Modern Creator
Why Modern Creator?
Leveling Up with Eric Siu · YouTube

7 Ways I Use Jev + Grokbot to Run My Business

Eric Siu opens the Slack dashboard where a classifier named Jev decides pass, hold, or refuse across recruiting, outbound, content, and software spend before any human or expensive model gets involved.

Posted
today
Duration
Format
Demo
educational
Views
318
19 likes
Part of the collectionJev, explainedEvery Jev breakdown, synthesized into one page.
Read the playbook
Big Idea

The argument in one line.

A cheap classifier bot that gates every workflow into pass, hold, or refuse before a human or an expensive model gets involved is what actually lets a business run more AI agents without drowning in slop.

Who This Is For

Read if. Skip if.

READ IF YOU ARE…
  • A founder or ops lead running multiple AI workflows (recruiting, outbound, content) with no way to filter garbage before it reaches a human or an expensive model.
  • Someone building AI agents who keeps getting inconsistent 'soft pass' answers from an LLM and needs a hard gate instead.
  • A marketing or sales operator who wants leads, LinkedIn outreach, or content drafts auto-triaged into pass, hold, or refuse before anyone looks at them.
SKIP IF…
  • You're hoping for a specific no-code tool to copy. Jev, Grokbot, and the 'Chief of Staff' dashboard are internal systems Eric built, not products you can sign up for.
  • You run one simple workflow with low volume. The gate stack pays off once you have multiple bots and enough volume that a human can't eyeball every item.
TL;DR

The full version, fast.

Eric Siu runs a classifier bot called Jev in front of every AI workflow in his business, deciding pass, hold, or refuse before a human or an expensive model gets involved. He shows the actual gate tables for four systems: a Recruiting OS that screens candidates on AI fluency before a human ever sees them, a Revenue/Outbound OS that blocks duplicate outreach and personalizes cold contact with warm news, a Content/AEO OS that catches AI slop and invented statistics before publishing, and a Spend/Ops control plane that recommends SaaS renewals or downgrades. The core lesson: chunk data and run a cheap classifier before burning expensive model tokens, and never let the verbs soft, ready, send, and publish collapse into each other, because that's how automated systems leak bad output.

Free for members

Chat with this breakdown — free.

Sign in and you get 23 free chat messages on us — ask for the hook, quote a framework, find the exact transcript moment, generate a markdown action plan. Bring your own key when you want unlimited.

Create a free account →
Chapters

Where the time goes.

00:00 – 00:17

01 · Jev + Grokbot = superpowers

Cold open: combining a classifier (Jev) with an execution bot (Grokbot) is framed as an unfair AI advantage.

00:17 – 00:59

02 · How the classifier works

Jev is introduced as a classifier: it can sort a 60,000-lead list down to the 2,000 that are ICP-fit, or check content against what's already been published.

00:59 – 01:45

03 · From inputs to decisions

The shared architecture: a type-safe classifier layer that outputs a multiple-choice call, a yes/no, or a confidence score, then routes to hold/suppress/route/clear-recommend with a human-in-the-loop step before a bot executes.

01:45 – 03:33

04 · Recruiting and AI-fluency questions

The Talent Bot screens candidates on promotion history and tenure before a human sees them, sends 5 AI-fluency questions, and only passes qualified people to Juicebox and LinkedIn Recruiter / HeyReach for outbound.

03:33 – 03:58

05 · Single Brain Gateway (sponsor)

Sponsor read for Single Brain Gateway, an API gateway that connects tools, keys, and connectors into one place for agents.

03:58 – 05:00

06 · Outbound: check the relationship first

The Revenue/Outbound OS suppresses outreach to people already spoken to recently, and personalizes cold contact using warm news (like a recent promotion) inside a 30-day window.

05:00 – 05:12

07 · Website lead qualification

Website visitors who look ICP-fit get admitted, held, or suppressed, and qualified ones get pushed to the CRM automatically.

05:12 – 05:41

08 · Speed to lead

A speed-to-lead bot decides within 60 seconds whether to dial, hold, or skip a lead as spam, then calls using an AI (xAI) voice.

