All right, hi everybody. It is so good

to see everyone. If you are in the Grok

Bot workshop, meet Grok Bot, you're in

the right place.

Uh we'll do a quick round of intros, but

I think I'll let people trickle in. Um

my name is Amrita.

And I'm going to be the host for today.

I do really like when people actually

put where they're calling in from uh cuz

usually it's all over the world. So, if

you want to put in the chat where you're

calling from, I would love to to see all

the wonderful cities.

>> Oh, wow.

Starting with Melbourne.

2:00 a.m. Wow. Thanks for joining

Hopefully you can go to bed after this.

>> Amazing. We'll get started in just a

minute or so. Um while we're waiting,

Nate and Fuzzel, do you guys want to

introduce yourselves?

>> Yeah, sure. I can go first. Uh thank you

all for joining us. My name is Nate

Umlauf and I'm on the AI deployment team

here at Cursor. So, I basically just

make sure that that our customers are

are getting the most out of the tool.

>> Yep. Same team as Nate. Uh ADM is what

we call it. And my name is Fuzzel and

I'm happy to help with the questions in

the chat today.

>> Amazing. Um and as I said, I'm Amrita.

I'm a field engineer here at Cursor.

I've led a couple of these workshops. Um

you might have seen the we've upgraded

the AV setup, so I feel very

professional today.

Um and yeah, I'm excited to get started.

Uh I do want to just call out today's

session is about Grok Bot. And so, if

you haven't uh

set up Grok Bot or if you haven't

downloaded it yet, it's on uh Mac and

iOS. Um actually, it's on Mac and

Windows and iOS. Um so, you can actually

sign up for it at this website um

x.ai/bot.

Oh, actually, let me make sure I'm

sending that to everybody.

x.ai/bot.

Um and that's where you can sign up for

a Cursor Ultra account or a Super Grok

Heavy account and then you'll get access

to GrokBot via either of those.

We love feedback, and there's a very

easy way to send feedback via GrokBot,

so please try it out. And if you already

have it installed, follow along today.

And yeah, I'm excited to to hear and see

what you guys all think about it.

Okay.

Um let's get started. Nate and Fussel,

I'm going to probably have some natural

pauses during the session. Um and if you

guys could help

>> Cool.

>> curate common questions or things or

themes that come up, that would be

great.

>> You got it.

>> Sounds good.

>> Sweet. All right, I'm going to start up

with some slides, and then I'd love to

just jump in straight into the demo. Um

so we're going to do two demos today.

We're going to do one like general

purpose how anybody could use GrokBot,

and then we'll do one that's a little

bit more engineering focused, or even

like product and development focused. Um

and both ways you'll kind of see the

beauty and the power of of the product.

Okay.

>> one thing just to call out is if you do

have questions, make sure you put them

in there's like the little Q&A section

of Zoom, as opposed to just putting them

in the the chat where they'll probably

just kind of go to die because there's

so many people in there.

>> Thank you, Nate.

Okay. So, GrokBot.

What is GrokBot? It's basically the way

I like to describe it, a team of

always-on agents that act at your

delegation or your disposal. And what I

like about GrokBot is kind of three main

things. The first is that each bot has

memory. And so, what that means is you

basically have a persistent, long-living

agent at your disposal that you can ask

questions to, that will remember kind of

the answers it's given before. It will

also remember, you know, any follow-ups

that you've talked to it about. And I

like this because you can have basically

a long-running conversation with an

agent over weeks, months, and it'll

still be able to categorize and

understand everything you've talked

about it with it before.

GrokBot also has access to tools. So,

skills, plugins, all of the paradigms

that you've seen. Yeah, name

>> Are you Are you sharing a slide?

>> Oh my gosh, I'm so sorry. No, I'm not.

Let me share.

>> Good call, Sankar. Sweet. Perfect.

>> Thank you.

Here we go.

So, welcome to Grockbot.

It's basically your team of always-on

agents, as I've mentioned. And so, all

of these agents that you have at your

disposal are basically going to be

agents that have long-list living

memory, as well as tools and computers

at their disposal. So, you'll see that

all of these agents will actually live

inside of your Grockbot interface that

I'll show shortly. And what's nice about

these agents is that they can actually

communicate and talk to each other. So,

these three things is what I want you

all to take away from this session is

that an agent will have or your bot will

have persistent memory, it'll be

integrated in your ecosystem, and it

will also have access to its own

computer. And I'll show all of these

three things today, so you can kind of

see what makes Grockbot so special and

so different.

The main thing that I want to hone in on

today, and the main difference with

Grockbot, is we were in a world where a

lot of times we were just asking agents

to do things for us. So, we were just

saying, "Hey, can you create these

slides? Hey, can you edit this file for

me?" And we're going more from a

task-based mental model to a

persona-based mental model. So, a lot of

these bots that live inside of your

ecosystem, they have personalities, they

have roles, they are experts in

particular things. Um it's been really

fun seeing how people name their

different Grockbots, which has been

great. And so, that's kind of a good

example of how to think about, you know,

this new world where you have a team of

agents that are working on different

things.

And then, as I mentioned, you're going

to go more from asking your agent to do

things to delegation. Um and we'll see

that in a very kind of easy example

where I'm actually going to bring up a

chief of staff bot, and that bot is

actually going to delegate to other bots

that exist inside of my ecosystem.

So, again, what I want to mention today

is that these bots are meant to be

almost like colleagues or teammates, and

they're meant to use your tools like you

would use them.

So, for today we're going to start again

with the chief of staff bot, and that

bot is going to have three bots that

basically almost report to it, but that

it works well with. So, the first is an

inbox manager, the second is a schedule

coordinator, or think about it as like a

calendar manager, and then the last one

is a to-do list organizer. And what's

nice about all three of these, oh sorry,

what's nice about all three of these is

that all of them are going to be able to

talk not only to the chief of staff, but

also to each other. So, I'm going to

show this in action, and then I'm going

to pause for questions after the initial

demo, um and then show you all a little

bit about the controls and guardrails

that we put around GrokBot as well.

Okay, so let me minimize this.

And this is what I'm going to show you

first, which is just I have like a

sample calendar. Um so, I'm going to

open up

my calendar here. Um and you can see I

just have some stuff going on today, so

I have commute, I have some workout, I

have some customer calls and product

syncs. Um and what I'm going to do is

I'm going to have my chief of staff

GrokBot actually help me organize my

calendar around to-do lists that I have

to do, and around kind of what's in my

inbox right now.

Um so, I'm going to go, minimize this,

and actually open up GrokBot for you all

so you all can see it for the first

time.

So, this is what a lot of you will see

when you download GrokBot. Um it looks

very similar to iMessage, or maybe like

a chat-based interface that you've seen

before, but we try and keep it as simple

as possible, because we basically have

thought that you want to work with these

agents like you would with, you know, a

friend, a colleague, and so we kind of

created that interface to be similar.

What I'm going to do is I'm going to

create a new bot. I'm going to create my

chief of staff bot. Um Um and this is

kind of how a lot of folks really start

out with Grockit Bot is just working and

seeing what their paradigm for

organization is. So, in here I'm

actually going to click on this bot. I'm

going to call it chief of staff.

