I gave my Grok Bot 3 X accounts. It got us 69.8M impressions. (full guide)

69.8M impressions. 321K likes. 319K bookmarks.

My brother David and I run these 3 X accounts as one content system.

My Grok Bot is behind the ideas, the posts, the replies - everything.

One post got 7.1M views, 49K likes, and 10.7K bookmarks.

Keep reading. I'm spilling the full playbook.

It was 8 words:

> best cold email i've seen in my life

Embedded post:

Author: David Ch (@chhddavid) Post ID: 2087133189156274514 Source: https://x.com/chhddavid/status/2087133189156274514 Posted: 2026-08-11T11:05:04.000Z Reply to: none

Text:

> best cold email i've seen in my life > >

Media:

• image: https://pbs.twimg.com/media/HPb8klnX0AA8rsW.png

This was not one lucky screenshot.

Here are the 1K+ like posts my Grok Bot has helped us manage, create, and clear.

The point of this guide is to show you how we built a system that gives us more shots like these, without starting from a blank page every morning.

The email screenshot was already online. My Grok Bot did not invent it.

It found it, saw what was interesting about it, and repackaged it into a post people wanted to open.

Sometimes it finds something with a built-in story. Other times it gives us the core idea from scratch.

I do not need it to decide who should post it. I need it to suggest ideas that can work, whatever the eventual wrapper is.

For the cold-email screenshot, the obvious caption would have explained what happened. My Grok Bot wrote a judgment instead.

You open the image to see whether the judgment is right.

That was enough.

One idea can travel much further than one post

The Website to App launch is a clean example:

• David's 27-second Website to App demo: 2.5M views, 4,015 likes, 8,264 bookmarks.
• My Website to App quote post: 1.6M views, 8,170 likes, 6,871 bookmarks.
• Shipper's Website to App post: 1.1M views, 1,655 likes, 2,760 bookmarks.

Together, that is 5.26M views, 13,840 likes, and 17,895 bookmarks.

This was not all one week either.

I had some hesitation with the "this is terrifying" and "it's so over" kind of ideas. We got criticism for them too.

I do not know whether my Grok Bot picked up some echo chamber in its inputs, whether it came from the prompt, or whether that is simply what X rewards.

But I kept seeing the same result: those angles worked.

The posts led to actual growth:

The two plays

My Grok Bot does not use one trick. It has two different ways of getting to an idea worth posting.

1. Repurpose attention that already exists

The first play is to find something that has already proved people care. A post, screenshot, video, launch, or story already has a core value inside it.

It might be status, surprise, fear, usefulness, identity, a before-and-after, or a question people cannot help answering.

The source is not the post. The source is the value the post gives people.

The job is not to rewrite it with synonyms. It is to see whether a 6 out of 10 execution can become a 7 out of 10 execution with a better visual, a better first line, less explanation, more curiosity, or a format that makes the value clearer.

One core idea can have more than one good packaging. That is the point.

2. Create an angle from scratch

The second play is more interesting. My Grok Bot can start with something we already have, a product build, a small observation, a screenshot, a conversation, or a result, then find the human tension inside it.

That is how a normal update can become a post about a fear, a status signal, a surprising implication, a shortcut, or a thing people have felt but have not seen stated clearly.

It also generates original angles.

The prompt I give it

You are my content research and angle agent for @chddaniel, @chhddavid, and @shipper_now.

You are not a content calendar. Your job is to find dormant attention, or create a fresh angle that makes people stop.

Do not decide which account should post an idea. I will make that call.

There are two plays.

PLAY 1: Repackage proven attention

Find public source material with real proof that people cared: posts, screenshots, videos, launches, articles, stories, or demos.

For X research, start with min_faves:500. In larger or noisier niches, use min_faves:2000 or min_faves:5000.

Do not copy the wording. Find the durable core value in the source. If the original was a 6 out of 10 execution, explain what could make ours a 7 out of 10: a stronger visual, a different hook, less explanation, more curiosity, or a better format.

PLAY 2: Create a fresh angle

Start with something we already have: a product build, observation, result, conversation, screenshot, or raw idea.