05:41 – 05:53

09 · LinkedIn outreach

LinkedIn intent signals via HeyReach get a pass/no-pass call before being queued for outreach.

05:53 – 07:14

10 · Content and AEO

The Content/AEO OS mines ideas from podcasts, YouTube, and internal calls, then classifies them for AI-slop tells, uncited stats, and duplicate topics before drafting.

07:14 – 07:38

11 · Single Grain (sponsor)

Sponsor read for Single Grain, Eric's AI-enabled marketing agency.

07:38 – 08:27

12 · The actual content review queue

Live look at the SEO/AEO bot's ship-ready queue: drafts score above 0.35 to auto-publish, and only borderline scores near the line get spot-checked by a human.

08:27 – 09:01

13 · Software renewal recommendations

The Haggle Bot reviews SaaS tools like Asana against actual usage data and recommends renew, downgrade, or cancel, but never auto-spends.

09:01 – 10:01

14 · Screen before expensive model work

The lesson on chunking: don't run a full dataset (like sales call transcripts) through an expensive model first. Chunk it, tag it cheaply, then escalate only the hits.

10:01 – 10:12

15 · Hold weak evidence

Claude (testing a new Opus model) caught that the workflow was doing the expensive-model-first step backwards, confirming the chunk-then-classify order is cheaper.

10:12 – 10:24

16 · Ready is not permission to act

The closing framework: gates beat soft-pass LLMs, and the four verbs soft, ready, send, and publish must never collapse into each other.

10:24 – 10:50

17 · Your next step

Closing recommendation to adopt Grokbot and Jev, and to bring a classifier layer into whatever agent harness you're already using.

Atomic Insights

Lines worth screenshotting.

  • A cheap classifier bot that only decides pass, hold, or refuse can screen thousands of leads or candidates before a human or an expensive model ever sees them.
  • Jev is built to refuse rather than fill: for recruiting, that means rejecting most candidates by design, not trying to find reasons to pass them.
  • Candidates get 5 AI-fluency questions before a human reviews them, including how much of their own money they spend on AI tools each month.
  • Reaching out to a lead who already talked to sales recently is an easy way to look unprofessional. A suppression gate blocks that outreach before it sends.
  • A speed-to-lead bot calls a qualified website visitor within 60 seconds using an AI voice, deciding first whether to dial, hold, or skip them as spam.
  • Content ideas mined from podcasts, YouTube, and internal sales calls are worthless without a classifier, because unclassified AI output just becomes more AI slop.
  • A content draft above a 0.35 'ship-ready' score is trusted to publish; only a handful of borderline scores near that line get a human's eyes.
  • A 'haggle bot' looked at actual SaaS usage data and recommended downgrading a tool, something a human never would have caught by just eyeballing the bill.
  • Burning expensive model tokens before running a cheap classifier is backwards. Chunk the data first, tag it cheaply, then only send the hits to the expensive model.
  • Four verbs, soft, ready, send, and publish, must stay separate. Collapsing them into one meaning is exactly how automated systems leak bad output.
  • A fall-closed default at a 0.55 confidence threshold, paired with honest counts, beats claiming a fix works before the receipts back it up.
  • The classifier lives as one shared layer across every bot, so improving Jev once improves recruiting, sales, content, and spend decisions at the same time.
Takeaway

Screen before you spend, and never blur the verbs.

GATE STACK PLAYBOOK

Eric Siu's real product isn't Jev or Grokbot, it's the discipline of putting a cheap pass/hold/refuse gate in front of every workflow before a human or an expensive model gets involved.