And I'm going to say, "You're my

day-to-day organizer.

Um helps me

stay on top of things."

And you can see it immediately responds

to what I name it. Um so, it's able to

understand, "Okay, this is my job." And

it's going to kind of like point me in

the right direction of does it, you

know, do I want it to run the day? Do I

want it to herd other agents or

something more specific?

What I'm going to do is I'm actually

going to ask it to spin up those three

or two other agents that I liked. So,

I'm going to say, "Um I would like you

to spin up a inbox manager, a calendar

scheduler, and a What was my last one?

Um a to-do list organizer.

And how work with those bots."

And what's nice about this is I can

always talk to my agent as it's working.

So, I can even say, "Um make sure that

you're able to access

my calendar

and my personal Gmail account."

So, while it's working, let me actually

show you how I connect to some of the

tools and plugins that actually exist

within Grogbot. So, you'll see here that

there's just one kind of entry point.

It's called plugins. And you'll notice

that I have a couple that's connected

already. So, I have Gmail, I have Google

Drive, I have calendar. Um other common

ones that people have are Notion, Slack.

But depending on your domain and your

role, you can also connect to

Salesforce, to Clay, to HubSpot. Um if

you're an engineer, obviously you can

connect to GitHub, GitLab, all of these

other tools that exist. And what's nice

about this is that it is such an easy

way to connect that you can also even

connect multiple accounts. So, I can

have my personal email, maybe my shared

calendar with my partner, my work email

all connected in the same Grok Bot

instance and it would be able to

identify between the different accounts.

Awesome. So, what you'll see here, and

this is so cool, is that it has my three

different bots here. They're all

different colors, different shapes. Um

and then my chief of staff actually has

a little staff group chat with all of

them. So, I can see here that, you know,

all of them are kind of, you know, can

talk to each other, can work on things

together. Um and so, it's kind of up to

me if I want to put stuff in this group

chat here, but I can also have my chief

of staff be the one doing the

delegating. So, you can see here that

it's connected uh to my personal email

plus my family calendar and my, you

know, calendar with my partner. Um and

so, it's going to ask me to maybe work

on a particular task related to my

calendar and to my to-do list. So, what

I'm going to do is I'm going to keep

talking to my chief of staff here. Um

and I'm going to say, uh I'm actually

going to use voice mode here. I'm going

to say,

Oop, allow. I'm going to say, I have a

ton of to-do lists uh or a ton of things

on my to-do list. I need to do my

laundry, I need to call my grandmother,

I have to go buy groceries for a big

dinner party this weekend. Um and then

tomorrow I am meeting up with a friend

to help her with a presentation for

work.

So, I'm going to pause. I'm going to

send that over. It's going to

transcribe.

Um so, I'm going to say, I have a ton of

things on my to-do list. Just like that.

Take that part out. Oop, sorry. Ton of

things.

Um

and I'm going to ask it to uh work with

my calendar scheduler and my to-do list

organizer to slot these tasks in

when I have time.

And notice that you can tag your agents

just like you would tag a person in an

iMessage group chat. Um I like that

because it kind of tells the chief of

staff who I wanted to coordinate with. A

lot of times it'll do that on its own as

well. But this is kind of a good way uh

for kind of the chief of staff to

realize, you know, this is these are the

people that I want you talking to.

And so what we're going to see is that

it's going to actually uh put all of

these things on my calendar. Um, and

what I can do if I want to maybe

customize this or make it more my own is

I can actually teach it the types of

things that I like to do at particular

times. So for example, I can say, create

a skill that shows or that make sure

that my chief of staff

always knows to that I like to do

laundry late at night.

Um,

so you can see here I'm asking it to

kind of learn from my my general

day-to-day. And what this means is that

not only does this agent have memory,

but it's able to learn from my

preferences. So this skill, which is

tends to be a an AI paradigm of

basically a superpower that the agent

has, now lives in my chief of staff

forever. And it'll be able to learn

going forward if I ever want to do

laundry that it should schedule that

late at night.

So you can see here that it kind of

makes a plan for me. Um, I'm going to go

ahead and see what it messaged my two

different bots so I can see that it told

my calendar scheduler, like, "Hey,

Amrita asked us to slot these tasks.

These are my proposed holds." Um, I can

also go back and see, you know, what it

messaged maybe my to-do organizer. It

said that it captured these four tasks

and I can actually go and see what those

four tasks are. So this is a very cool

kind of new paradigm where we're able to

see how agents can delegate to each

other, how they can talk to each other.

I've even seen agents push back on each

other and we'll actually see an example

of that in an engineering use case where

you have a front-end and back-end

engineer talking to each other. But now

if we go to my calendar, let's see how

it did.

Uh cool. All right. So, looks like it

did exactly what I want where it said I

need to call my grandmother here. Um I

think it put my laundry later at night.

There it is. Um and then it said I need

to help my friend with my work

presentation and the grocery run for the

weekend dinner party is on Saturday. Um

and I like this because, you know, I can

change this around. I can customize it

even more. Um I can make things

recurring and I can do all of that

through my Rockbot.

Awesome. I'm going to pause here. Nate

and Fussel, are there any questions I

can answer around this uh just general

delegation framework?

>> I don't think anything specific to

delegation framework, but we have just

been getting a lot of questions on theme

of

skills, markdown files, like how that

differ from, you know, using the Cursor

desktop app and and I think you're

probably going to get into it with like

teaching Grokbot a skill from a video

demonstration and sort of how that that

all works. So, I think we'll we'll

answer most of those uh throughout the

presentation.

>> Absolutely. And I'll actually cover

skills very quickly here. So, we see

that I added that skill to my chief of

staff, which is the the fact that I do

laundry late at night. Um you can see

here if I actually click into the skill,

skills are very straightforward in

Grokbot. It basically has a name, a

description, and then instructions for

the agent. What's nice about these

skills is first of all, they're

shareable. So, it's very easy to

actually publish this skill and then

maybe give it to Nate or someone else on

my team. And then they can use that same

skill very easily. Um similarly, if you

have skills that are more

engineering-focused, for example, if I

actually show you my full list of

skills, go to plugins down here, you can

see that I have a skill for my QA agent.

Um she's called QA Quincy. And I

basically tell her how I want her to do

screen recording for a QA test. And you

can see here that, you know, I have

instructions on what to record, how to

do it. But, this is an example of, you

know, a skill that you could maybe take

from Cursor or any of your previous AI

tools and just plop right into Grokbot.

And what Nate was mentioning, which is

uh kind of where we're going to start

talking about computer use, is that you

can teach your agent a skill as well.

So, for example, if I want to teach my

Chief of Staff agent, uh let's say how

to book a flight for a family vacation

I'm going on, I can actually open up my

Chief of Staff's computer. So, this is

all uh

all kind of on a remote VM. Each of my

agents, each of my bots here have access

to their own computers. And I can often

see it, you know, do things on its own.

But what I like to do sometimes is

actually teach them how to do something.

So, for example, I can hit this teach a

task button and I can actually click

into the browser here.

And I can say um I want to look at

flights from SFO to NYC. And I can

basically teach it the types of flight

that I like booking. So, for example, I

always want to use an United. Um I

always want to fly, preferably early in

the morning. Um and then, you know, if

there's anything related to the flights

itself, the type of seats I want, um

it's able to kind of understand that.

