🇺🇸 🇦🇷 Product Engineer
United States
Joined May 2010
- Tweets9.3K
- Following3.7K
- Followers1.4K
- Likes8K
Ok maybe now it will make sense to have AI answer the phone...
We believe voice is the most natural way to interact with intelligence, so we created Dessa, the most authentic full-duplex speech model ever built. Talking with it feels like talking with a person…full of emotion, nuance, pauses, and a natural cadence.
block.xyz/dessa
I have a lot of projects on @Replit, and checking on them meant opening each one, one by one.
So I built an agent that manages all of them from one place. Here’s what I found 👇
✅It spots projects that have gone idle, so I can clean up and keep my account lean
✅One prompt gets me stats across several projects at once (“visitor stats for these 3”)
✅It compares projects side by side, so I can see which ones are actually working
Built entirely on Replit. Video below 🎥
@amasad @pirroh @samuel_spitz, @raymmar, @franciscocrz, @nickco @MannyBernabe @zhenthebuilder @lhchavez and @HL3rd_ , would love your take.
Suggestion for the @Replit @ReplitSupport team! 💡
We Latinos LOVE WhatsApp, especially in LATAM, but also here in the US. Many of us even run our businesses through it.
How about a native WhatsApp integration in Replit so we can build apps that send and receive WhatsApp messages?
This would be HUGE for the Latino market! 🚀
I think Replit has now built 3 or 4 things I originally suggested… after telling me they couldn’t be done 😅
I’m starting to think “no” just means “not yet.”
Keep shipping, @Replit. I’ll keep the feedback coming 🫡 @amasad
Hey Ricky!
Each project on Replit is its own isolated environment right now, so there isn't a way to share code or modules across projects directly. The closest option is multi-artifacts within a single project, where multiple outputs like a web app, mobile app, and slides can share the same backend, database, and file storage.
For moving code between projects, you can export as a ZIP and import into another project, though that creates a copy rather than a live link.
Hope this helps!
Quick feedback for my @ReplitSupport friends 😀
New projects keep trying to reuse my existing third-party accounts (like Resend).
I'd love credentials scoped to each project, with the option to reuse existing ones.
Different projects, different accounts. That's all for today 🫡
Ricky Funk retweeted
🚨 side project alert 🚨
Announcing Muse Gadgets, an open source ESP32 firmware and Linux sdk so that you can make hardware devices that work with Muse.
Grab an API token from gadgets.muse.ai and point your favorite coding agent at the github repo to build your own peripherals for Muse.
It’s funny how you can inspire someone and have absolutely no idea you did it.
@JJEnglert, that happened to me watching your video.
At 16:17, when you showed the onboarding experience at @tenex_labs, something clicked.
A couple of years ago, I was trying to do a version of what Tenex is doing today. I was using @Replit to build AI tools for companies, bringing AI into their workflows to save time, reduce costs, and automate repetitive work.
Replit wasn’t quite there yet.
Now it is.
Today I run a mentorship community where we use GoHighLevel as the main platform, while I’ve also built a separate platform in Replit with custom tools for our members.
After watching your video, I made a decision:
I’m getting rid of GoHighLevel.
I’m rebuilding the entire member experience myself in Replit.
Onboarding.
Courses.
Live sessions.
Resources.
Custom tools.
Individual action plans.
Everything.
One video. One idea. Completely changed the direction of something I’ve been building.
You never know who’s watching or what your work might inspire them to create.
Thanks, brother. 👊
POV: your boss asks you to build something by next week. You've never built software before. At least not something other people have to use.
This video walks you through it, start to finish.
Here's the path:
- The stack: Claude Code builds it, GitHub backs it up, Vercel puts it live
- Build vs. buy: only build the thing that makes you better than everyone else
- Write the plan first. It's the GPS for your agent.
- Map every person who will use it, and what each one needs
- Design it in Claude Design before a single line of code
- Build the thing
By the end, you've shipped a real, working app.
Know someone who wants to build their own software? Send this to them.
Timestamps:
0:00 The ask
0:35 The stack
3:03 Build vs. buy
4:10 Why you plan first
6:00 Set up your project and GitHub
7:22 Build the plan with Claude
9:20 Feeling overwhelmed? That's normal
10:03 Map your users
11:19 Design it in Claude Design
13:21 Review and tweak the design
15:18 The finished app
This might be the nuttiest video I've made to date. Yay or nay? Let me know.
This is exactly what I recommended @Replit a few months ago. Make it easy so the masses can build games on your platform.
We just open-sourced an entire game studio.
Introducing GameDev OS by Scenario.
It gives your coding agent 9 specialists and 64 skills.