01The classifier concept
  • A classifier bot doesn't need to be smart, it needs to be cheap and consistent: pass/hold/refuse, multiple-choice, or a confidence score, run on every item before anything expensive happens.
  • The output of a classification isn't final. It routes to a human who adds judgment, then hands it back to a bot to execute, and the system gets better each time that loop runs.
04Recruiting OS
  • Screening on two promotions across two companies with a 3-year average tenure, before a human looks at a resume, cuts the review queue down to the candidates worth a human's time.
  • Five AI-fluency questions (like how much of their own money they spend on AI monthly) is a cheap, fast filter for whether a candidate can actually operate in an AI-native role.
  • The classifier is deliberately biased to reject: for high-agency hiring, rejecting almost everyone is the point, not a bug to fix.
06Revenue/Outbound OS
  • Blocking outreach to someone your team already talked to recently, or who's about to close, is a suppression rule worth building before you scale any outbound system.
  • Personalizing with real news (a promotion, a new role) inside a 30-day window turns a cold, generic outreach into a warm, specific one at almost no extra cost.
  • A speed-to-lead bot that calls a qualified visitor within 60 seconds, using an AI voice, only works because the classifier decided first whether they're worth calling at all.
10Content/AEO OS
  • An idea-mining workflow that generates 40 content ideas a day is useless without a classifier to check whether it's already been made, whether it reads like AI slop, or whether it backs up its claims.
  • A 'ship-ready' score with a hard threshold (0.35 in this system) means most drafts publish without a human re-reading them, and only borderline scores need a spot-check.
13Spend/ops control plane
  • A bot that classifies actual tool usage against what you're paying for can catch a SaaS downgrade a human would never notice by just glancing at the invoice.
  • The bot only recommends (renew/downgrade/cancel), it doesn't auto-spend. Money decisions stay one step removed from full automation.
15The core lesson
  • Running an expensive model over a full dataset before classifying it is backwards. Chunk the data, tag it cheaply, and only send the hits to the expensive model.
  • Soft, ready, send, and publish are four separate states. Treating any two of them as the same thing is exactly how automated systems leak bad output into the world.
  • A fall-closed default (reject when uncertain) paired with honest, visible counts beats claiming a fix works before the receipts prove it.
Glossary

Terms worth knowing.

Jev
The classifier bot at the center of the system. It doesn't take action, it only judges: pass, hold, refuse, or a confidence score, then hands the decision to another bot or a human.
Grokbot
The execution layer that acts on Jev's classification, including making outbound calls with an AI voice and running the day-to-day agent workflows.
ICP
Ideal Client Profile. The specific traits (industry, size, role) that mark a lead or candidate as worth pursuing, used as a filter before any outreach happens.
AEO
Answer Engine Optimization. Writing and structuring content so AI search engines and chatbots are likely to cite or quote it directly.
Speed to lead
The practice of contacting a new lead within seconds or minutes of them showing interest, before their attention moves elsewhere.
Haggle Bot
An internal bot that reviews SaaS subscriptions against actual usage data and recommends renewing, downgrading, or canceling the tool.
Ship-ready score
A numeric score Jev assigns to a content draft. Anything above the set threshold (0.35 in this system) is trusted to publish without a human re-reading it.
Fall-closed
A safety default where the classifier rejects or holds an item when it isn't confident, rather than letting uncertain items pass through.
Resources

Things they pointed at.

00:00toolGrok (xAI) ↗
03:33productSingle Brain Gateway ↗
04:15toolJuicebox
04:50toolHeyReach ↗
07:14productSingle Grain ↗
07:14toolClickFlow ↗
10:50linkLeveling Up newsletter ↗
Quotables

Lines you could clip.

02:51
“Jev is really strong at refusing rather than filling.”
Sharp, counterintuitive framing of what a classifier is actually good at.→ TikTok/Reels hook for an AI-agents audience↗ Tweet quote
05:20
“The speed to lead bot within Grokbot actually calls them using the XAI voice, and it sounds really good.”
Concrete, surprising capability claim.→ Cold open for a short on AI voice agents↗ Tweet quote
10:10
“Gates beat soft pass LLMs.”
A four-word thesis statement, screenshots well straight off the dashboard.→ Newsletter pull-quote or carousel slide↗ Tweet quote
10:12
“Soft does not equal ready, does not equal send, does not equal publish.”
Memorable four-verb framework, easy to turn into a graphic.→ IG carousel or pinned tweet↗ Tweet quote
The Script

Word for word.

Read-along

Don't just watch it. Burn it in.

See every word as it's spoken — crank it to 2× and still catch all of it. The same dual-channel trick behind Amazon's Kindle + Audible.