And if I just pause this now and go back

here, my Chief of Staff is now able to

learn from this demonstration. It's able

to see how someone can book a flight or

how I can book a flight, the type of

preferences I have. And it will turn

that demo into a skill. So, now my Chief

of Staff can, you know, put this flight

into my calendar and basically keep

learning from all these different

workflows that I'm showing it.

Awesome. So, a little thing about

computer use. Um

right now, uh Grokbot has access to all

of these plugins, but there are times

where there is a plugin that doesn't

exist or there's certain things that it

can't access via an MCP. That's where

computer use really comes into handy. Um

you'll notice that, you know, for if you

ever want to create slides and maybe I

actually don't know if if PowerPoint is

a plugin here. Looks like it's not, but

you can easily teach your chief of staff

how to make PowerPoint decks by just

opening up PowerPoint on your Linux VM.

Um you can also teach it how to make

slides in Google Slides if you want. Um

and so doing all of those showcasing,

doing all of the teaching of skills,

really makes it easy for Grok Bot to be

able to use its own computer and do all

of these things for you.

The last thing that I want to highlight

here, um and as I mentioned Grok Bot is

available on mobile, it's available on

desktop, is that Grok Bot operates

completely remotely, meaning that I can

close my laptop and my chief of staff,

my organizer, my calendar scheduler,

will all still run with no problem. I

don't need to keep my laptop open. I can

have all of these agents running in the

background. They can run while I'm in a

meeting. They can run while I'm away

from my keyboard. And then I can come

back and see the output. So what we

really see from Grok Bot in terms of

value and ROI is the fact that you save

time. You save so much time just by

having these agents work in the

background for you and complete things

that, you know, can be tedious, that can

be time-consuming, and that can often

times be impossible to fit in a 24-hour

day. These agents are able to do all of

those things for you.

Okay.

Um one thing that I wanted to show

besides skills, um so you can see here

that it's turning this skill into a

flight skill, and we'll come back to

this shortly, um is a routine. So you

can see here that I have this very

simple button just called create

routine, um where I can actually give my

Grok Bot a um you know, basically just a

recurring or a scheduled set of tasks

that I want it to do.

Um and here's the Google Flights skill

that I just created from that video I

showed it. Amazing.

Um a very common routine, or one that I

actually depend on, is having a routine

for my inbox. So I'm going to go to my

inbox manager now. We haven't worked too

closely with him yet, but let's see how

he does.

Um and what I'm going to do with him is

So actually going to say, um every

morning, so I'm going to say, I want you

to be like my morning briefing routine.

I'm going to say, every morning

I want you to go through my inbox.

And I'm someone that subscribes to a lot

of different magazines, newspapers,

journalistic, you know, Substack, all of

those things, but I always don't have

time to check all of them because

they're kind of scattered through my

inbox in between a bunch of spam. Um, so

I'm going to say, every morning going to

go through my inbox, I want you to check

all the newsletters I subscribe to,

and then I want you to, uh, send me a

Slack message with the highlights

from each newsletter.

And, you know, it can be like Pragmatic

Engineer, which I love. It can be The

Skimm, um, Current Affairs. There's a

lot of different ones that I subscribe

to, and so I'm just going to ask it to

basically consolidate all of that

information into one place for me, as

opposed to me kind of sifting through

all of the unreads that I have. You can

see here that I have a bunch of

different triggers. So this one I would

want probably every day, maybe at, you

know, 9:00 a.m., uh, maybe a little

earlier, 7:30. Um, but my triggers don't

have to be time-based. They can be based

on a message being sent. It can be based

on an incident being launched. And I'll

actually show an example of that

shortly. Um, but cool. I'm going to make

this so that it's active, and then what

I'll do actually is I'll just authorize

this so you all can see, um, that I'm

actually logging in to Gmail for it so

it's able to know that I I'm giving it

permission to access my email. Just

going to go in here. And then that way

it will have access to my, um, my inbox

and it's able to see all of these

things. And this is exactly what a lot

of our sales team does whenever they

want to send follow-ups. It's a little

what our marketing team does when they

need to send like mass emails is they

have kind of Rockbot give access to its

email. Beautiful. Um, and then that

they're able to, uh, run these routines

or run these kind of scheduled uh,

delegation tasks. I'm going to just do a

test run right now so we can see how

this does.

While this is running, are there any

questions I can answer from the crowd?

>> Yeah, I think a lot of things that I'm

seeing now too is related to like how do

you think about tweaking or changing the

memory of your Grok Bot which I think

you're probably about to maybe get into

here with some of the instructions and

creating these routines but that's kind

of another theme that I've I've seen

come up in the chat.

>> Yeah, I do think so the interesting

thing about memory in Grok Bot is this

is basically the first of its kind in

terms of these long-lived agents that

have persistent memory.

Memory stored in S3 buckets so it makes

it really really powerful if you ever

need to ask the agent to think about

something that it worked on maybe a week

or two weeks ago. If you ever want to

tweak your agent, I would say that

routines, skills, all of the things that

you would do normally in Grok Bot do

help kind of make your agent become more

powerful.

There's also I think good examples of

how you can tell your agent what not to

do.

LLM agents generally respond really well

to patterns and anti-patterns. So a lot

of times when I create skills and

there's a particular thing, for example,

I never want my agent to you know format

my emails in a really like haphazard

way. I can give an example in my skill

of what a good email is versus what a

bad email is. And so that's kind of a

good example of how you can teach your

agents to get better and to learn from

what they're doing but they will do that

automatically. That's kind of the beauty

of Grok Bot.

One thing I do want to call out though

while this is running is there's also

some controls that you can set with Grok

Bot in terms of what it can or cannot do

just from like a system level. So if I

go to my action settings here,

you can see I'm actually going to close

this guy. You can see that you know I

have some uh controls on so for example,

if I don't want GrokBot to, you know,

run everything without me telling it to,

I can turn this off so that it will

check each action before it runs.

But I think this is what's really cool,

which is I can give it specific

instructions on when and how it should

ask me for a particular task. So for

example, if I want GrokBot never to send

an email without my permission, I can

say when GrokBot wants to send emails to

external vendors, it should always ask

first. I can add that as a rule. Could

say when GrokBot wants to um add a new

calendar event

to my shared calendar, not my personal,

I can say that it should always ask

first. And so you can be, you know,

systematic and granular here in terms

of, "Hey, I don't want GrokBot ever to

do X, Y, and Z." And so I'm going to add

up those rules here. You can see I have

some other rules that I'm saying allow

automatically. And actually, when you

use GrokBot for the first time, it will

start prompting you being like, "Hey, do

you want me to do this? Do you want me

to always do this? Or do you want me to

never do this?" And so it's going to go

through all of these kind of test cases

with you. And then as you kind of use

GrokBot more and more, you can start

setting those uh those guardrails in the

settings automatically.

So, GrokBot has memory. GrokBot can

learn from its prior mistakes or from

what you tell it. And then GrokBot also

has controls, so you can make it very

clear when it should or should not do

something based on what permission you

gave it.