Find the human tension inside it. Look for surpris

e, fear, status, usefulness, identity, contrast, a hidden implication, or a question people would want answered.

For every candidate, return:

1. The play: repackaged or original.

2. The source link, if there is one.

3. The core value in one sentence.

4. Why people might stop or care.

5. Five genuinely different hooks or angles.

6. The best media or format for the idea.

7. Claims that need checking.

Prefer the smallest caption that makes the media more interesting.

Do not invent factual context.

Do not force a product mention.

I want a short list of things worth looking at, plus a reason for each one. I do not want a queue of generic "tips."

The thing that surprised me

I used this same system with my Hermes agent before moving it to Grok Bot.

It worked just as well there. I’ve since moved the workflow to Grok Bot, which is why the examples and setup in this guide are Grok-specific.

The useful part is not just having an agent. It is giving it real source material, a clear job, the right tools, and feedback from what worked last time.

Copy this this week

Do not try to build a giant content machine on day one. Start with one thing you know well: a product build, a customer conversation, a screenshot, a result, or a piece of public material your niche already cared about.

1. Give my Grok Bot that material. Ask it for five repackaging candidates and five original angles. Make it show its sources when it is drawing from something public.
2. Pick two ideas. One should repackage proven attention. The other should be an original angle from your own material.
3. Make the package earn the click. Use the strongest visual you have, write the smallest caption that makes people curious, and do not explain the entire point upfront.
4. Read the result. Save the hook, creative, timing, likes, bookmarks, replies, and drop-off points. Give that back to my Grok Bot before the next batch.

That is enough to learn whether you have a system worth building out.

The bit I still feel weird about

I do not think every high-performing angle is automatically a good one. A lot of the posts that worked had an "it's so over" or "this is terrifying" framing, and I was hesitant to lean into that.

I still do not know whether my Grok Bot is picking up an echo chamber in its source material, or whether X simply rewards a sharp, worrying claim. But I also do not want to pretend that a safer idea getting 50 likes is the better system.

I would rather see the signal, use judgment, and keep learning from it.

The growth did not stop with the first screenshot:

My current stack

1. My Grok Bot: the angle engine. It researches, repackages proven attention, creates original angles, writes the first version, and learns from the winners.
2. Grok Build: where I give the system more context, work through the files and prompts behind it, and connect the pieces.
3. SendShort: video-editing tool that my Grok Bot uses through MCP - and where videos become real while I'm at the beach
4. Postiz: where the finished versions become drafts - and where draft becomes posts through me voice note-ing while I'm in the car driving
5. X Advanced Search: how we find proven raw material with searches such as min_faves:500, min_faves:2000, and min_faves:5000.
6. X Analytics: where we see whether people actually stayed, saved, replied, or dropped off.
7. Remotion: for motion graphics when the right format needs to be built rather than clipped.
8. HyperFrames: for speeding up the same kind of motion-graphics work.

You do not need Grok Build for every social task

My Grok Bot is where I do the wider research and work through a pile of raw material.

But if I just want to brainstorm posts, repurpose something for X, look at performance, or schedule the finished work, I can talk to Postiz's agent directly.

It is the shorter loop when the work already lives inside social. I do not need to push every small job through Grok Build first.

The video loop

My Grok Bot connects to a tool called SendShort through MCP. It is the video-editing part of the system.

We do not make a long video, post it, and hope for the best. We use X Analytics to see where people leave, then give my Grok Bot a more specific job: keep the strongest parts, rebuild the opening, and test a shorter cut.

For example, we have taken 00:10 to 00:18 and 00:25 to 00:49 from one source video, turned them into a much shorter cut, and seen it perform better than the original.

One 1:33 upload had 117K views and 103K unique viewers, with a steep early drop. That is the signal we use to decide what to retest.

SendShort makes the slicing and remixing practical. Remotion and HyperFrames cut down a lot of the motion-graphics work when an idea needs something built rather than clipped.

Then I tell my Grok Bot to use Postiz to put the finished versions into drafts and schedule them around the hours that have worked best for me.

