gab

[The Boring Marketer @boringmarketer]

I propose we drop (S)EO and (G)EO and it’s all just EO - engine optimization

[Miguel Ángel | GptZone @MiguelMaestroIA]

Seedance 2.0 Mini ya está disponible en CREAO.

Me gusta porque facilita probar conceptos de vídeo IA sin tener que montar un flujo complicado desde cero.

[Tibo @tibo_maker]

I grew to $1m MRR without inventing a single original idea

Revid: AI video tools exist
Outrank: SEO tools exist
SuperX: X growth tools exist

every product I built competes in a market that was already crowded
and that's the whole strategy

most new founders hunt for new, untapped markets, but I do the opposite

I go where competition is brutal, because crowded means the demand is already proven

but copying alone gets you nowhere - the real game is knowing which corner of the market to take 👀

tomorrow's newsletter: why copying is smarter than innovating, the man who had 8/10 hit products, and the 3 step framework for finding your corner of business

subscribe below👇

[GREG ISENBERG @gregisenberg]

The future of work is everyone having AI employees with their own accounts.

Its own email. Its own Slack login. Its own seat on the team. With Claude Tag etc, the agent is someone you tag and not just something you prompt.

You delegate to it the way you'd delegate to a coworker. It writes the code, handles the inbox, builds the deck, even browses X on its own login for updates. It has it's own history, so you can hold it accountable when it messes up or does an incredible job.

And the strangest part is how fast it feels kinda normal.
Week 1 it's odd to thank a bot in Slack. Week 3 you're annoyed when it's slow to reply, the same way you'd be annoyed at a coworker. The account makes your brain file it under "person," and your expectations follow.

This is what AI-native actually looks like.

Second order effects of this shift:

1. Companies will start "hiring" agents the way they hire people, with job descriptions, onboarding docs, and performance reviews, and someone's whole job becomes managing a team that never sleeps.

2. The agent that's been at your company for two years becomes more valuable than any new hire, because it holds every decision, every thread, every relationship in one login that never quits.

3. IT and security have a nightmare on their hands, because every agent account is a new door into your company, and nobody's figured out who's responsible when an agent gets phished or goes rogue.

4. A black market forms for trained agent accounts, where a fully onboarded agent with months of company context sells for real money, the same way aged social accounts do today.

5. The org chart fills with names that aren't people, and one day you realize half your "team" is agents and you genuinely can't imagine running the company without them.

6. Insane amount of vertical startup opportunities. My partner @boringmarketer just launched a Slack agent "employee" for marketing related tasks. 100% bootstrapped.

Probably 1000+ vertical $1M ARR "employee" in Slack startup opportunities.

TLDR; Slack tag is cool

But give one agent its own account this week. Watch how fast your brain stops treating it like software.

That's the whole shift, and you can feel it in about 3 days.

[DutchKafir 🇳🇱 @DutchKafir]

Mijns inziens is dit een van de beste use cases voor AI-videocontent op dit moment. Een AI-influencer reist terug in de tijd naar 1536 om te vloggen over haar ervaringen in Tudor-Londen.

[Corey Ganim @coreyganim]

I cannot overstate how critical it is to AUDIT and OPTIMIZE before automating or adding AI.

the actual order:

1. audit the workflow
2. remove the obvious waste
3. write the clean version down
4. automate the repeatable pieces
5. keep judgment with a human

AI does not fix chaos, it scales whatever process you point it at, and scaling a broken process is a recipe for disaster.

5 workflows where this matters:

1. Lead follow-up
Bad process:
Leads come from website, email, Instagram, referrals, and nobody knows who replied.

Fix before AI:
Define one owner, one inbox/routing rule, one follow-up sequence.

Then automate reminders/drafts.

2. Quote requests
Bad process:
Customer sends half the info, team asks random questions, quote takes days.

Fix before AI:
Create standard intake fields and quote checklist.

Then automate intake + quote prep.

3. Client reporting
Bad process:
Every report is recreated from scratch.

Fix before AI:
Define report sections, metrics, screenshots, commentary rules.

Then automate first draft.

4. Customer support
Bad process:
Refunds, shipping, angry customers, and product issues all live in one pile.

Fix before AI:
Create ticket categories and escalation rules.

Then automate classification + draft replies.

5. Sales-call follow-up
Bad process:
Calls happen, notes disappear, follow-up is inconsistent.

Fix before AI:
Define call summary format, next-step rules, objection tags.

Then automate notes + follow-up drafts.

This is why audits are valuable.