Okay. This uh morning routine is still

running. Um you can see that I have a

lot of unread emails. Um so it's giving

me kind of just like a general, like

nothing really needs a reply, a lot of

things. So this is just something, a

newsletter that I have to reply to

between my friend group that I need to

do, but other than that, um what it's

going to do is that it's going to send

me that newsletter highlight to Slack uh

based on what I told it here.

And so that's kind of a very cool way

for a lot of people to use Grokbot is

just as like an email triage or as an

email, you know, cleaner.

A lot of times I've seen that people use

it as a way to kind of filter the noise

and just really take what's important.

I've seen people file expenses using the

the computer use and the routines via

Grokbot and not having to do that

manually. And so these are really great

ways that you can kind of take those

minutes off your day that would take so

much time and actually just have an

agent do a number of them.

Nate and Fuzzel, is there anything that

you guys would like to add based on how

you guys use Grokbot before I move into

the engineering use case here?

>> I think you kind of covered the way I

use the inbox and calendar scheduler a

lot. So I have my chief of staff and I

have these what I call like utility

agents. And so I'll have the chief of

staff talk to the utility agents so that

they can get those tasks done. And then

kind of off-handing that from one agent

to another so that they can kind of

focus on that for me.

And I think that's the theme of how bots

talk to each other in Grokbot.

>> Yeah. And in this group chat, which I

love, sometimes I like to do is I like

to maybe just give it a little bit of uh

of leeway and say something like

um my inbox and my calendar are really

noisy.

Can you come up with some strategies

on how I can better organize my day?

And sometimes I do this when I'm just so

overwhelmed with the number of emails

I've gotten, with the number of calendar

events I have, uh with things that I

know have been piling up in terms of,

you know, I need to pay Xfinity, I need

to respond to X, Y, and Z. This kind of

lays things out for me in a really

systematic way. So sometimes if you

don't even know where to start. So a lot

of times if you're, you know, maybe just

opening up Grokbot and you're like, I

want to organize my life, how do I do

it? Talk to an agent about that. Get the

strategy from your agent and then you

can start kind of doing the delegation

and the organization of your team. Um

think about it like these guys are here

to help you. Um they're here to kind of

support you. They have access to your

tools so that you go don't have to go in

and do all this for you. Um I have

people that have used Grok Bot to help

them organize their finances. Um and

we're actually going to have a series of

workshops over the next coming weeks

where you'll see how Grok Bot is used in

every part of the the SpaceX AI org. So

how our sales team uses it, how our

marketing team uses it, how our FinOps

teams uses it. Um and so this is kind of

a cool way for you to see see a general

purpose, but then also kind of dive deep

into okay, what actually from this can I

take into my day-to-day?

Cool.

>> And I don't really have anything else

that to add, but I what I feel like when

I started using Grok Bot, I always found

it kind of funny to look at the

interactions between your Grok Bots and

like watch their little conversations.

Uh so that was something that I know

when I started using it, I would I would

check out and it's kind of funny to see

they can get quite testy with each other

sometimes.

>> Yeah, they really do have their their

own personalities. Um and it's it's

funny seeing what people name them. Um

you'll see my engineering team is I they

have they have cute little names.

Um but you can see here this is an

example of how a chief of staff will

kind of tag the people important, you

know, in this in the previous scenario

when I showed, I tagged them myself, but

this is a chief of staff tagging them

and basically getting responses. The

inbox manager is saying, "Okay, I'd run

like a filter." She sees only mail that

needs a reply. This morning there was

200 unread and a lot of them were from

LinkedIn. The calendar scheduler is kind

of giving her a take on this. So this is

kind of a cool way to see what the

agents think about what my day-to-day is

and this is where you would input skills

here and kind of give it more info about

how I like to run, you know, my day.

Okay, cool.

Um, I'm going to switch gears now and go

and talk about how I would extend this

to an engineering team. Um, and we can

come back and check on these guys at the

end. I would actually love to see, um,

oh, looks like my newsletter highlights

are in Slack already.

Um, so we can come back and and see how

that did. Um, but I do want to talk a

little bit about like how would you use

this at an enterprise or an industry um,

and what it looks like for particular

teams.

So, I'm actually going to close this and

I'm going to open up my engineering

team.

Um, so the cool thing about GrokBot, as

I mentioned, is that you can you can

mold it and basically

play with it so that it works inside of

your guys's workflows. Um, and so this

was actually based on how a lot of

engineers at Cursor

uh, use uh, GrokBot. And so what I'm

going to show is basically I have, I

think, five five teammates here. Um, my

main one is tech lead Taylor, so I'm

actually going to pin her, so she'll be

at the top right here. Um, and she's the

one that basically works, again, with

her engineering team

in order to build a new feature, um, or

to basically push out something to

production. Um, so all of these

engineering personas, what's nice about

this is they all have access to the

repository I'm working in. Um, it's

basically a flight booking repository

called Flylo.

Um, but what's nice about this is that

again, these are not task-based agents,

these are agents that are personas.

Meaning that back end Bobby doesn't just

have to work in this one flight booking

repo. He's a back end engineer, meaning

that I can give him another, you know,

repository. I can give him an open

source repository. I can give him a

repository that he's never seen before,

but because he's a back end engineer,

he's going to be able to learn it,

understand it, and work on it. Um, and

so that's kind of the nice thing about

these personas is they're able to work

across multiple projects, multiple

long-lived projects, but still have

their their memory, their persona, and

not have to, you know, get that that

context switching back and forth when

you're asking one agent multiple things.

Um so, what I'm going to do is two

things with my engineering team. I'm

going to show you all how I would build

a new feature. Um I'm going to start

actually with tech lead Taylor on that.

And then I'm going to show you all what

an on-call agent actually looks like. Um

so, on-call in engineering is basically

people who have to immediately fix a

incident or a bug that comes up, and it

could be at any time of the day. Um so,

I was a software engineer before this

role, and there were times where I would

have to wake up at 3:00 a.m. or 4:00

a.m. to fix an issue that was, you know,

pulling down all or that was basically

breaking production. Um and so, the nice

thing about Rockbot is you don't have to

do that. You can just have an agent

that's always on-call, and that agent

can be woken up, can be triggered at

different points of the day, and be able

to kind of solve those problems without

kind of disrupting anyone on your

engineering team and their workflow.

So, I'll start first by talking to tech

lead Taylor. Um you can see that I

actually have a skill for tech lead

Taylor, which I call the new feature

grill. And this basically is a way for

me to work with a tech lead on building

a new feature and having her ask me

questions that maybe I didn't consider.

Um so, sometimes I'll call this a

devil's advocate, or I'll call this

grill me, which is a very common skill

name. Um and you could basically use it

as a thought partner when thinking of a

new feature that you want to make.

But for today, I turned it off just cuz

she can ask a lot of questions, which is

good. I like that. This is me and her

going back and forth on some of them

actually. Um but for today, what I'm

going to do is I'm just going to ask her

to work with the team. So, I'm going to

say,

"Work with our engineering team

to build a new feature for the Flylow,

that's our booking website for the

Flylow

um project.

I want to build a way

uh to not just book flights,

but also lodging

and hotels

based on where I'm going.