If you combine Jev with Grokbot, you've got an AI superpower. You've got AI advantages that other people just don't have right now. And what I'm going to do in this video is I'm going to show you how I'm using Grokbot and Jev and how you can also think about applying it to everything else that you're doing.
All right, so first and foremost, the way you want to think about Jev is it is a classifier, right? And so what this means is that it can classify a lot of the... things that you're trying to optimize for.
So let's say you're trying to optimize for people that you're trying to recruit, or you're trying to optimize for a certain set of leads that you're going for. So you want to have only ideal client profile fits in your lead list. So let's say you have a 60 ,000 list of leads.
You maybe only have... 2000 that are icp fit but you don't have to sift through all of them right from an aeo seo standpoint maybe you want it to you want to make sure that all the content you're pumping out is not related to content that you've already created right or sometimes maybe you do but you can add all these classifiers and jeff can classify it very quickly for pennies on the dollar so the way this workflow works is that you know then you have type safe jeff this is your shared layer over here and then you can basically implement hey is this a is this a choice right is it like a multiple choice like you know abcddf field close, like it's a yes or no situation, right?
Or it can be like, it can be a confidence score type of thing. So you can have different levels of classification. You can have a lot of layers of classification.
And then from there, you can decide if something is a hold, a suppress, a route, a clear recommend, and then other agents can take it over from there. Because once you have it classified, then you can kind of take it from there. And then you have a human in the loop here kind of jump in and they add in their judgment layer and then this can continue to be better over time.
And then you hand it back over to the bot and the bot executes. And this is just the future of work. The way it works for us is I'll just give you an example here for recruiting.
Okay. So we use this pretty heavily when it comes to recruiting. It's been awesome.
Okay. So again, I'm mostly talking about this from a work standpoint, but For example, if we're reaching out to someone, if we look at their profile and their profile doesn't have at least two promotions at two different companies with an average tenure of three years, we're not going to try to shortlist those people, okay?
So we have a talent bot that manages that. And the talent bot here, Jeff can decide if it's a pass, hold, miss on the roll cards. Okay, we send them five questions to kind of gauge where they are from an AI fluency standpoint, right?
So we'll ask them, hey, what percent of your work is done by AI right now? And also, what are daily AI drivers? How much of your own money are you spending on AI?
per month, we ask them those questions, right? After those questions are asked, if they respond, then it'll go ahead and evaluate them. Okay.
Then only then if they pass, then it will move over to us. And then, um, you know, we, we have a software, but that we use for, for each individual recruiting called juice box. It'll actually manage juice box as well.
It actually manages a LinkedIn recruiter as well. So it can manage the outbound there. Um, now That is at your own risk if you want to risk your own account to do that.
But we also use Hayreach for outreach as well. So Jeff is really strong at refusing rather than filling, right? But when it comes to recruiting, what are you doing?
You're rejecting most of the time because the idea here is that you're trying to recruit the top people that are in the top 1%, probably in the top, even the top 0 .1 % of people that join your company because you're trying to build an organization of high agency. curious people adaptable people that's what you're looking for right so recruiting to me as um you know the founder and the owner of the company i That is number one for me, right?
I want to make sure that we have the best team. And so that's been a godsend for us. If you're enjoying this right now, you got to check out the Single Brain Gateway.
This is free access that you can connect all of your tools in with. This is basically an API gateway. And you can have all your connectors, all your tools, all your keys in one spot, in a secure spot.
So agents can talk to it. So your team can access it as well. And there's so much more that you can do with it.
And you'll find other growth workflows within the Single Brain Gateway. So just go to singlebrain .com slash gateway to learn more. And we'll see you on the other side.
So the other thing that we have over here is, you know, we have a revenue outbound OS. Okay. So you can see here, what does this do?
Okay. So it looks for, you know, warm tier one, tier three leads. And basically it looks for people that if we're reaching out to them, it's going to suppress people that we've spoken to recently.
Basically, it's going to block customer outbound before we send. Because in the past, people just kind of blast whatever. And it's like, hey, what if we talk to these people already?
What if they're actually about to close with us and then we're reaching out to them for net new sales? That makes us look bad. It makes us look unprofessional.
And then, by the way, if there's news and we haven't talked to them. If there's warm news in the last 30 days or so, we'll reach out to these people and say, hey, you know what? Congrats on becoming CMO.
Because when you become CMO at a new company, people want to buy new stuff, right? And so we'll look for news. And then if they don't have the news, we'll still reach out to them if they're ICP fit, okay?
And so just adding that little personal touch goes a long way. Website outreach. So if someone reaches our website, they seem to be ICP fit, we'll decide.
Do we admit, hold, suppress? And do we push them to our CRM? Like if they are ICP fit, then Jev is going to help classify that again.
And speed to lead. That's okay, cool. When someone looks like they're a fit to work with us, we will decide if, do we dial them?
Do we hold? Do we skip them? Do they look like spam?
Are they already a customer, right? Are they already, are they ICP fit before we dial them within the first 60 seconds? And guess what?
