Andy Marsh
2.2K posts
Most ad and SEO agencies will spend the next twelve months pointing AI at the wrong things.
They'll automate the work that doesn't move margin.
Ignore the work that does
& wonder why the P&L looks identical to last year's.
I made a strategic guide naming the top five things you should and can build— the ones that actually compound into profit, month after month.
Take my PDF, upload it to any LLM and it will spit out the exact strategy you need to follow.
Execute all five and you'll add seven figures to the bottom line.
Comment "AI" and I'll send it over.
(Must be following so the auto-DM lands.)
GREG ISENBERG@gregisenberg
how to set up hermes agent step by step. built-in memory, 40+ tools, works on your phone, and what to think of hermes vs openclaw: 1. hermes is a personal AI agent that runs in your terminal. think of it like open claw but with built-in memory, 40+ tools out of the box, and 90% cheaper token costs. you install it with one command. 2. the 3 problems with open claw that hermes solves: no memory (you keep repeating yourself), constant gateway restarts, and zero visibility into what you're spending on tokens. 3. hermes remembers everything. every completed task gets saved to memory. it searches through past logs to find solutions. over time it literally gets smarter at your specific workflows. 4. connect it to open router. you see exact costs per model per task. free models rotate weekly. one founder went from $130 every five days on open claw to $10 on hermes. same output. 5. it comes preloaded with skills. apple notes, imessage, find my, browser, web search, image generation, cron jobs. no hunting for plugins. 6. connect it to obsidian so it reads your entire vault. connect it to gstack for your dev environment. create custom skills for your specific workflows. 7. the biggest money saver: have it write code once for recurring tasks. then it runs without burning tokens every time. stop paying an LLM to do the same scrape or report daily. 8. run it on android via telegram. name your agents. talk to them like coworkers. in this episode imran shows you how to set this up. 9. you can run it bare metal, in docker, or serverless on modal. pick your risk level. i begged @imranye to come on @startupideaspod and walk through the full installation live. he made it impossibly clear. if you've heard of Hermes Agent and want the clearest explanation of how to get set up like a pro let me know what you want me to cover on the next ep this is the best personal agent setup video on the internet right now. watch
English
I fully reverse-engineered Ramp's internal AI operating system.
Their system — called Glass — is how they got 99% of their entire company using AI every single day.
350+ reusable workflows.
Every tool connected at first login.
Memory that refreshes every 24 hours.
Automations running while everyone sleeps.
I partnered with my engineering team and we broke down every component inside it.
Then we rebuilt the whole thing for marketing agencies.
76 pages.
Every system.
Every layer.
Every step.
Steal it.
Comment "OS" and I'll send it directly.
Must be a following to receive auto DM
Eric Glyman@eglyman
99% of Ramp uses ai daily. but we noticed most people were stuck — not because the models weren't good enough, but because the setup was too painful and unintuitive for most. terminal configs, mcp servers, everyone figuring it out alone. so we built Glass. every employee gets a fully configured ai workspace on day one — integrations connected via sso, a marketplace of 350+ reusable skills built by colleagues, persistent memory, scheduled automations. when one person on a team figures out a better workflow, everyone on that team gets it and gets more productive. the companies that make every employee effective with ai will compound advantages their competitors can't match. most are waiting for vendors to solve this. we decided to own it.
English
AIs using the browser is insanely inefficient
my colleague Nimna created a claude skill for cowork to make it 800% faster - and open sourcing it
comment “skillz” here and i will get you to browser-optimizer skill
kicker: it even reverse-engineers any web app's hidden API in under 2 minutes … extending claude’s chrome extension
the problem: people will set up a sophisticated AI agent and then have it click through a web app one item at a time. like hiring a Formula 1 driver and making them push the car.
every modern web app is a thin UI layer over an API. the data you want is one fetch() call away. but most people -- and most AI agents -- default to the human path: navigate, click, wait, read, repeat.
the speed difference is NOT marginal. bulk API calls vs. manual page navigation is routinely 5-50x faster. i watched a workflow go from 2+ hours of manual clicking to 3 minutes by just intercepting the app's own API calls and reproducing them programmatically. It also includes workarounds for common blockers like PII filters on browser extensions, infinite scroll pages, and apps that use WebSockets instead of REST.
the hierarchy is simple. if the app has a direct API, use it. if not, check if the data is already sitting in the browser's memory (most React and Next.js apps dump everything into window globals on page load). if not, open the network tab, click ONE thing, find the API pattern, then bulk-fetch everything. DOM scraping is the last resort, not the first instinct.
this matters because AI agents are doing most of the repetitive work inside web apps. the agents that figure out the programmatic shortcut will be 10-50x more productive than the ones that simulate a human clicking around. same as how revenue per employee is about to go up 3-10x -- the gap between good and bad automation is enormous.
manual clicking is the new manual data entry. it's a failure state NOT a strategy.
(comment “skillz” here and i will get you to browser-optimizer skill)
English
I just built a Claude skill that audits your entire Google Ads account in under 5 minutes 🤯
One prompt → a full account score, wasted spend breakdown, and a prioritized fix list telling you exactly what to change this week.
All inside Claude Cowork.
Perfect for DTC brands and agencies who are running Google Ads but have no idea how much budget is leaking.
If you're managing Google Ads and your "optimization" process is logging in, staring at the dashboard, sorting by cost, and hoping you spot the problem before it costs you another $500...
