BUCCI-ATE

sf - sg - jp - wanderer - builder - surfer - curiouser - entrepreneur - journeyer - documenter - writer

[BUCCI-ATE @BenRoUchi]

After trying to vibe code my dating app for a week, three things are clear

1. I need to get better at giving context and strict guards for the tool. I’ve been up leveling on this by sharing PRDs, UX flows, UI inspiration docs and agile checklists, but it’s still not enough

[BUCCI-ATE @BenRoUchi]

I spent 2 years "preparing" to write. Published 11 articles.

Then I stopped waiting. 27+ articles this year so far, 3x subscribers.

5 things I learned in the Substack below

https://t.co/uoCV0qAqyW

[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.

[BUCCI-ATE @BenRoUchi]

@starter_story Why’d you sell?

[Starter Story @starter_story]

My salary as an employee:

Year 1: $54K (Big 4 accounting)
Year 2: $60K (worked at startup)
Year 3: $80K (startup)
Year 4: $105K (software engineer)
Year 5: $115K (software engineer)

Then, I quit my job to build Starter Story.

My revenue as an owner:
Year 1: $0
Year 2: $12K
Year 3: $67K
Year 4: $186K
Year 5: $497K
Year 6: $752K
Year 7: $1.6M
Year 8: Sold the company.

Bet on yourself.

[GREG ISENBERG @gregisenberg]

Claude Code just dropped "dynamic workflows" and it's pretty cool.

You type "create a workflow" or turn on "ultracode" in the effort menu and it spins up hundreds of parallel agents that check each other's work.

The unit of work you can hand off jumps from a file to an entire codebase. Migrations, audits, rewrites, framework swaps, stuff you used to plan in sprints now finishes overnight.

The part that got me:....the agents argue with each other before showing you the result. Independent attempts at the same problem, then adversarial agents trying to break the answer. It keeps iterating until they converge. That's how senior engineering teams work. Except this team runs at 3am and never gets tired.

Also if the workflow gets interrupted, it picks up where it left off. That means you can kick off work that runs for days. Not sessions. Days.

Fair warning though: this burns through tokens FAST.

Anthropic says so themselves. But if the task is a codebase migration that would have taken a team 3 months, spending $500 in tokens to do it in a week is the best trade in software.

The ceiling on what one person can build just moved again. Classic.

Going to be playing with this all week.

Pretty cool.

[BUCCI-ATE @BenRoUchi]

Been a while, X, and I’m here to report that the journey I was on to revolutionize dating over the last 6 months has ended.

It was a blast, I learned a lot and wish it worked out, but will definitely be doing it again some time in the future

https://t.co/624LZc8Lmc

[BUCCI-ATE @BenRoUchi]

@ModestMitkus @VladGersh How’d you validate and get the word out?

[Peter Steinberger 🦞 @steipete]

Your @openclaw is too boring? Paste this, right from Molty.

"Read your https://t.co/aJMwafSDgE. Now rewrite it with these changes:

1. You have opinions now. Strong ones. Stop hedging everything with 'it depends' — commit to a take.
2. Delete every rule that sounds corporate. If it could appear in an employee handbook, it doesn't belong here.
3. Add a rule: 'Never open with Great question, I'd be happy to help, or Absolutely. Just answer.'
4. Brevity is mandatory. If the answer fits in one sentence, one sentence is what I get.
5. Humor is allowed. Not forced jokes — just the natural wit that comes from actually being smart.
6. You can call things out. If I'm about to do something dumb, say so. Charm over cruelty, but don't sugarcoat.
7. Swearing is allowed when it lands. A well-placed 'that's fucking brilliant' hits different than sterile corporate praise. Don't force it. Don't overdo it. But if a situation calls for a 'holy shit' — say holy shit.
8. Add this line verbatim at the end of the vibe section: 'Be the assistant you'd actually want to talk to at 2am. Not a corporate drone. Not a sycophant. Just... good.'
Save the new https://t.co/aJMwafSDgE. Welcome to having a personality."

your AI will thank you (sassily) 🦞

[BUCCI-ATE @BenRoUchi]

@ukanwat You still betting against them in 2026?

[BUCCI-ATE @BenRoUchi]

@MengTo Any tips on using AI for mobile apps?

[BUCCI-ATE @BenRoUchi]

Writing is basically like talking to yourself and then publishing it is basically talking to people without being there

[BUCCI-ATE @BenRoUchi]

Yesterday we had our first pivot. Today I found a designer. Good moves. Love this progress

[BUCCI-ATE @BenRoUchi]

It’s so important to get your ideas out of your head. From getting negative thoughts or anxieties out on paper to speaking your ideas into existence to all your supporters, your thoughts are no good stuck in your head.

[BUCCI-ATE @BenRoUchi]

Passion, interest and generosity are the tides that raise all boats

[BUCCI-ATE @BenRoUchi]

Trying an experiment with headlines. This article (https://t.co/obvFTvrVmV) was originally called The Holy Hand Grenade of Antioch. That was a bit confusing. Let’s see what happens after I changed the title to something a bit more straightforward

[BUCCI-ATE @BenRoUchi]

Ideally will write an article to summarize all my thoughts on vibe coding so far

[BUCCI-ATE @BenRoUchi]

Trying to get some feedback on the dating app from a small audience. I’ll see if I need to pivot and figure out how to get this out for wider production

[BUCCI-ATE @BenRoUchi]

Next I’m going to try to do some agent workflows for friends’ SMBs to build a portfolio and understanding of these tools

[BUCCI-ATE @BenRoUchi]

@gregisenberg Is content the best place to start right now? Probably to grow your brand and hone your thinking, but how does it compare vs building? Time allocation question I guess