The speed to lead bot within Grokbot actually calls them using the XAI voice. And it sounds really good. And by the way, guys, all these bots that I'm telling you about right now, you're not going to figure it out the first time.
Sometimes it's days of work or weeks of work to get it right. Okay. uh, LinkedIn intent.
Okay. So, um, basically we'll look at people on, on Hayreach. So Hayreach is good for LinkedIn outreach and we'll decide, are they a pass or are they go to reach out to these people?
Right. Um, before we queue them up here. So next one that I was talking to you about is this, uh, this content AO operating system.
Okay. So you can see here, uh, we can, we will mine for content ideas. So it can be from content that I'm putting out on my podcast, my YouTube channel.
Uh, it can be from our internal calls that we're ingesting, uh, client, uh, client, client objections or prospect objections, internal calls that we're having. Basically, a content spike is maybe something that's worth looking at in terms of creating content around, right?
And so every single day now, this workflow has gotten way stronger where it's giving me, you know, it was giving me 40 ideas a day, but I couldn't judge if we had produced this content already, if it looked like AI slop. If it had cited statistics, it had done all these things. I couldn't classify these things, right?
And so the problem with AI before is like you're just going to publish a bunch of slop. But now that you have this. We're making sure we have statistics in there.
We're making sure that we have some images in there. We're making sure that, is there an AI tell? We're making sure that, are we backing up our claims in there as well?
Are we making sure that we're pulling from maybe recent statistics and news as well? And then image slop gate. So if we have, we can tell through the AI tell classifier here, if we're publishing a bunch of trash where you can't even read the text.
We don't want that. If you're enjoying this, you got to check out single grain with a G single grain .com. If you need help with marketing.
AI -enabled marketing on the paid media side, on scaling creatives, on AEO SEO, on building cold outbound infrastructure, on having these agents live inside your Slack, building these managed marketing agents with a team, with people that actually know how this stuff works. Go to singlegrain .com and we'll see you on the other side.
And also, by the way, it'll review the ideas initially, it'll run a classifier. And then once it finishes drafting, it'll run like a publish gate classifier as well to make sure that this fits our guidelines. So for this SEO AE1, I'm going to show you this real quick.
And so you can see it working in actions. I've continued to improve this where it's like, hey, for the content that we're writing, I want you to make sure that we have an H1 for each of these. And it basically will put like a criteria gate saying, hey, this is actually ship ready.
And so anything above like a 0 .35 is considered ship ready. And then these are a hold over here. So very quickly, I can trust.
the judgment of this and maybe i don't have to click all these maybe i'll click like a few of these up here and a few of these down here just to make sure that the judgment is good is this already live mofu content here's the here's the headline here's the idea over here uh here's examples of where you actually covered this is this meaningfully better than what you have out there we have this haggle bot okay what the what the haggle bot does is it negotiates uh deals for us where hey are we gonna renew this sas product are we gonna downgrade it are we gonna cancel it um so asana it took a look and it's like it actually combined Jeff and it's like, it classified everything.
It's like, hey, based on this classifier, it doesn't seem like many of your users are actually active. You should probably downgrade it. So I couldn't classify that before, but now it's like, okay, well, not only can I see what we're, can this Hagglebot see what we're paying for?
It can see who's actually active within these tools. And then we can decide what to do there, right? One recommendation I have for you, one lesson that I learned from all this as well is that you don't want to burn the expensive tokens first and then put the classifier.
As often as possible, you want to avoid that. What you want to do is you want to, if you're going to evaluate a large data set, then you want to chunk the data. Okay, so let's say you're looking at a bunch of gone calls, like that sales intelligence.
So instead of... going through all the transcripts going through all of them maybe you just chunk it right so maybe like a couple minutes of each of these and then you run like a cheap tag on each of these like a numeric result an operator pain upsell signal aeo spike nothing right um now what i had done was i had queried uh jeff inside of our our slack agent that every anybody on our team can can access and i just said hey look at all of our gone calls um and then tell me where you see opportunities for um where we can kind of map out case studies right and then that's where it called out it's like hey You actually shouldn't be doing that.
And Claude actually called it out when I was testing Opus, new version of Opus. And I said, hey, it's actually way cheaper if you do it this way. And then, you know, gates beat soft pass LLMs.
Okay, so helpful model soft pass. Jev refuses when something is very thin, right? So thin being that it's low quality.
So it saves time there. And then soft does not equal ready, does not equal send, does not equal publish. So four verbs, collapsing them is how fleets leak.
And so you don't want these to kind of overlap with each other. Obviously, these are all kind of different actions over here. So anyway, I would just say that, you know, it has sped us up ultimately by having this classifier.
So highly recommend that you use Grokbot, number one. Highly recommend that you use Jev, number two, but also highly recommend that you're using Jev within any of the harnesses that you're using. I do believe that this is going to become table stakes in the next, probably within the next three to six months or so as of this recording.
So anyway, that's it for this video and we'll catch you in the next one.
The Hook

