In this video, Mike, a co-founder of Zapier, demonstrates a new product called AI Bots, which integrates AI automation within the Zapier platform. The purpose of the AI Bots is to enable users to effortlessly create, customize, and control automation tasks using natural language inputs and a simplified interface. This initiative follows the initial launch of AI actions in Zapier, which successfully executed over 50 million tasks, proving the growing demand and utility for AI-driven automation.

Though many users find traditional Zapier setups complex due to high configuration demands, AI Bots aims to simplify this by allowing tasks to be automated with minimal user input. The demonstration includes setting up an AI Bot to manage daily tasks by retrieving calendar events, summarizing them, and sending messages on Slack, illustrating the bot's ability to infer and act upon instructions with some user customization for better control.

Key takeaways from the video:

Please remember to turn on the CC button to view the subtitles.

Key Vocabularies and Common Phrases:

1. automation [ˌɔtəˈmeɪʃən] - (noun) - The operation or control of equipment or a process by automatic means. - Synonyms: (mechanization, systematization, computerization)

The entire goal is to help more people in the world be able to successfully use, figure out, discover, and actually adopt automation using AI.

2. canvas [ˈkænvəs] - (noun) - A surface or area where ideas are presented or developed, often metaphorically. - Synonyms: (platform, backdrop, framework)

This is sort of a canvas view. This is usually how people set up and build zaps.

3. configuration [kənˌfɪɡjʊˈreɪʃən] - (noun) - Arrangement or setup of the components in a system. - Synonyms: (setup, structure, arrangement)

Lots of configuration, nitty gritty stuff you got to get right.

4. preview [ˈpriːvjuː] - (noun) - An advance showing or visualization of something. - Synonyms: (preview show, sample, foretaste)

Excited to give you all one of the first public previews of a new product called AI Bots.

5. inference [ˈɪnfərəns] - (noun) - The process of deriving logical conclusions from premises known or assumed to be true. - Synonyms: (deduction, reasoning, conclusion)

They will try to infer and guess and do things completely unprompted.

6. autonomous [ɔːˈtɑnəməs] - (adjective) - Capable of operating independently without control from another system. - Synonyms: (self-governing, independent, self-sufficient)

The bots making decisions completely autonomously on your behalf.

7. deterministic [dɪˌtɜrməˈnɪstɪk] - (adjective) - Having a fixed outcome and is predictable and not random. - Synonyms: (inevitable, certain, predetermined)

Get more deterministic control over how the bot makes decisions.

8. self-healing [sɛlf ˈhiːlɪŋ] - (adjective) - Capable of repairing itself or recovering functionality on its own. - Synonyms: (restorative, regenerative, recuperative)

There's a lot of self-healing capabilities.

9. colloquial [kəˈloʊkwiəl] - (adjective) - Used in ordinary or familiar conversations; not formal or literary. - Synonyms: (informal, conversational, everyday)

It seems like a very colloquial way to refer to what these systems are.

10. reliability [rɪˌlaɪəˈbɪləti] - (noun) - The quality or state of being trustworthy or performing consistently well. - Synonyms: (trustworthiness, dependability, consistency)

How much consistency and reliability matter for AI automation.

AI-powered workflow automation with Zapier co-founder Mike Knoop

Okay, up next, we have founder demos. Mike from Zapier, which rhymes with happier, is going to show us a little bit of what they've been working on over at Zapier. Hey, everyone, I'm Mike, one of the co founders of Zapier. Thank you, Sonia and Pat, for inviting me back this year to show something new. One year ago, I was here, we were launching our V one of AI actions on Zapier, an API that translates natural language into executed API calls. A bit of an update on that. Over the last year, we've executed over half a million of those on behalf of our users. And to date, we've been launching tons of other stuff AI related on Zapier. And to date, we've run over 50 million AI tasks on Zapier. If you're not familiar with Zapier, task is basically something that's completely automated on behalf. It's completely hands off.