📁 GameDev OS
┃
┣ 📁 2D Artist
┃ ┣ 📁 Concept Sketches
┃ ┗ 📁 Sprites and VFX
┃
┣ 📁 3D Artist
┃ ┣ 📁 Image to 3D
┃ ┗ 📁 Rigging and Retargeting
┃
┣ 📁 Environment Artist
┃ ┣ 📁 Textures and Skyboxes
┃ ┗ 📁 Walkable 3D Worlds
┃
┣ 📁 Art Director
┃ ┣ 📁 One Character, Every Shot
┃ ┗ 📁 Quality Check Before It Ships
┃
┣ 📁 Sound Designer
┃ ┣ 📁 Music and Score
┃ ┗ 📁 Gunfire and SFX
┃
┣ 📁 Video Producer
┃ ┣ 📁 Cinematic Trailers
┃ ┗ 📁 Captions for Every Platform
┃
┣ 📁 Marketing Artist
┃ ┣ 📁 Store Art for Every Platform
┃ ┗ 📁 Ads From One Shot
┃
┣ 📁 Technical Director
┃ ┣ 📁 Workflows Imported From ComfyUI
┃ ┗ 📁 Custom Pipelines
┃
┗ 📁 Cost Manager
┣ 📁 Model Bake-Offs With Cost
┗ 📁 Team Budgets
Each specialist knows the major models for its job: Seedance, GPT, Meshy, Rodin and more.
And they work together.
2D Artist sketches the gun → 3D Artist builds it → Environment Artist builds the world around it → Sound Designer adds the gunfire → Video Producer cuts the trailer.
One agent. An entire game studio behind it.
Free to install. Runs on your agent.
Comment “OS” and I’ll send you the entire skill library.
I once sold a product 3 months after having the idea.
Not because the code was brilliant. Because I refused to write any until someone asked for it.
The idea was a marketplace connecting U.S. companies with talent in Latin America. Here's how it went:
Week 1: No product. Just a "coming soon" landing page and a few targeted ads in Latin America. Hundreds of people signed up.
Week 2: I called them. What jobs do you want? What worries you? What would make you trust a platform like this? Those conversations wrote the product for me.
Week 3: Only then did I write the PRD.
Month 1: A small team and I shipped the MVP on no-code. Not pretty. Real.
Month 2: 8,000+ people onboarded.
Month 3: A U.S. company reached out to acquire it. We sold.
I've been an engineer, a CTO, a CEO and now a product manager, and the lesson hasn't changed:
→ Demand before code. A signup page is the cheapest prototype you'll ever build.
→ Talk to users before you write the spec. The spec should be a summary of what they told you.
→ Ship the smallest real thing. Polish is a reward for traction, not a prerequisite.
The hardest part of product isn't building. It's having the discipline not to build until you've earned the right to.
What's the fastest you've ever validated (or killed) an idea?
#ProductManagement #Startups #ProductDiscovery #BuildInPublic
Last night we taught a room full of cleaning business owners how to build their first website with @Replit.
Live. One prompt.
One of them had been paying $500/mo for a site she didn't own. Another was quoted $9,200 for her own domain.
3 minutes later, they all had one.
Please @replit If Plan Mode is already active, it should automatically spin up a background task instead of asking me to switch to Build.
I already told Replit I want to plan first. The product should handle the transition for me, not make me manage the workflow.
Two calls I've made about @Replit:
1. Replit needs to let you brainstorm, not just build. Then came the free tier where you can actually think out loud.
2. Replit needs to own go to market, not just the app. Then came GTM partnerships.
Here's the third: Replit needs the next level of automations.
Connectors handed the agent the keys to your whole stack. But nothing fires unless you're sitting in the chat watching it. That's a helper, not an employee.
Give me triggers. Give me schedules. Give me runs that happen while I sleep.
Come on Replit. Let's do it.
I've been on both sides of the wall that Replit is tearing down.
The technical side first: I started in networks and infrastructure, moved into iOS engineering, and ended up as Director of Mobile Development at MediPortal, then CTO at Route, where I built three software products for commercial cleaning companies and set the technology strategy. That work got me promoted to CEO, where I raised $2M pre-seed. I studied Computer Programming at NYU, and I used to write code every day.
The other side is that I also ran a cleaning company with 250+ clients and sold it. Payroll, routes, quality inspections, collections, hiring. I knew exactly what software should exist. Building it was still slow enough that most of it never got built.
That's the gap Replit closes, and I'm not speaking theoretically. Everything I ship now runs on it. Cleanse (usecleanse.com) is an AI business advisor for cleaning company owners, bilingual English and Spanish, built after 50+ owner interviews. Talo (freetalo.com) is the operations platform for those same owners. liderconimpulso.com serves a Spanish-speaking community of cleaning entrepreneurs. rickyfunk.com is my portfolio. Four production products, prompt and tool-call architecture, model selection, integrations, deploys, all of it.
What excites me most about companies like @replit specifically is that it's the job I already did as a CTO and as an owner, just with better tools and a bigger surface. Treating Finance or Recruiting as its own startup with its own customers and metrics isn't a framing exercise to me. I've closed a month, chased receivables, and lost a contract on a bad walkthrough. I want to sit with a department lead, argue about what's actually broken, and ship the fix that week.
I'm humbled about what @amasad created, and of course the team behind it, @pirroh @agi2asi @seijadvice @samuel_spitz @nickco @HL3rd_ and many more!
Ricky Funk retweeted
⚽️ Desde las 10, la Reserva que dirige Hugo Ibarra visitará a Vélez con:
👉 Ramiro García; Pedro Velurtas, Renzo Giampaoli, Gabriel Aranda, Valentín Barco; Equi Fernández, Alan Varela, Gabriel Vega; Vicente Taborda; Exequiel Zeballos y Gonzalo Morales.
I called it months ago…