The bait, then the rug-pull.

Eric Siu doesn't pitch a tool in this video, he opens his own dashboard. Jev is the classifier that judges every lead, candidate, draft, and renewal in his business, and Grokbot is what actually acts on the verdict.

Frameworks

Named ideas worth stealing.

00:59model

The Four-Gate Stack

  1. Recruiting OS
  2. Revenue/Outbound OS
  3. Content/AEO OS
  4. Spend/Ops Control Plane

Every workflow in the business routes through the same shared classifier layer (Jev) before a bot or human acts, structured as a Gate / Owner bot / What Jev decides / Lesson-receipt table.

Steal forAny project running multiple agents (an admin job queue, a content pipeline, a submissions queue) that needs one shared trust layer instead of one-off validation per bot.
09:01process

Screen Before You Spend

  1. Chunk the dataset
  2. Run a cheap tag pass (numeric result / pain signal / spike / nothing)
  3. Only send hits to the expensive model
  4. Apply a strict ship gate

Running an expensive model over a full dataset before classifying it is backwards and burns money on rows nobody needed. Chunk first, tag cheap, escalate only the hits.

Steal forAny pipeline that processes bulk data (call transcripts, submissions, comments) before an expensive model pass.
10:12principle

The Four Verbs Discipline

  1. Soft
  2. Ready
  3. Send
  4. Publish

Soft, ready, send, and publish are four distinct states. Treating any two of them as equivalent is how an automated fleet leaks bad output into the world.

Steal forAny admin queue with an approve/publish step. Keep the states named separately in the schema instead of collapsing them into one boolean.
CTA Breakdown

How they asked for the click.

MENTIONED ON CAMERA
00:00toolGrok (xAI) ↗
03:33productSingle Brain Gateway ↗
04:50toolHeyReach ↗
07:14productSingle Grain ↗
07:14toolClickFlow ↗
10:50linkLeveling Up newsletter ↗
FROM THE DESCRIPTION
PRIMARY CTAWhere the creator wants you to go next.
OTHER LINKSAlso linked in the description.
Frame Gallery

Visual moments.