We've heard a lot about agents today, and clearly it's happening. In fact, a lot of it's happening right now on Zapier. These are totally 100% automated. A lot of those 50 million tasks are using Zapier. Classic looks something like this. This is sort of a canvas view. This is usually how people set up and build zaps. Lots of structure. There's a high degree of learning, there's a big learning curve, lots of configuration, nitty gritty stuff you got to get right. And as a result, this sort of puts a huge depression on the amount of people who can successfully use and adopt Zapier. So that's what I've been working on the last six months. Excited to give you all one of the first public previews of a new product called AI Bots. Inside of Zapier Central is the name of the product, and this is a sort of ground up reimagining of what we're calling AI automation. Entire goal is to help more people in the world be able to successfully use, figure out, discover, and actually adopt automation using AI.

So let's show a demo of this thing right now. Probably looks pretty familiar. Standard chatbot. Instead of coming here and say hello and it will talk back to me, it doesn't do anything right now. This is sort of a blank slate bot, so let's customize it. We're going to build a new behavior. Behaviors are how you customize what these AI bots can do on your behalf. Now, these bots, you can customize them to change the behavior when you talk to them. But I think a more cool thing to show off something more new and novel is how to control this bot, doing stuff on your behalf in the background, even when you're away from your computer.

So I'm going to take a second to type in a quick prompt I have prepared. Maybe I'll do this. All right, so let's do schedule every morning, get the list of today's meetings on my gCal, summarize, define short bullets emojis, send the summary to me in slack, and we'll do this. Add a fun, automation inspired quote at the end. All right, lots of typos, but you all know that's resilient to that. So here we've got the bot starting to suggest how to automate this. So in this case, we're going to use this suggested schedule trigger. Can happen every day, every morning, let's say. Sure. 05:00 a.m. riser, and we'll add that as a trigger.

Now, what we're going to do is we're going to equip this AI bot with a set of available actions. The way to think about this is you're giving this AI bot permission to act on your behalf and do things in the real world. For this use case, the two that got suggested that are relevant, we're going to do this Google calendar find event. We want it to be able to find all of the calendar events. And I'm going to actually choose a specific calendar. We'll come back and I'll actually talk a little bit more about this in a minute. We'll add that, and then we want it to be able to send a slack message. In this case, let's not do channel message, we'll do direct message to me. Got that? And then here, I'm also going to choose a specific value for me in slack and add that, and we're all set. All right, this bot set up, it's done.

I can turn it on and it will work tomorrow morning. But I if you're like most users who use Zap, you like to test things and make sure that they work the way they do. So we'll go ahead and click test behavior. And this is one of the first cool things is we kind of introduced this concept of threading, which is how to group context together for a single task that the bot is doing. I'll try to pull this guy over. Is this legible? I can also zoom in a little bit. There we go. A little more. So there we go. Went ahead and pulled off my calendar. It's giving me a preview of what it's going to retrieve, and that all looks good.

So we'll say, yep, that looks good. Go ahead. Now, one of the cool things about the spot while this is sort of processing here, is you notice how you pick certain values for the calendar and the slack, so that's not required. One of the things these bots do out of the box is they will guess everything. This takes advantage of a lot of the AI actions technology we built over the last year out of the box. They will try to infer and guess and do things completely unprompted. Zero shot. However, one of the things we learned from real users is that doesn't always work. Oftentimes you want a degree of control over how the bot actually makes its decisions in order to increase the scope of use cases.

I think one interesting thing that I found is not every user needs that, though. There's actually a lot of use cases where you might just say, be fine with these bots making decisions completely autonomously on your behalf. But there are a lot of use cases, and it opens up the aperture, the amount of use cases you can do. If I the users can get more deterministic control over how the bot makes decisions and what it does.