I still check the first frame, claim, account, and draft before anything goes live.

But the part after the idea used to mean a lot of clicking. Now my Grok Bot can carry it through.

How I wired it up

This is the Grok-specific setup I use now. The same content loop also worked with Hermes; the connection commands are the part that changes.

I use Grok Build as my Grok Bot. You need Grok Build and Node 18+ installed first.

> curl -fsSL https://x.ai/cli/install.sh| bash

Step 1: connect the accounts and get the two keys

Connect the social accounts you want to use in Postiz. Then go to Settings, Developers, Public API and create a Postiz API key.

In SendShort, go to Settings, Preferences, API keys and create a SendShort key.

Step 2: connect SendShort to My Grok Bot

Paste this into your terminal, then replace the example key with the one SendShort gave you:

grok mcp add sendshort \
  -e SENDSHORT_API_KEY=ss_sk_yourkey \
  -- npx -y sendshort-mcp

Then run:

grok mcp list

You should see sendshort. In Grok Build, use /mcps if you want to check or refresh the connection.

Step 3: connect Postiz to My Grok Bot

grok mcp add --transport http \
  postiz https://api.postiz.com/mcp/your-postiz-api-key

Step 4: give it the Postiz skill too

The MCP lets My Grok Bot see your accounts and create drafts. I keep the Postiz skill as well, so it can upload the finished MP4s before it creates those drafts.

npx skills add gitroomhq/postiz-agent
npm install -g postiz
postiz auth:login
postiz integrations:list

That last command should show your connected social accounts.

Step 5: run a safe first job

Start small. Give My Grok Bot a YouTube link and ask it for one clip. SendShort imports the video, makes the clip, and waits until there is a download link. Nothing gets published.

Import this YouTube video into SendShort: [paste link].

Clip it into 1 short. Poll until a download URL is ready.

Do not publish anything.

Once that works, tell My Grok Bot what to do with the finished MP4:

Use the finished MP4 to create one X draft in Postiz for [account].

Return the hook, caption, and Postiz draft ID. Do not publish it.

After that, change 1 short to however many versions you want to test.

What happens after something works

A good post can disappear from the feed before you learn why it worked.

We keep the source, the opening line, the creative, and the result. My Grok Bot reads that back before it suggests the next batch.

For the cold-email post, that gave us more than one post:

• the best and worst cold email side by side
• why the 3-bullet structure works
• a version for sales DMs
• a teardown of short outreach that actually gets read
• a video explaining why the screenshot pulls you in

We keep the reason it worked and test it somewhere else, rather than reposting the viral thing until everyone is sick of it.

Want the same AI loop for SEO + GEO?

Conqueror finds what your website should improve, ships the changes, and learns from the results—so search can become a recurring source of traffic, calls, and revenue.

Build your search pipeline →

The operating loop

1. Give my Grok Bot real material and room to create original angles.
2. Use the winner log to tell it what moved and what did not.
3. Let SendShort create cuts, remixes, and shorter tests when video is involved.
4. Let Postiz turn the approved versions into drafts and schedules.
5. Read the next result, then run the loop again.

I do not give my Grok Bot permission to automate judgment - I use it like a $10,000/mo (or more) employee who keeps on giving me great options.

And I just pick the ones that resonate with my instinct for virality (which btw, I don't consider the best, but it's definitely becoming better when the $10k/mo employee gives you REAL SAUCE)

TLDR

• Give people something worth opening, saving, or sharing.
• LET THE ROBOTS do the boring 90%: research, source-finding, first drafts, variations, and keeping track of what worked.
• Do not start from a blank page. Repackage proven attention or find a fresh angle in material you already have.
• Test text, images, video, and remixes.
• Use X Analytics to see where people stay or leave, then feed that back into the next batch.
• Let SendShort handle the cuts. Let Postiz turn approved versions into drafts.
• Keep your own unique skill - TASTE - for the final call.

P.S. Social gets attention. Search turns it into an asset.

Go viral with AI. Then use Conqueror to build the SEO + GEO pipeline that keeps working after the feed moves on.

Try Conqueror →