So, this is a pretty big feature. Um I'm

probably going to need to spin up new

endpoints. I'm definitely going to have

brand new UI and new a new like, you

know, routes and pages I'm going to have

to build. Um I'm going to want QA Quincy

to definitely test this end to end. And

if I actually click into her here, you

can see that she takes videos of

everything that's going on. So, not just

the front end, but she'll also confirm

that the back end is working as well by

taking screenshots of the network

inspector. And so, this is a very prime

example of why you would want your

Rockbot to have access to its own

computer. You can see that it can launch

things on its own localhost port. Um

it's able to take full end-to-end video.

So, this is an example of QA Quincy

taking a video of the front end and the

back end engineer uh their PRs working

together. Um and that's kind of another

thing I want to highlight with these

engineering teams is that a lot of

times, you know, when you're starting on

a project, the tech lead kind of works

with um

works with the agents on who does what.

But sometimes there's a bit of a waiting

game, right? Where Bobby has to put up

APIs, he has to set the contract for the

APIs, and then Faye has to wait on what

Bobby is doing, and then build a UI

based on that. Um Quincy in the scenario

will have to wait to see the the back

end and the front end finish. But what

you can see here is that the tech lead

and the QA and back end engineers are

able to message each other and kind of

see, "Okay, who is still waiting on

what?" So, the the orchestration here

and the coordination between the agents

is quite seamless. It kind of takes away

all of the the dead meeting time that

you would need. Um and you basically

have these agents talking to each other,

basically being like, "Hey, have you

finished this part yet? No? Okay, cool,

then I'll work on this instead." Um

you'll also notice I actually had two

other two other agents that are no

longer with us, um product page and

release Riley. So, you can see back-end

Bobby was able to be like, "Hey, page

and Riley are not here anymore, so I'm

just going to loop in Taylor and Fay."

Um and so that's kind of a way for the

agents again to stay sharp and be aware

of what's going on around them. They

don't just do exactly what's been asked

of them, but they're able to coordinate

with the other agents as well. So, here

is Fay. She's messaged Bobby and looks

like, you know, they were saying, let's

actually go here. Oh, perfect. Fay said,

"Hey, Taylor assigned lodging as this

new thing. Um please post the contract

when you have it, all the paths methods

until then, you know, I need to wait."

Um Bobby's starting to work on it. Fay

said, "Okay, got it. Um it's going to be

owner only. We're going to just do the

destination lodging for now." And then

back Bobby said, "Okay, this is what I'm

working on. These are the endpoints just

so you have an idea." And now Fay

immediately can start on the front end.

So, it's so quick and easy for these

agents to talk to each other, um which

is really great because you want these

different agents to be able to to listen

and communicate and know when something

could be blocked.

Okay.

Um any questions Nate and Fuzzell from

the audience here?

>> We got a good one from Saad who said,

"So, technically if I set this up

properly once, I never have to open the

Cursor desktop app again.

>> [laughter]

>> Is my understanding correct?"

>> Um so, I I will say a lot of our

engineers at Cursor, Francis Thai, um

she's a wonderful engineer. She uh will

probably speak on this in a couple

weeks. Um she uses Grokbot pretty

heavily. Um she still uses Cursor. A lot

of times she'll use Cursor to review

code. She'll use Cursor for certain

features like Cursor Canvas um and some

of the other kind of tools that we have.

But, you absolutely can use Cursor, can

use cloud agents, all of the tools that

you get within cursor, you can use from

Grokbot definitely. I will say it's a

little bit more about orchestrating your

agents rather than the implementation.

Like if you look at the code, so both

Fay and Bobby will put up PRs and those

PRs you can review, you know, within

cursor or within GitHub, up to you. Um

so it's a little bit more about what the

agents are doing and less so about, you

know, how they're implementing it and

what code they're writing. That I would

still reserve for the cursor side of

things.

And actually speaking of the devil, you

can even see here how uh the UI is being

built. So if I hit open in cursor, you

can actually see the folder that it's

working in. I can actually see what the

agent is doing, how it's implementing

it. I'll start to see all of the files

here on the right. Um so I'll see all of

the diff come up. Um but you get all of

the information from Bobby, from Fay

into these cursor cloud agents, which is

where the implementation happens.

>> And one other thing that I've seen come

up in the chat um quite a bit is just

asking for more

dedicated sessions on this. We're going

to do a few of those, but I did see a

few come up around prospecting,

go-to-market, sales, stuff like that.

And I actually just put a X post from

one of our teammates, Krista, who wrote

up a really, really nice uh sort of

download of how she has used Grokbot and

how it's kind of transformed how she

works at Cursor on our go-to-market

team. So if anybody is curious about how

that works prior to the the session that

we'll do later, uh just check out the

link that I just put in the the Zoom

chat.

>> And she will also be leading a workshop

next Wednesday actually. It's not on the

calendar just yet. Um but Krista will be

talking about all of the different bots

that she uses for prospecting. And I'll

actually I'll have a slide at the end of

the session where I kind of talk about

that. Prospecting, outbounding, doing

follow-ups, all of those tools, she's

built bots for them. She also has a

chief of staff named after her very cute

dog. Um, and so you can kind of see

those workflows next Wednesday. And then

we're going to have a series, as I

mentioned, of GrokBot workshops in

particular. So we'll do one for

marketing, we'll do one for finance and

RevOps. Um, we'll do one for, uh, I

think like SDRs and just general like,

you know, BDR type workflows that can

really see the the ROI of using these

agents. So, um, we'll definitely do a

lot more of these like GrokBot for

product, GrokBot for X workshops.

Okay.

Um, while this is working, I'm going to

work with Taylor on something else. So

this is another cool thing about GrokBot

is, you know, Taylor's obviously

communicating with these agents, but

that's not her full-time job. She can

handle other things. And so what I'm

going to talk to her about actually,

while she's working with these other

agents, is spinning up an on-call agent.

So I'm going to say, "Hey Taylor,

I want to have an agent that's just

dedicated

for on-call work. I want them to be able

to monitor

Datadog and PagerDuty constantly

and to let me know

if there are any spikes in API errors or

customer issues coming up."

Um,

"Let's spin one up."

And so this is kind of where, again, you

can take multiple entry points here. You

can talk to your tech lead on how to

build it. You could actually just go in

and build it yourself with create new

bot. Um, I like working with a tech lead

because, again, with that grill me

devil's advocate skill, she asks really

good questions back. So it makes me kind

of think a little deeper about the type

of agent that I want here. Um, but she

said, "Okay, I'll create a dedicated

on-call agent pointed at Datadog and

PagerDuty." As I mentioned, these are

MCPs, so you can see that I have the

Datadog one added already. And I don't

think I I PagerDuty just yet. Yeah, I

would have to add that. Oh, looks like

it's part of my team, so maybe. Um but

these are again tools that you can

import in via the the plugins here um

and just add via OAuth. If there's any

custom uh you know, tools that you guys

use, for example, incident.io,

um

you can always just ask Cursor or ask

Rockbot to set that up for you um as an

MCP and it'll automatically be able to

identify that as well. So that's

actually another good reason why you may

still want to use Cursor here and there

is to set up these integrations between

your code and MCPs that don't exist

here. The goal is to build these plugins

more and more, so you can see here that,

you know, we have Microsoft 365, um but

we'll also have more of these tools that

make it really easy to use. Um but at

the end of the day, what I do really

like is to start with the plugins that

exist and then kind of go from there to

see what gaps.

