Ryan
178 posts


It has never been easier to buy a marketing or advertising agency and make millions of dollars.
Every month I'm meeting founders that are doing some mind-blowing numbers in such a short period of time because they're using AI properly.
So, I put my team to work to use all of the best modern techniques that I'm seeing work right now with simple AI tools that you can use to buy agencies, grow EBITDA, and make millions of dollars.
Inside, you'll get:
The math behind the M&A.
The strategy is to grow EBITDA via revenue growth
The strategy to cut costs with AI
And far more.
All packaged in an 83-page blueprint that you can use to buy an agency right now.
Comment MNA and ill send it.
Must be following to get the DM.
GREG ISENBERG@gregisenberg
My "36 biggest startup opportunities" tweet went viral. I took the top 9 (AI, mobile apps, IRL) and did a full deep dive. Episode is live below youtu.be/IFLY6L3YPGo?si… Happy building, I'm rooting for you
English
Ryan retweetledi

everything i know about Google Ads.
7 modules. one free notion doc. video course included.
you’ll go from $0 to $1M if you apply everything that’s inside.
took me years and $250M in managed spend to learn this.
takes you 5 minutes to get it.
like, RT + comment "GOOGLE" and i'll send it over.
(must be following)
GIF
English

BREAKING: Claude Code + Meta Ads MCP replaced my $5K/month creative strategist.
It connected to my Ad Manager. Looked at my best ads. Then cranked out 12 new ads ready to launch.
Took minutes.
Here's the full system. No coding required.
Most marketers I know still download CSVs from Meta Ads. Paste them into ChatGPT. Ask "what should I change."
That worked in 2024.
In 2026 you can plug Claude right into your live Meta ad data. Uses something called MCP. Model Context Protocol.
Then run it straight into your AI ad making process.
Here's what it does.
Pulls live campaign data on command.
"Show me my top 3 ads by ROAS this week." Answer in seconds.
Finds what makes your winning ads work.
Looks at the hooks, visuals, and buttons that get clicks from your best stuff.
Writes creative briefs automatically.
Gives you the angle. The visual style. The pacing. Not spreadsheets. Real creative direction.
Makes ready-to-use prompts for HeyOz.
Copy and paste into your AI ad tool.
Get launch-ready ads from one idea.
Spots tired ads before costs spike.
Watches click rate, frequency, and spend. Tells you when an ad is dying.
Here's the part most people miss.
It doesn't just look at your ads. It makes the next batch for you.
All in one chat.
Setup takes about 15 minutes.
No coding required.
I don't know why more agencies aren't using this yet.
Comment LOOP and I'll send the one-click setup guide.
English
Ryan retweetledi
Ryan retweetledi

dm'd a girl in fitness running an info biz last week
3,400 followers. 8 months posting. 0 sales.
asked what her offer was
"$50/month coaching for women trying to lose weight"
there's the entire problem in one sentence
she changed 3 things and pulled $4,200 in the next 14 days. didn't grow her audience. didn't post more. didn't rewrite a single tweet
1. raised the price to $147 one-time payment
2. repackaged it as a 6 week sprint, not monthly coaching
3. added a half-off upsell at checkout
cheap signals trash. monthly signals desperation. no upsell signals you don't know what you're doing
your audience isn't the problem. your offer is.
most accounts on x stuck at $0/month aren't there because nobody's watching. they're there because the offer broke before anyone got close to buying it.
i wrote out the entire offer structure that actually sells on x. pricing tiers, packaging logic, the upsell stack, how to repackage what you already have without starting over. 11 pages, free.
RT + comment "OFFER" and i'll dm it (must be following)
English

Proper keyword research before a Google Ads launch takes a good media buyer 4–6 hours.
Most agencies charge $500–$1,500 just for that one deliverable.
I turned the whole thing into a single Claude prompt that spits out the same output in minutes.
Paste in your product details and it gives you:
→ the exact search terms your customers are using right now
(classified by intent - ready to buy vs. just browsing)
→ which terms to bid on first and which to avoid entirely
(the terms that drain budget are just as important to know upfront)
→ competitor terms worth targeting
(kept separate from your main campaigns - the way it should be)
→ a full negative keyword list before you spend a dollar
(this alone stops the most common beginner mistake on Google)
→ a complete campaign structure ready to build out
(campaign names, match types, bidding strategy - all of it)
works whether you're already on Google or haven't started yet.
I've generated $75M+ on Google. this is the exact research process we run before every new client launch.
Like + comment "Research" and I'll send you the prompt
(Must follow for DM)