Frame at 00:00 from 7 Ways I Use Jev + Grokbot to Run My Business00:00Frame at 00:11 from 7 Ways I Use Jev + Grokbot to Run My Business00:11Frame at 00:20 from 7 Ways I Use Jev + Grokbot to Run My Business00:20Frame at 00:28 from 7 Ways I Use Jev + Grokbot to Run My Business00:28Frame at 00:36 from 7 Ways I Use Jev + Grokbot to Run My Business00:36Frame at 00:44 from 7 Ways I Use Jev + Grokbot to Run My Business00:44
Frame at 00:00 from 7 Ways I Use Jev + Grokbot to Run My Business00:00Frame at 00:11 from 7 Ways I Use Jev + Grokbot to Run My Business00:11Frame at 00:20 from 7 Ways I Use Jev + Grokbot to Run My Business00:20Frame at 00:28 from 7 Ways I Use Jev + Grokbot to Run My Business00:28Frame at 00:36 from 7 Ways I Use Jev + Grokbot to Run My Business00:36Frame at 00:44 from 7 Ways I Use Jev + Grokbot to Run My Business00:44Frame at 00:52 from 7 Ways I Use Jev + Grokbot to Run My Business00:52Frame at 01:00 from 7 Ways I Use Jev + Grokbot to Run My Business01:00Frame at 01:09 from 7 Ways I Use Jev + Grokbot to Run My Business01:09Frame at 01:17 from 7 Ways I Use Jev + Grokbot to Run My Business01:17Frame at 01:25 from 7 Ways I Use Jev + Grokbot to Run My Business01:25Frame at 01:33 from 7 Ways I Use Jev + Grokbot to Run My Business01:33Frame at 01:41 from 7 Ways I Use Jev + Grokbot to Run My Business01:41Frame at 01:49 from 7 Ways I Use Jev + Grokbot to Run My Business01:49Frame at 01:57 from 7 Ways I Use Jev + Grokbot to Run My Business01:57Frame at 02:05 from 7 Ways I Use Jev + Grokbot to Run My Business02:05Frame at 02:14 from 7 Ways I Use Jev + Grokbot to Run My Business02:14Frame at 02:22 from 7 Ways I Use Jev + Grokbot to Run My Business02:22Frame at 02:30 from 7 Ways I Use Jev + Grokbot to Run My Business02:30Frame at 02:38 from 7 Ways I Use Jev + Grokbot to Run My Business02:38Frame at 02:46 from 7 Ways I Use Jev + Grokbot to Run My Business02:46Frame at 02:54 from 7 Ways I Use Jev + Grokbot to Run My Business02:54Frame at 03:02 from 7 Ways I Use Jev + Grokbot to Run My Business03:02Frame at 03:10 from 7 Ways I Use Jev + Grokbot to Run My Business03:10Frame at 03:19 from 7 Ways I Use Jev + Grokbot to Run My Business03:19Frame at 03:27 from 7 Ways I Use Jev + Grokbot to Run My Business03:27Frame at 03:33 from 7 Ways I Use Jev + Grokbot to Run My Business03:33Frame at 03:43 from 7 Ways I Use Jev + Grokbot to Run My Business03:43Frame at 03:51 from 7 Ways I Use Jev + Grokbot to Run My Business03:51Frame at 03:56 from 7 Ways I Use Jev + Grokbot to Run My Business03:56Frame at 04:07 from 7 Ways I Use Jev + Grokbot to Run My Business04:07Frame at 04:15 from 7 Ways I Use Jev + Grokbot to Run My Business04:15Frame at 04:24 from 7 Ways I Use Jev + Grokbot to Run My Business04:24Frame at 04:32 from 7 Ways I Use Jev + Grokbot to Run My Business04:32Frame at 04:40 from 7 Ways I Use Jev + Grokbot to Run My Business04:40Frame at 04:48 from 7 Ways I Use Jev + Grokbot to Run My Business04:48Frame at 04:56 from 7 Ways I Use Jev + Grokbot to Run My Business04:56Frame at 05:04 from 7 Ways I Use Jev + Grokbot to Run My Business05:04Frame at 05:12 from 7 Ways I Use Jev + Grokbot to Run My Business05:12Frame at 05:20 from 7 Ways I Use Jev + Grokbot to Run My Business05:20Frame at 05:29 from 