuff that's creative, um, and, and relationship-driven, and those things that we wish we had time for. And so I think that it's just, it's such an exciting thing for our role, and I don't think it's gonna take our jobs. There may be, you know, certain admin things it does take eventually, but it's not gonna take the whole thing.

    8. CVClaire Vo39:45

       Yeah.

    9. CHCortney Hickey39:45

       Think about the scope of what we do. Our whole job is to be, you know, all wide across the org and a little bit of depth in each area. But now you can be wide across the org, have more depth, and have more time for, for projects and special things that you can do

11. 40:00 – 44:32

    Lightning round and final thoughts

    1. CHCortney Hickey40:00

       for your team.

    2. CVClaire Vo40:00

       Okay, so speaking of special things, you have been one of the people I think is closest to answering this question, which is: How close do you think we are to replicating executives? How happy is Wade with your AI [chuckles] versions of him? And do you think we're actually working towards a world where those get quite high fidelity relative to individuals, preferences, feedback, thought process, communication process?

    3. CHCortney Hickey40:30

       Yeah, it's a great question. I think there are certain parts where we're getting kinda close on. So over time, you know, I used to think of myself as a clone of Wade in certain instances. I could write comms like him, I could run his schedule, I could do things like him, and now we've, we've got a clone of AI tools that are helping me do things like him, too. So there's certain parts of, of what he thinks and does that we're pretty close to replicating with these AI tools. What I'm not sure of is Wade or any exec, um, but speaking just for Wade here, he's a constant learner. He is, he is ingesting so much information, learning new things, trying new things, building every day, like hands-on keyboard. Like, the amount, uh, he can grow and learn, like, the pace of that is so high that I wonder how you could keep these models up to date with that-

    4. CVClaire Vo41:26

       Yep

    5. CHCortney Hickey41:26

       ... because, like, I, you know, I know they, they update fast, but, like, y- how can you, how can you grow at, at the pace of, of someone's brain? And, and how... You're evolving does change. Your thought process does change over time. So there's things, old things in Zapier history, where someone's like, "Oh, I heard Wade said we'll never do X, Y, Z."

    6. CVClaire Vo41:45

       [chuckles]

    7. CHCortney Hickey41:45

       And he's like, "That was an old decision. That was an old decision. Like, I have so much new context that's changing the way I think." And so for a leader who's constantly adapting, changing the way they think-... and using new information to help them make smarter decisions, how do you, how do you replicate that part of it? I don't know. There's things that- but the consistent side, like how he writes internal memos or, you know, how he writes certain things, are, we're pretty, pretty close to replicating. [laughs]

    8. CVClaire Vo42:12

       [laughs] Okay, and then final question: when, um, AI Wade is not replying to you the way you want, or you're not getting what you need out of a specific prompt, what is your prompting technique? Do you- are you all, an all-caps girl?

    9. CHCortney Hickey42:26

       [chuckles]

    10. CVClaire Vo42:26

        Do you- what do you, what do you do here?

    11. CHCortney Hickey42:28

        Oof, I am not an all-caps girl. I'm a ramble, so I love the dictate feature, and I love to talk to it, and I give it feedback very, very direct. I'm just very direct as a person and, and demanding, and so I do that. I'm like, "I don't understand why you're doing it this way. Show me your reasoning of why you did it that way, because I told you to do this, and this is what I'd like to see, and here's the feedback I have," and I just ramble and give it, you know, everything I'm thinking. I think folks, like, sometimes don't know where to start and, and try to give it this very specific feedback and write it. No, just, like, give it top of mind, pretend it's someone with no feelings, and be demanding.

    12. CVClaire Vo43:06

        [chuckles]

    13. CHCortney Hickey43:06

        So I don't know. Hopefully, the AI robots don't come for me. I do say please and thank you sometimes, so-

    14. CVClaire Vo43:11

        Good.

    15. CHCortney Hickey43:11

        Well.

    16. CVClaire Vo43:11

        Good, good. [laughs] Good.

    17. CHCortney Hickey43:13

        'Cause I hear-

    18. CVClaire Vo43:13

        Yes, AI, AI, we, uh, we, we, we know you have fe- feelings. I don't know. [laughing] We'll see what happens in 10 years.

    19. CHCortney Hickey43:20

        Yeah.

    20. CVClaire Vo43:21

        Um, okay, Cortney, this has been so great. Where can we find you, and how can we be helpful?

    21. CHCortney Hickey43:27

        Yeah, so, uh, feel free to connect with me on LinkedIn. I love posting about additional use cases, things I'm building, workshops we're having, but I'd, I'd love for y'all to check out this EA exec ops AI playbook I just made recently, which has, like, you know, six different categories of things that the EAs do consistently and in different ways. We've, we've automated that and ways that folks can replicate it and give me feedback on it. I'd love to, I'd love to hear what we're missing, what we can build out more. I'm looking for new things to build all the time, so I love, I love getting feedback from the community on what would be helpful.

    22. CVClaire Vo44:00

        Awesome. Well, thank you for joining us.

    23. CHCortney Hickey44:02

        Yeah. Thank you, Claire. [upbeat music]

    24. CVClaire Vo44:04

        Thanks so much for watching. If you enjoyed the show, please like and subscribe here on YouTube, or even better, leave us a comment with your thoughts. You can also find this podcast on Apple Podcasts, Spotify, or your favorite podcast app. Please consider leaving us a rating and review, which will help others find the show. You can see all our episodes and learn more about the show at howiai pod.com. See you next time! [upbeat music]

Episode duration: 44:32