English
Ryan retweetledi

i've been testing the new Higgsfield MCP connector to generate ALL our google ads creatives inside a normal Claude project
and results have been absolutely INSANE
so i've decided to document the ENTIRE system...
covering the setup, workflow, and ready-to-run templates to generate visuals for shopping, display, demand gen, shorts, and long-form youtube ad campaigns in SECONDS inside Claude
here's what's included inside the guide:
> 3 paths to connect Higgsfield MCP to Claude
(Claude Cowork, Claude Code with JSON config, Python for automation)
> phase-by-phase workflow:
product photography → video generation → asset organisation > campaign deployment
> 10 animation templates
covering supplements, pet care, skincare, fitness, collagen, and home goods
> batch generation prompt
builds a full asset package in one session
> the prompt feedback loop
turning one winning format into 40+ proven variants
> monthly calendar:
week-by-week production schedule to sustain creative velocity
all backed by everything i learned after generating $20M+ for ecom brands at my google ads agency.
and for 24h, it can be ALL yours for free
like + comment "GUIDE" and i'll send it over
(must be following + RT for priority access)

English

Imagine paying $1,000 for product photos in 2026...
AI can turn one product image into dozens of scroll-stopping ads.
Different styles.
Different backgrounds.
Different creatives.
All in minutes.
I made a step-by-step guide showing exactly how to do it.
Comment “Guide” and I’ll send it.
(must be following)

English

I just filmed a 50-minute Meta Ads training for 2026.
(full course)
This has everything I've ever learned after
- Making $50K in the first 20 days on a BRAND NEW ad account
- Working with 40+ businesses
- Generating over $20M+ through our funnels
And it’s going to help you overcome the 3 BIGGEST mistakes people are making with their Meta ads in 2026.
1. Generic ad messaging
2. Incongruent funnels
3. Poor pre-call systems
Thing is...
They're EASY to fix when you know the system.
And I compiled quite literally everything I know into this training.
Inside:
1. Complete Andromeda creative strategy (how to build 25-30 diverse ads)
2. Funnel structure and how to setup your landing page for paid ads
3. Pixel conditioning done right to get qualified leads only
4. Pre-call nurture system for 70-80%+ show rates
5. Campaign structures for EVERY budget
50 Minutes of pure sauce.
If you want it:
Comment "META"
And I'll send the full course.
(must be following for DM)
English

I make unlimited product shoots with codex for $0 😱
here's the system that turns one URL into a full ecomm photo library:
step 1: scout the product page
→ @firecrawl pulls the REAL product reference. package, label, claims
→ tested on gruns, rhode, blueland, stumptown. no logos, no story art, no stock
→ for shopify it grabs JSON-LD product images. cleanest ref every time
step 2: lock product truth
→ extracts the must-preserve list. ie package shape, label text, claims, product count
→ every shot locked to the real reference before generation runs
step 3: build the shot plan
→ category-aware: supplements, skincare, coffee, cleaning kits each get different taxonomies
→ PDP hero, label detail, scale-in-hand, lifestyle, email, marketplace, social vertical
→ 12 shots per run. each one ships at its real ratio.
step 4: generate the shoot
→ runs against the real reference + the preservation list
→ actual 1:1, 4:5, 9:16, 16:9. (not a square with a 16:9 label slapped on)
→ gruns full set: 12 / 12 live QA pass
→ codex uses your sub. other agents use the @OpenAI api
step 5: score every frame
→ scores product accuracy, brand fit, and artifact risk on every shot
→ nothing ships unscored
→ the point is to catch failures before you have to
step 6: reroll the failures
→ failed shots get prompts rewritten + regenerated against the SAME reference
→ stumptown first failed because story art got selected. the agent fixed it. 3/3 pass after.
→ pass or exhaust. no infinite loops.
step 7: ship the magic frontend
→ every run emits a static index.html. the showoff moment.
→ premium gallery, QA scores, export links by channel
→ open one file. show the team
input: one product URL
output: 12 product shots + a magic frontend gallery
photo shoots: $5-25K, 4 weeks. this: 10 minutes, $0.
I packaged the entire system as the Brand Shoot Kit.
7 agent skills:
- scout (real product reference detection via @firecrawl)
- preserve (locks packaging, labels, claims, geometry)
- shot-plan (category-aware PDP/lifestyle/social/email taxonomy)
- generate (ratio-aware shoot at real dimensions)
- qa (scores every frame on accuracy, brand fit, artifact risk)
- reroll (auto-fix failed shots before human review)
- export (channel renders + magic frontend)
also works with claude code, @openclaw, hermes (@nousresearch) or any agent framework
giving it away free.
comment SHOOT + like + follow
(must follow so i can DM)
English