All right, On-Call Ollie is up. That's

so funny that it kept the alliterative

names. I think that's again a testament

to Grokbot's intelligence. Um let me see

where On-Call Ollie is. So let me

actually just message them and say,

"Hey, I'm On-Call Ollie. I'm going to

watch for Fly low, Datadog, and

PagerDuty nights and weekends. I'll only

page you if API errors spike or a

customer-facing incident is actually

firing." Amazing. So this basically, in

terms of an ROI here, this basically

takes so many hours and, you know, sleep

off basically or, you know, lack of

sleep off of my engineers' time. Now

that I have this On-Call agent, it's

able to constantly monitor these

dashboards and tell me if there's

anything that I should be worried about.

And this is an example again of Grokbot

asking permission. So you can see here

that says, "Hey, I want to create a new

standing automation that will fire on

PagerDuty events and delegate to another

agent. Um it's inventing its own

routine, so it's asking me, is that

okay?" Um I'm going to say sure. I'll

say allow here. And then this one is to

poll Datadog every 15 minutes and

message Amrita on findings. So I'm going

to say allow once here as well.

Um and I can always again tweak this.

So, if I don't want it to pull these

services, what I can do is I can say

like, "Hey, I only want you to message

me um when there's like a specific

incident that's fired. So, like if a

DataDog webhook is triggered for some

reason, that's when I want you to

message me." Um but again, I can work

with this on-call agent to see what

makes sense here for my purpose.

Okay. Um let's see how we're doing with

our logging UI. So, you can see here

that it's building it's in this cloud

agent. Back in Bobby, it looks like it

finished already um or it's basically

done so that front-end Faye can actually

work on it. QA Quincy is still holding

until she gets the PRs from Bobby and

Faye. Um but while this is working, I

kind of want to show you all a previous

run of this where we actually

implemented a feature together, all all

of us, on um using your credit card

points to book flights. Um so, you can

see here that this is Quincy actually

again recording end-to-end flow of it

working. Um but what Quincy does is he's

able to get the PRs from Faye and uh

Bobby. So, you can see here immediately

Faye is able to get that, you know,

front-end quick upgrade. Um you can see

that Bobby is able to send that to Faye.

Um and so, the back and forth between

the agents for a fully fleshed out

feature. So, actually let's go ahead and

just open this PR so you all can see. Um

the back and forth is really great

because at the end I can see, okay, this

is the QA follow-up. Um the QA uh I

think agent also added a comment with

the video. Let me see if it's still

there. Maybe not. Um but that's kind of

a good way again for your agent to learn

what it should be should and should not

be doing with your PR. So, for example,

when QA Quincy first started, she wasn't

taking any screenshots of the network

inspector. And so, I asked her to do

that and then to add those videos to the

PR. So, if we actually scroll down all

the way here, you can see, "Okay, the

recording is on phase PR and the comment

is with this particular network clip."

So, if I actually go here, go back to

phase PR and I scroll down, here are all

the new back end end points that were

set up by Bobby and I keep scrolling.

Keep going. Here we go. This is my QA

screen recording immediately added as a

comment from me by QA Quincy.

Um and you can see here that I think it

even adds like a little comment at the

8-minute mark when the back end network

inspector is shown saying like, "Hey,

I'm confirming that this actually works

and this is, you know, going to be done

as expected." Um so, again, you get a

full end-to-end workflow here. You get

uh this product spec that is you're

talking about with tech lead Taylor and

then you get your fully fleshed out PR

with not just unit tests by back end,

but end-to-end tests by your QA Quincy

agent as well.

Um and so, this is how we love to build

out, you know, our engineering work. Um

some other examples of agents you can

build besides, you know, On-Call Ali, um

you can have an agent that's like a CI

watcher. Um so, Francis, the engineer

that I that I work closely with, she was

saying that she has just like a CI

watcher agent that basically checks to

see if uh you know,

all the tests in the PR are green and

then if if not, it will keep going in

and trying to auto fix things. Um and

that's kind of a nice way of basically

separating your DevOps agent from your

back end agent. Um but there's a a bunch

of different directions that you can go

here. Uh for example, you can set up a

product agent that's able to take all of

these PRs and turn them into release

notes. So, I'll actually do that with

you all. Create a new bot. I'm going to

call it

I think the previous one I had was

called product page, which I like.

Product page.

And I can say something like, "Takes the

new features built by the engineering

team

and turns them into customer-facing

release notes."

And I can even say

um the credit card point feature for Fly

Low is officially complete.

Can you talk to Bobby

Bobby and Faye?

Sorry, Fran and Faye. And um you know,

get details that we can share

with customers.

And when we released both Grok Bot and

uh Grok 4G, we'd been using this tool

for a while internally. And so I know

for a fact that our marketing teams

worked very closely with our product

teams, which worked very closely with

our engineering teams to get like our

blog posts, our Twitter posts,

everything that we basically had to do

that was customer facing, but that

needed to reflect some level of

technicality about the product, we were

able to do via Grok Bot by these agents

all talking to each other.

Um so I actually want to keep this one

up so we can see how it does and what

it's doing here. Oh, sorry. Um

but while I'm doing that, I'm going to

basically show one last thing in the 3

minutes that we have before I'll break

for questions. Um but if there's

anything else that folks would like to

see about the product, I'm happy to show

it.

>> I think um a theme was how bots can kind

of talk to each other and work together.

So is there um

is there something you've experienced

where you think maybe five or six bots

talking to each other maybe gets too

complicated? Is there some kind of uh

benchmark that you recommend of like

don't have 12 bots, you know, talking on

the same topic or or anything like that?

>> Yeah, that's a really good question. A

lot of times I ask people to to try it

out and see for themselves. I think me

personally, this is probably the limit

of the number of agents I want all

talking to each other. Um and a lot of

times what is nice about Grok Bot is

they don't always all have to talk to

each other for some, you know, tasks to

get done. That's kind of where the

intelligence of this agent-to-agent

communication is, where if I ask Taylor

to be like, "Hey, I want to build out

just the UI for this feature." It's

going to be smart enough to know to talk

just to Faye and not to Bobby.

Um and so, the agents don't always have

to talk to each other. If they do, um

I do think there is kind of a a an upper

limit on the number of agents that you

can have where it does get kind of

confusing. But, it's up to you. Um and

again, it's how you want to organize

your team. Every org, every industry,

and every enterprise has, you know,

their teams organized differently and

they have their leadership and their

managers organized differently. So,

what's nice about this and I think what

makes Grok Bot so fun is you are in

control. You get to be the CEO here and

you get to kind of organize your agents

how you like and what makes sense to

you. Um so, a bit of a non-answer there

because, you know, it's kind of

dependent on what you see, but you will

notice that the agents are smart enough

to know who should pull in at the right

time without pulling in everybody.

>> Yeah. And also, just to echo, I also

have like around 12 to 15 agents as as

my job.

>> [laughter]

>> Yeah.