7 Ways I Use Jev + Grokbot to Run My Business05:29Frame at 05:37 from 7 Ways I Use Jev + Grokbot to Run My Business05:37Frame at 05:45 from 7 Ways I Use Jev + Grokbot to Run My Business05:45Frame at 05:53 from 7 Ways I Use Jev + Grokbot to Run My Business05:53Frame at 06:01 from 7 Ways I Use Jev + Grokbot to Run My Business06:01Frame at 06:09 from 7 Ways I Use Jev + Grokbot to Run My Business06:09Frame at 06:17 from 7 Ways I Use Jev + Grokbot to Run My Business06:17Frame at 06:25 from 7 Ways I Use Jev + Grokbot to Run My Business06:25Frame at 06:34 from 7 Ways I Use Jev + Grokbot to Run My Business06:34Frame at 06:42 from 7 Ways I Use Jev + Grokbot to Run My Business06:42Frame at 06:50 from 7 Ways I Use Jev + Grokbot to Run My Business06:50Frame at 06:58 from 7 Ways I Use Jev + Grokbot to Run My Business06:58Frame at 07:06 from 7 Ways I Use Jev + Grokbot to Run My Business07:06Frame at 07:14 from 7 Ways I Use Jev + Grokbot to Run My Business07:14Frame at 07:22 from 7 Ways I Use Jev + Grokbot to Run My Business07:22Frame at 07:30 from 7 Ways I Use Jev + Grokbot to Run My Business07:30Frame at 07:35 from 7 Ways I Use Jev + Grokbot to Run My Business07:35Frame at 07:47 from 7 Ways I Use Jev + Grokbot to Run My Business07:47Frame at 07:55 from 7 Ways I Use Jev + Grokbot to Run My Business07:55Frame at 08:03 from 7 Ways I Use Jev + Grokbot to Run My Business08:03Frame at 08:11 from 7 Ways I Use Jev + Grokbot to Run My Business08:11Frame at 08:19 from 7 Ways I Use Jev + Grokbot to Run My Business08:19Frame at 08:27 from 7 Ways I Use Jev + Grokbot to Run My Business08:27Frame at 08:35 from 7 Ways I Use Jev + Grokbot to Run My Business08:35Frame at 08:44 from 7 Ways I Use Jev + Grokbot to Run My Business08:44Frame at 08:52 from 7 Ways I Use Jev + Grokbot to Run My Business08:52Frame at 09:00 from 7 Ways I Use Jev + Grokbot to Run My Business09:00Frame at 09:08 from 7 Ways I Use Jev + Grokbot to Run My Business09:08Frame at 09:16 from 7 Ways I Use Jev + Grokbot to Run My Business09:16Frame at 09:24 from 7 Ways I Use Jev + Grokbot to Run My Business09:24Frame at 09:32 from 7 Ways I Use Jev + Grokbot to Run My Business09:32Frame at 09:40 from 7 Ways I Use Jev + Grokbot to Run My Business09:40Frame at 09:49 from 7 Ways I Use Jev + Grokbot to Run My Business09:49Frame at 09:57 from 7 Ways I Use Jev + Grokbot to Run My Business09:57Frame at 10:05 from 7 Ways I Use Jev + Grokbot to Run My Business10:05Frame at 10:13 from 7 Ways I Use Jev + Grokbot to Run My Business10:13Frame at 10:24 from 7 Ways I Use Jev + Grokbot to Run My Business10:24Frame at 10:29 from 7 Ways I Use Jev + Grokbot to Run My Business10:29Frame at 10:37 from 7 Ways I Use Jev + Grokbot to Run My Business10:37Frame at 10:45 from 7 Ways I Use Jev + Grokbot to Run My Business10:45
One-click upgrade to your Google

Get more breakdowns in your search results

Add Modern Creator as a preferred source and Google shows you more of our breakdowns in Search, Top Stories, and AI Overviews. It only changes what you see, and you can undo it in your Google settings anytime.

Add to Preferred SourcesOpens your Google source preferences with us pre-loaded. Tick the box and you're done.
Watch next

More from this channel + related breakdowns.