after generating $10,000,000+ for service-based businesses with meta ads funnels…
i’m giving away EVERYTHING i’ve learned about it on a 98-page blueprint
same systems we used to profitably manage +$1M/mo in ad spend
like + comment “META” and i’ll send it to your DMs
(must be following + RT for priority access)
English

I just built a Claude and ChatGPT stack that finds leads, runs content pipelines, produces marketing assets, and cuts AI costs from a single GTM workflow every week.
Feed it your lead list, your campaign brief, and your brand design system → it studies your ICP signals, voice, and visual identity → generates qualified leads, on-brand assets, and recurring reports while you review and approve.
All inside Claude Opus 4.7 and ChatGPT 5.5.
Perfect for GTM engineers who are still running Claude and ChatGPT in separate tabs, paying Opus rates for tasks a router handles at 88% less, and briefing designers on assets Claude Design produces in minutes.
If you're running GTM across multiple AI tools in 2026, you already know the math - the teams that scale aren't the ones with the most tools, they're the ones with a stack where every tool handles the task it's actually best at. Most teams waste 40% of their AI budget on the wrong model for the wrong task if they're lucky.
This stack solves it:
→ Firecrawl and LinkedIn MCP scrape and score leads in one prompt - 100 raw contacts filtered to 50 high-intent prospects with a reason per contact and 73% connection acceptance rate vs 40% on standard campaigns
→ profile.md and hooks.md give Claude permanent voice and format context so every LinkedIn post reads like you wrote it and Playwright MCP publishes and schedules without you touching the platform
→ /loop handles short-burst local file tasks, /schedule runs cloud-based recurring reports, and ChatGPT Workspace Agents handle team-shared CRM and Slack workflows with persistent memory across runs
→ NotebookLM queries 300 sources at zero marginal cost per query and GPT 5.5 turns raw unorganised data into a clean filterable HTML executive dashboard with a working month selector in one prompt
→ Claude Code Router redirects simple high-volume tasks to Kimi K2.6 at 88% cheaper than Opus 4.7 with the same interface, same skills, and same commands
→ Claude Design extracts your full brand system in 10-15 minutes and exports it as a portable skill file every campaign planning, social content, carousel, and animated video skill calls automatically
→ ultrathink forces maximum reasoning on complex strategy prompts, /caveman cuts output tokens on bulk generation, and /clear wipes irrelevant context between unrelated tasks
No paying Opus rates for tasks a router handles for pennies.
No running Claude and ChatGPT in separate tabs with no system connecting them.
No briefing designers on assets the stack produces in minutes.
What you get:
- Full lead gen stack: Firecrawl setup, LinkNav and Apify skill, and 24-hour LinkedIn signal workflow
- LinkedIn content pipeline: profile.md template, hooks.md structure, and Playwright MCP publishing setup
- Automation decision rule: exact criteria for /loop vs /schedule vs ChatGPT Workspace Agents
- Research and asset stack: NotebookLM skill, GPT 5.5 dashboard workflow, Claude Design extraction, and ChatGPT Images 2.0 multi-format generation
- Cost cutting setup: Claude Code Router install, /caveman skill, and GPT 5.5 task routing guide
Built 100% across Claude Opus 4.7, ChatGPT 5.5, Claude Design, and ChatGPT Images 2.0.
I put together a full playbook with all skill files, the router configuration, the Notion library setup, and the exact decision rules for which tool handles which task to get the full stack running from one workflow.
Want it for free?
> Like this post
> Comment "STACK"
And I'll send it over (must be following so I can DM)

English
Ryan retweetledi

I found the BEST way to turn anyone into a hyper-realistic AI actor.
Like the one in this video.
I made a guide covering EXACTLY how to do it with Seedance 2.0:
- Midjourney portrait guide
- Human library setup
- Ref2vid Seedance workflow
RT + reply “ACTOR” and I’ll send it to you for free (must be following so I can DM)
English