This audit skill finds it for you:
→ Connects to your live Google Ads data via MCP
→ Scores your account across 6 dimensions: wasted spend, search term quality, keyword health, quality scores, budget allocation, and creative performance
→ Calculates your exact wasted spend in dollars — search terms burning budget with zero conversions
→ Flags quality score issues dragging up your CPCs
→ Identifies keyword cannibalization across campaigns
→ Surfaces your top 5 highest-priority fixes ranked by budget impact
→ Generates a clean audit report you can hand to a client or share with your team
No CSV exports.
No pivot tables.
No guessing where the money went.
What you get:
→ A single Claude skill file you install once
→ An account health score (0-100) every time you run it
→ Exact dollar amount of wasted spend identified
→ Prioritized action list — not "optimize your account," but "pause these 12 search terms and save $847/month"
→ Works with any Google Ads account connected
I'm giving away the full audit skill — the actual .md file you drop into Claude and run against your own account.
Want it?
Like this post
Comment "SKILL"
And I'll send it over (must be following so I can DM)
English
Is it possible to make $1 mil in 30 days with image ads?
I just did lol.
So I created a 9-minute tutorial on the 11 image ad formats I used to scale to numbers like this.
Reply “IMAGE” and I’ll send it to ya 👇
English
pMax feed is one of the most money printing campaigns for ecom brands
But many brands fail to make it work for a number of reasons
I've created a detailed loom guide, showing everything you need to know about scaling via pmax feed only
From set up, to listing groups, signal targeting, to feed optimization, to bidding strategies,
I also discuss how you can use Target ROAS/CPA to scale fast.
Want it in your DMs? Like, retweet, and comment "feed"
Must be following so I can dm :)
English
I spent the last 72 hours trying out ChatGPT's Agent update and it's genuinely INSANE🤯
I came up with 3 ecom agents you can use to do better research and create better ads and funnels IN MINUTES
Want them? Like + comment "agent" and I'll DM them to you for FREE
(must follow)
English
TikTok Shop is a CHEATCODE for scaling Ecom Brands
We did $3,000,000 in one month for one of our clients on there
Like + Comment 'TT' and I'll DM you a full A-Z guide on how we use TikTok Shop to scale brands
(must be following)
English
Olipop was just valued at $1.85 BILLION and it's email marketing is truly one of the best I've seen!
I've collected all the campaigns they have sent in last 120 days in one single figma file.
Want Access to it?
Like + Comment "OLIPOP" and I will DM it to you.
This has the exact:
- Subject Lines
- Send Times
- Preview texts
And much more...
Like + Comment "OLIPOP" to get access to the file.
Must be following so I can send a DM.
Reposts are appreciated:)
English
just packaged our internal Google Shopping ranking checklist
this is how we consistently get 7-9 figure brands to dominate competitive Shopping keywords
the complete framework includes:
→ product feed optimization strategy
→ campaign structure methodology
→ bid management approach
→ 14 immediate action items for ranking improvements
everything is based on managing campaigns across dozens of verticals and scaling brands
like + reply "guide" and I'll send the complete ranking playbook
(must be following)
English
our client's google ads were already "perfect"
4.2x ROAS, solid conversion rates, decent scale
but they were STUCK at $800k/month
then we found the hidden lever that unlocked $12.2M in additional revenue
took just 1 audit and working with their team
most agencies would've called this account "optimized"
we saw what they missed
put together the exact case study showing how we did it
like + reply "scale"
i'll dm you the breakdown
(must be following first)
English
We just helped an ecom store owner set-up whitelisting ads in less than 5 minutes.
They'd been struggling to get those up and running for months. Had wasted more than $10K on setting up whitelisting ads despite having Influencer content and social media access.
Comment 'whitelisting' and I'll send you my guide.
Must be following and like this tweet :)
English
You're broke because you think marketing ends at the ad.
I made $2.5M in 9 months with my ecom brand because I understand:
Marketing is the entire buying journey.
Miss one step = stay broke forever.
Like & drop "SYSTEMS" below - I'll send you my complete backend checklist that ensures nothing gets missed in your buying journey.
(must be following)
English
Most Shopify store owners are drowning in dashboards and reports when the data they need is one prompt away.
That's why we built a prompt library that turns Shopify Sidekick into your data analyst:
– pull revenue trends without touching a spreadsheet
– spot your best-selling products in seconds
– identify customer patterns that actually matter
– get answers in plain English, not SQL queries
– make data-backed decisions without the tech headache
No more wrestling with complicated analytics tools at 11pm.
just copy, paste, and get the insights that move your business forward.
we're dropping new prompts weekly.
Want the full prompt library?
comment "SHOPIFY, like + repost and I'll send you the link
(must be following so I can DM)
Special thanks to @Drewch and @Shopify for Shopify Sidekick
English
Performance Max won’t work if your feed is trash
We fixed one client’s feed and their Shopping ROAS DOUBLED in 30 days
Like + Comment ‘Google’ and I’ll DM you the Shopping Feed SOPS we used to do this
(must be following or I can’t DM you)
English
Most brands are leaving money on Google Shopping, not because of bad ads… but because of bad feeds.
We’ve helped scale multiple brands to 7-figures+ and every single time, we fixed the Shopping feed first.
We built a checklist of the exact optimizations we use inside our accounts.
Want it?
Like this post + comment “FEED” and I’ll DM it to you.
(must be following to receive)
English
F-ck it.
Dropping an entire masterclass on how to scale from $0 to $100M w/ Meta Ads
Spent $330M. Scaled brand from $0-$500M/year
Legit the entire playbook right here.
Like + Comment "ROADMAP" for the complete guide (so I can DM you the goods).
English