>> Yeah. Um that fossil is is stronger than

me. I don't think I can handle that many

agents, but yeah.

Cool. So, this is an example of of page

basically getting the customer copy

about the the one-time credit card

payment feature that we worked on

earlier. Um what's nice is Bobby was

like, "Hey, by the way, we also just

implemented this new feature on

destination lodging. Don't forget that."

Um and so, giving that customer-facing

um piece to to product pages well. Um

you can see that QA Quincy is now

starting on the QA for back-end and

front-end for the lodging piece, which

is great. Um so, it's going to run the

full-stack cases with network and use

the desktop here. So, let's see actually

if I can see it working. Not yet. I'll

keep this open so we can see what it

does. Um there we go. It's launching

those. And then, front-end Faye is

actually asking me if I can push code

changes to a PR that other team members

can see, which is nice. This is a good

example of GrokBot being like, "Hey, I

want to make sure you're okay with

this." And I'm going to say, "Sure,

that's totally fine."

Um

And so, this is kind of where you, you

know, talk to your agents and make sure

that you are giving them the level of uh

access and permissions that you're

comfortable with.

Okay, the last thing that I do want to

show is the mobile app. Um so, again,

it's available on the App Store. Um and

we highly recommend that folks actually

just download it and see for themselves

kind of the difference. It's very

seamless between the desktop and the

mobile app, but obviously, you have a

little less real estate with with the

mobile app just cuz it's on your phone.

What I'm going to do actually is I'm

going to mirror my phone, so you all can

see what the mobile app looks like. Um

but again, as I remember or as I

recommend I highly recommend you all

downloading it. Um so, I'm just going to

connect right here. Give me 1 second.

And here we go. So, here are all of my

agents. Um we have Friend and Fay,

Quincy, Bobby. And then, we also have

Product Page, On-Call Ollie. Um I can

scroll down and see the the Inbox

Manager, Chief of Staff, all the guys I

had earlier. Um but if I click into, for

example, Friend and Fay, you can see

that it looks really, you know, very,

very similar. I can see the messaging

between the bots still, so I can go and

see all of that communication

end-to-end. Um as I mentioned, you can

add files or images. So, for example, uh

if you want Friend and Fay to copy a

particular website or a particular brand

style, you can always just add that

here. And then, voice mode. This I think

is what makes uh using GrokBot on the go

so easy is that you can just talk to it.

You can send it a message, and then it

will immediately start working. So,

especially for your Chief of Staff, if I

immediately was like, "Hey, I forgot to

buy groceries. Can you please add this

to my to-do list?" It will automatically

do that, and then we're good to go. Um

so again, really easy to coordinate

across all of these agents. Saves you so

much time,

um you know, both from a work standpoint

and a personal standpoint, but then also

is just it's fun. I think that's what I

love most about Rockbot is that it's a

really, really fun tool to use. It makes

working with agents easy.

It makes it interesting and also I think

it's just a real I think what I'm what

I'm happy about is that this is like a

really, really big leap in technology

and I'm super excited that Space X AI

and Kaskus get to be a part of that.

Um cool. So this is the mobile app.

Again, you know, pretty straightforward,

pretty easy. Launching new bots, group

new group chats, pretty straightforward.

Everything that I showed you earlier is

available here in the mobile app. It's

just, you know, a little bit constrained

vertically.

Okay.

Before we finish, I do want to just top

off with two last slides as a little

leave behinds. Sorry, let me open my my

keynote.

Um so what I want to show is the other

use cases. And again, as I mentioned,

we're going to have specific Rockbot

workshops on this. So in the marketing

use case, these are two examples where

you can have a media manager and a

growth manager that again works across

your ecosystem. For sales, you can have

a prospecting bot and an outbound bot.

And these are again just the beginning.

There's so many other use cases that you

can think of, I'm sure, for folks who

live in these in these domains.

And then the last thing is what did we

cover today in terms of what makes

Rockbot different and so powerful? I

think it's again the fact that bots that

act like teammates. These are colleagues

that can talk to you, they can talk to

each other, they can talk to their

superior. Um the persistent memory and

continuously learning. Um these are bots

that are able to remember what they did

before. For example, when back end Bobby

was talking to product page and was

like, "Hey, by the way, we worked on

this new thing. Did you forget about

that? That's something that we should,

you know, keep in mind."

And then lastly, the fact that work is

constantly happening even when the

laptop is closed. So, you can launch

Grokbot from your phone, you can launch

it from your laptop, but then you can go

ahead and close your laptop, be done for

the day, and these agents will still

continue on. Um so, a very cool product,

very excited to share this, and I'm

excited to see how you guys are going to

use it. As I mentioned, um if you want

to use it, you would want to go to

x.ai/bot.

You either download it for a Mac or on

your phone, um and these are kind of the

subscriptions that you will need in

order to try it out. Um but please give

us feedback. It is a really, really cool

feature. Um and we've seen a ton of

different use cases on Twitter. There's

a one that I love about someone who is

now running their entire plumbing

company via Grokbot and has saved them

hours of the their their day. Um so,

there's there's really a lot to uncover

here.

Okay. I'm going to stop sharing now.

Actually, you know what? I'll I'll keep

Grokbot on the screen so that y'all can

maybe just continue to see it work.

Oops. Wrong Grokbot. Let's go back here.

There we go. Um

I'll keep it on the screen, um but I'm

happy to open it up for questions in the

last 5 minutes that we have. Are there

anything any themes any things that I

can help answer?

>> I think we've gotten a number of

questions around Well, first, uh uh

checking out the recording of this. Um

I'll go ahead and put a link to our

workshops page uh on cursor.com. So,

uh this is where you'll be able to see

um Rita mentioned that Krista from our

go-to-market team is going to be doing

uh another workshop next week on how to

use Grokbot for go-to-market use cases.

So, that will all be available on the

link I just put into the chat. And this

is also where you can find uh previous

workshops that we've held. So, if you

guys are curious about checking out any

other like on-demand content, uh the

recording should all be posted there.

And then I believe

we should follow up uh if you input your

email into the Luma uh invite with a uh

an email when the recording is

available. So you guys will get

notified, but if you're ever curious

about things you maybe didn't intend or

miss in the past, a lot of those are

available on the link I just put in the

chat as well.

>> Amazing. I'm looking at some questions

here.

Again, as Nate mentioned, we will send

the recording out.

Um

People are asking

the best way to improve self or have

self-improving loops with Grok Bot. Next

thing is that Grok Bot will do that for

you. So it will learn from itself and

continuously kind of get better as you

use it. But adding skills, adding

routines, things that will basically

make it more customizable to you will

probably help. Um some other questions

are

can Grok Bot use your phone to make

calls? I do know a number of people that

have connected Grok Bot to their

iMessage API so they can actually have a

scheduled Grok Bot that texts you know,

their roommates to do the trash or

something like that. And so I'm sure

maybe you can probably you know, wire it

up to make phone calls, but I think the

the iMessage use case is a very popular

one. Um and then Shawn asked about some

sort of token context window limit.

There is no context window limit in in

Grok Bot because of the the fact that

memory stored in S3 buckets.

And so you don't have to worry about

context ever getting degraded here.

Okay.

