I'm working on 24 startups simultaneously.(half a million b2b users, multimillion ARR). No VC funding, employees, calls, office, managers. Each business is 100% async over chat:.> me: idea, design, UX & marketing. > comaker: coding, product & support. Why, how, what:

as a first-time startup founder, just don’t do this:. - b2c.- Quit your main job to go all in with your startup.- Expect to make profits in your first 3 years.- Look for a cofounder.- Build before you validate the idea.- raise funding from VCs.- Waste time designing your landing.

A new proposal from @CMSgov under @DrOz wants to add catheters, ostomy & trach supplies to Medicare’s competitive bidding program. This is a bad idea and will worsen outcomes for seniors & Medicare recipients. My latest in @MedPageToday explains why ⬇️

RT @johnrushx: I started building an AI Agent for SEO in 2022. The 1st version took a year to build,.then another year to iterate & reach….

9. That's it. @seobotai isn't the only agent I built. Here is another one: It works days and nights looking for new directories and backlinks on internet and then can act in real world, register on websites, submit products, etc.

8. The amount of job done by agents is insane. One human would spend days or weeks doing what the agents all together did in 2 hours. The agent isn't perfect ofc. Human in the loop improves its output significantly. We still fight with hallucination and unpredictability of LLMs.

7. When there are so many steps unsupervised by a human, even one mistake gonna break the whole thing.- there are agents who adjust the plan, if some tasks cant be done. e.g. if a given website can't be scraped. - everything runs on queues & jobs based on "eventuall-consistency".

6. AI itself isn't that useful without external tools & apis.- some agents work as bridges to the real world. Creative agents ask the bridge agents for work to be done. E.g "go to these sites & put together a list of these items. ". (just like a human would ask their assistant ).

5. The results float up the stream:.- every higher level agent can initiate new tasks and ask to improve/redo. - the anti-hallucination agents fact-check the outputs.- the internal linking agent is called by the orchestrator at the end.

4. Agents perform Deep Research using the internet and various trusted content sources. Different LLMs are used to cross-roast each other. The user can optionally moderate the process, e.g. approve/decline the headlines:

3. Once the strategy is created, the "manager" model creates 100+ tasks. - then the next level models(100s of them) create 100s of tasks for their "employees/models". - they execute tasks & report back.- the manager models analyze, give feedback and iterate until they're happy

2. Next model creates an SEO strategy.- does keyword analysis.- looks at competitors.- looks at existing articles and pages.- comes up with full knowledge and topic tree.- tests it all for potential and demand via google search console API.- goes to google search to explore more

1. The user provides a URL of the site to the agent:.- it scrapes the website.- LLM learns all the details about the biz: pricing, audience, solution, problem. - It creates a full spec and passes it on to the next model.

I started building an AI Agent for SEO in 2022. The 1st version took a year to build,.then another year to iterate & reach a near-human level. Today, @seobotai replaces my entire blog SEO team. An average article takes 2 hours, 700 prompts & 125 tasks. How it works in detail:

RT @KalshiFB: My DoorDash delivery guy during football season

Twitter brain is insane 👏. I know how to cut my expenses in half now, from $76k to $38k:. 1) Move all my hosting to Hetzner (from AWS/Azure/Google). 2) Self-host everything I can on Hetzner: Sentry, Campfire, etc). 3) Use cheaper/smaller LLM models + caching. 4) Many vendors.

I've spent $76,082.42 in August 😓. Can you help me reduce this?. Contractors: -$10,137.78.Amazon Web Services: -$4,480.12.MongoDB: -$4,251.50.Google Workspace: -$1,913.61.Google Cloud: -$2,134.74.PayPal: -$4,678.55.Exa: -$1,549.00.Cloudflare: -$350.20.OpenAI: -$15,486.83.

ListingBott is a no-brainer for almost every startup.- SaaS, AI tool, Agency, and so on. Why list on all relevant directories?.- get more eyeballs on ur product.- LLMs may pick up ur product & recommend it cuz they browse directories.- earn backlinks for domain rating & SEO.

8. There are many more agents I run internally and I'll launch them at some point. My end goal is to automate literally everything. The next launch is SocialBot (the first ai agent for social media that doesnt create ai slop). More about my work:.

7. @indexrusher. - gets you indexed by bing(helps with LLM search optimization, so that chatgpt knows you).- helps with google indexing(up to 20 pages a day).- saves you time, often drives SEO traffic up.- offers one time fee (pay once, use for ever).

6. @marsxdev is my AI Coding tool that me and my comakers used to build all these agents.

Living with Bitachon - Now available 🇮🇱✡️.Written by Avraham Chaim Meir Ben Tov, בס"ד.B’Siyata D’Shmaya – with Heaven’s help. 📖Softcover (shown here) $17.70 - available at 📚Hardcover $27.79 available on Amazon:

5. @wrapifai can build small apps (lead magnets or mini tools to drive seo traffic).

4. @tinyadz_ runs ads for me (on it's own publisher network). It creates the campaigns, targets it at the right audience, sets the budget, does A/B testing. Literally zero work from my side.