All right, so it looks like a good calendar event. Sure. Let's go ahead and say go. It does like to check in a lot, so that's on our roadmap to tune that down. Other sort of fun surprises, I think, that we've learned from these AI bots. Frankly, we're still learning a lot about what these bots can do. There's a lot of cool latent capabilities built in, one that I've seen, I think Andrew mentioned this morning. There's a lot of self healing capabilities. These are hooked up in those agentic loops.

We've been able to observe the bot running into dealing with things that classically would just break zaps because they're super rigid. If you had a workflow hooked up to Google spreadsheet and somebody came in your team and they changed the name of the column in the spreadsheet, classically, a zap would just break, it'd be stuck. You'd get an error email. You have to come back and completely debug it and figure out, well, what happened here. And you always have to go through the entire learning curve of how to learn automation, how to learn reading, structured that canvas view in order to figure it out. And one of the cool things with these natural language systems is they can debug automatically and loop and fix it for you.

This is giving us a preview of the message. Let's take a quick look at that. There are a couple of links in here. Those don't actually look quite right, though. Those don't look like they're slack formatted. I think they're rendering nicely, but just from experience, I know that's not the slack link format. Let's go ahead and tell it to can you use the slack message formatting? Let that get done. Here's our automation quote. automation is like a good cup of coffee. Wakes you up with the possibilities of the day. All right, can you use slack message forming? We'll give that one more step and see if this is able to take our feedback. Which by the way, this is also another very important part of what we found from users is they want to give these bots feedback and say, hey, you did this good, you did this bad. Here's how to fix it and correct it.

One of the cool things is these bots can actually learn from the feedback instructions in order to update how they run in the future. You can see this one actually choosing to use a tool called updating instructions. This is going to take my feedback that I actually gave it, feed it back into the sort of instructions. So the next time, when this is running live and sort of completely autonomously, it's able to use that instruction to actually work.

One other maybe fun bit of trivia. Why name these things bots? When we were looking at some of our usage data of Zapier classic over the last ten years, one of the major themes that we saw is people tend to call their zaps bots. Like over a million people have named their zaps with the word bot in it. We decided to steal that name too. It seemed like a pretty good one. It seems like a very colloquial way to refer to what these systems are. Those links all look much better. That's using the right formatting there. Yep.

All right. And the very last step, hopefully, is going to be yes. And go can talk a little bit about the roadmap while we're waiting for this one to complete. I think one of the biggest lessons learned we've been getting real feedback from on this stuff is how much consistency and reliability matter for AI automation. One of the big feedback learnings we're seeing is, I think I showed it to you in the thread where kind of give feedback to the bot natural language. This is one of the biggest themes and trends we're seeing with how users want to interact with these systems is they almost think about these individual bots as their own individualized training. So the way they give them feedback, when they give them thumbs up, when they give them thumbs down, when they type them feedback, there's a very strong perception that, hey, I'm making my individual instance of the software significantly better.

That's one of the big things on our roadmap over the next couple of weeks is to be able to incorporate and take all of that feedback and actually make these things better online. There we go, it's sent. Did it show up? Slackbot render? The link's a little bit funny, but there we go. Zapier assistant from 218. That is a very quick look.

Let's see if I go back to the behavior and pop it open. There we go. You can see here at the end. Use the slack message formatting summary for sent to the user. Is that updating process where the bots are able to incorporate feedback right back into their instructions? That's Zapier AI bots in a nutshell.

I think one of the cool things is I just showed a demo with two apps on Zapier, but obviously the magic of Zapier is we support. What's the number now? Over 7000 integrations on Zapier and Zapier Central works with all 7000 out of the box, so you can connect any pairwise combination you want or even have these bots do multiple actions at once. This is. I'm not a fan or believer in waitlists, so this is available today. You can go to central dot zapier.com and log in with an existing Zapier account, or sign up for a new free Zapier account and give it a go. And excited to see what you all build with Zapier's new AI bots. Thank you.

Artificial Intelligence, Innovation, Technology, Ai Bots, Zapier, Automation, Sequoia Capital