Um if folks have used Grok Bot already,

I would love for folks to put in the

chat what they have been using it for.

If not, I'm happy to Yeah, I see that

someone has a raised hand. If they want

to come off mute and ask questions, I'm

happy to take any live questions for the

last couple minutes that we have.

It could also Oh, yeah. A couple live

questions. Okay.

Um

Alec, I think I saw your hand first. Do

you want to come off mute here?

>> Hi Rita. I had a just a quick question

about the the continual learning and

persistent memory thing.

>> Yeah.

>> So, is it is it similar to the way like

humans work where it's going to store

core concepts and things like that? Like

almost like like episodic memory instead

of having

uh

oh my gosh, I can't think of the word

right now, but like picture-perfect

memory like LLMs have so that it's more

so relying on its abilities than it is

its memory. And then the second question

that kind of is a follow-up to that is

whenever you're working on new tasks,

how does it is it just it that first

time that you do it? Is it going to kind

of be rough where you're going to have

to baby sit it along the way? And then

after that, it's going to continue to

get better or is it something that it

can essentially figure it out in one

shot the task that it hasn't done in the

past. Cuz I know Richard Sutton kind of

talked about that on the Sequoia Capital

podcast, I think a little while ago. So,

I'm just curious how Grok Bot kind of

fits into those two those two aspects of

things.

>> Yeah. Great questions. I'll answer the

second one first, which is I think with

most agents, the cold start problem is

is probably going to be there regardless

where when you talk to an agent for the

first time,

you might have to do a little bit of

hand-holding. You you kind of saw it a

little bit when the chief of staff agent

was like, "Hey, I'm a chief of staff,

but I don't really know what exactly you

want me to do here."

I do think as and then that kind of

leads into your second question, which

is the memory.

I do think right now the the memory that

we have is like a more picture-perfect

LLM type memory where you can teach it

skills, you can teach it videos, you can

give it information that it's able to

just consume based on, you know, what

it's able to see. I do think the goal,

however, is to improve memory as like

our number one feature so that it

remembers things like a human would. So,

episodic memory or even like memory

related to uh things that it's uh you

know seen or listened to. So, you know,

the concept mapping uh idea that that a

lot of humans have. So, I think that is

the goal is to improve memory so that

it's not just like an LLM-based memory

but more human-based. Um but I think

that will take a little bit of time and

training on our end as well.

>> Thank you.

>> Um cool. And then Max and Chance, since

you guys have your hands up, I'm happy

to stay for like a couple more minutes

and answer those questions. Max, you

want to go first?

I can't hear you, Max, if you're

talking.

Unfortunately.

>> Okay, can you hear me now?

>> Yes, I can.

>> Perfect. Sorry. Um so, um a couple

questions. I've been in first off,

awesome job. I mean, this was like a

full Claude code type of moment, open

Claude type of moment. And, you know, on

X, people have just been going crazy

with this, creating groups. And I think

it's really rare to have that

opportunity. So, just kudos to to you

and the whole um SpaceX AI and Cursor

teams on pulling this off. Um super

cool. And um in terms of

where uh I run a retail execution

business. And

uh we we serve some of the biggest um

food and beverage CPG brands like the

Poppys, Olipops, Chomps, Siips, and uh

Tastes.

So, um one of the things that is um

we're having a difficult time with, and

I think this might be common in a lot of

service providers, is tribal knowledge

documentation. So, we have like a tab

for everyone to, you know, document

their SOPs. And even with like record

and replay and code acts and different

things like that. And right now I have

um two different technical hires, a

senior director of AI/BI, and an

automation engineer that we just hired.

And we're

out Grokbot and we're planning on, you

know, getting this to scale out to the

entire team of about 130

>> Amazing.

>> So, we want to really figure everything

out first. So, the first big thing is

I noticed uh, you know, the the inklings

of this of passive workflow discovery.

Is there anything in the product roadmap

for passive workflow discovery where it

can monitor clicks, inputs, waste and

suggest automations

um, and skills to build for Grokbot

based on computer activity?

>> Yeah, I think so you might have seen it

in a couple of the agents where it

recommended building an automation. Like

for example, the on-call agent. It was

like, "Hey, my automation is going to be

uh, you know, polling Datadog or

PagerDuty." Um, I think another one was

my inbox manager when it was like a

clean slate. The first thing it

recommended was like, "Hey, my

automation is going to be like filtering

out any spam emails." So, I think there

is in the LLM or in in in the, you know,

the agent itself, there is some

preconceived notion of what you might

want to do.

However, I agree with you with the

tribal knowledge. I think the more I

mean, and this is true across every AI

product, the more context and the more

info you give it, the better it will be

at actually making a decision or doing

something. Um, and so I do think that

hopefully as Grokbot gets better, it

will be more aware of you know, passive

dynamic workflows and so it's able to

see like, "Hey, you know, Amrita is

often going to Google Flights, you know,

um, in in you know, her chief of staff.

Maybe we should just automatically keep

that as a skill." Um, but I think for

now the teach a skill via that video

recording is the best way to do it and

just feeding it info. So, I don't know

where your tribal docs, sorry, your

tribal knowledge docs live, but like if

you can connect to Confluence, to Google

Drive, to wherever, giving it that is

really important.

>> That's awesome. And one other quick

question is um, the other thing that our

team's been absolutely obsessed with

right now is we locked into like an

annual open AI subscription and I'm

hoping to switch it to

Rock Bot and just go all in with you

guys.

>> Great.

>> But one of the things that everyone is

obsessed with right now is the voice

mode within Coda app where you can

orchestrate and

people are now setting up skills that

you know, do a pre-flight intelligence

and then interview them in the morning

and then

>> Yeah.

>> put task notions that AI can execute and

create fan out different tasks to do

those. So I was just imagining like this

is such a cool opportunity as I cuz I

know that you guys have a pretty

advanced voice mode yourself.

>> Yes.

>> on the benchmarks and if you had not

only the ability to have like the main

orchestrator that you're talking with

have that but also each different bot

have its own personality where you can

join a group call and almost feel like

you're in a room full of team employees

where they're all talking back to you

with their own voices and personalities

and giving their expert advice if you're

trying to solve like a really difficult

problem engineering problem wise or

something like that. That would just be

like the coolest AGI moment I think for

me.

>> Yeah, and I I will say I'm I think there

will be a lot of advancements on that

end because we we have Grap Voice as a

part of SpaceX AI that's going to be a

big part of our our product suite.

So yeah, I am I am hoping for that as

well. I think Grap Voice is great. It

powers a lot of kind of really important

pieces of technology already.

So yeah, I I think that's definitely not

far on the road map and I'm excited to

see how that manifests in the product as

well.

>> Awesome. Thank you so much.

>> Of course.

I think unfortunately I do have to drop

folks. I did see two other hands Chance

and one other.

If you would like to email me, Nate or

or Fasal, our emails I'll actually just

put mine in the chat. It's Amrita at X

sorry at cursor.com Um, soon to be

Amrita at x.ai. We're still in the

process. Um, but yeah, thank you

everyone for joining. I hope this is

useful. The recording will be out soon.

Thanks, team. Thank you, Fuzzel and

Nate. Really appreciate it.