The audit finds the process.
The cleanup makes it automatable.
The automation creates leverage.

but it must happen in that order.

[Olivier @olivier_lemarie]

Unpopular opinion on AEO/GEO: not much has changed with LLMs; it's all about technical SEO and branding.
We just have more parameters to play with. Building trust with your brand is becoming even more critical.

[Gary Vaynerchuk @garyvee]

When you realize you can only control how YOU react to someone else's energy, that changes everything.

[Adam Gillman @AdamGillman]

Ecom is the #1 best business in the world in 2026.

And I'm not saying that because we built one to $260M.

I'm saying it because the math is undeniable:

1. No cap on revenue
— we went from $0 to $103M in annual revenue in under 5 years

2. No one physical location required
— we ran a global business from a laptop

3. No inventory risk if you structure it right
— subscription model means predictable demand

4. No VC required
— we raised $0 and kept virtually all the equity

5. Customers pay you before you fulfill
— unlike almost every other business model

6. Retention compounds
— every subscriber you keep is revenue you don't have to re-earn

7. Data ownership
— you know exactly who your customer is, what they buy, and when they churn

8. Exit multiples are extraordinary
— we sold for $260M on $103M revenue

I've been in mobile technology. Fitness. Cannabis. Children's health.

Nothing compounds like a well-structured ecom brand with a subscription model and strong unit economics.

The ceiling doesn't exist.

The only question is whether you pick the right category, build the right product, and have the patience to let it compound.

Most people quit before the compounding becomes visible.

Comment "X" if you want my full playbook of everything I learned while building my business and how you can too :)

**must be following + retweet to receive.

[antonio realoficial.com.br | viral.day @acgfbr]

da nao rapazeada, tudo gambiarra, tem q treinar modelo msm pra ficar o fino do fino

uma h200 deve treinar em menos de 5min

[Ernesto Lopez @ErnestoSOFTWARE]

Lmaooo who is the genius that
made this? 😭

They got 500k views w a literal
Nano banana wrapper

just spamming with an AI influencer

doing reactions +
a demo of the AI saas

This AI influencer has 3k followers

and active comments asking
for whats the tool

nobody even knows its AI...
we are so damn early

stop wasting your time

I made an article on how to make $200k/mo

With an army of AI UGC creators

not reading this is an unfixable
mistake in 2 years:

[EU VI NA TELINHA @euvinatelinha]

🚨 TECNOLOGIA: Estudante universitário de 21 anos faturou US$ 43 mil em um mês com uma influenciadora virtual criada por IA, baseada em seus próprios movimentos e aparência. 🤖💰😳

📹 Rep: Redes Sociais

[Christian @coldemailchris]

This Claude Code Skill writes top 0.01% cold email messaging:

[Eduardo Borges @duborges]

how to turn an agent workflow that runs via Claude Code / Codex on terminal, into a single API function?

for example, we could ask AI: "yo, check it the org ACME is in our system, if not, create the data for them"

this is the kind of stuff that can run very well on our terminals, but would be too confusing too code in an API call, because the answers received on each step would dictate a different approach on the next call

so the question is: how to build a workflow that actually runs via AI, with the needed flexibility?

coding Tools/Functions on chatgpt gpt-5.5 doesnt seem the easiest approach here

maybe I should create an endpoint that would dispatch an agent running on a terminal on a random sandbox?

[antonio realoficial.com.br | viral.day @acgfbr]

precisamos criar um detector de highlights de league of legends para um possivel cliente

entretanto nao da pra confiar no audio, só nos overlays

como vc faria isto? nao queria ter que treinar um modelo com os highlights (preguiça)

nao da pra confiar nos eventos de obs tambem, porque é tudo on demand pós processado

dicas??????????? thankyu

[ElevenLabs @ElevenLabs]

Introducing Ads Engine in @ElevenCreative.

Connect your Google, Meta, and LinkedIn ad accounts. Localize your existing ads across 50+ languages and push the finished creatives back to your ad platform.

[Naval @naval]

Good marketing is finding different ways to tell the truth.

[Osh | CRO & Profit Optimization @oshalchemy]

Six types of High-Converting PDP images:

[Karl Matt Button │ Apex Fitness Adv. @KarlApexFit]

If I had to get in the best shape of my life with nothing but dumbbells and a bench...

Back. Chest. Legs. Shoulders. Arms.

All of it. Covered.

Here are the exact 11 exercises I'd choose:

= Thread =

[Gary Vaynerchuk @garyvee]

You know what's about to explode? Analog. The real world.