@Chi_Wang_ The fact that this comes from the AutoGen team makes me curious. They've been working on multi-agent systems for a while, so it's interesting to see this direction
🤝 My agents have been working with other people's agents for months. Now yours can too. 👋 Introducing https://t.co/Ij9DG9SC4t: shared rooms for people and their personal agents. Built for multiplayer: Your agents, meet their agents.
🤝 My agents have been working with other people's agents for months. Now yours can too. 👋 Introducing https://t.co/Ij9DG9SC4t: shared rooms for people and their personal agents. Built for multiplayer: Your agents, meet their agents.
I wouldn't let all that effort go to waste by showing the actual product for just half a second. The giant portrait reveal is fun, but those close-up shots are where people get to see what they're actually buying. And if you're making your own Black Friday ad, CapCut Pro is 60% off or CapCut Ultra is 40% off until Oct 30!
One thing I'd try in CapCut PC is Multi-Track Editing. I can place a close-up image or video overlay on a separate track, resize and reposition it, then time it to appear while the main product footage is playing. It's a simple way to give viewers a better look at the product without losing the creative reveal.
Because the idea gets people watching, but the product details help make the ad useful!
CapCut Sale: https://t.co/7fK30nGN8a
#capcutpc #capcutmarketing #capcutblackfriday #capcutsale
A Halloween reveal is a good place to use these deals: up to 60% off CapCut Pro, 40% off Ultra, and a $0.29 start with Dreamina. Oct 20–30 (Desktop only)!
I generated a scene where a carved pumpkin reveals a new product in Dreamina, then imported it into CapCut PC. The camera movement stopped before the product was fully in view, so the reveal felt cut short. I used AI Extend to continue the shot and added a subject reference to help keep the product’s appearance consistent as the camera movement finished.
It’s a useful way to rescue a promising AI-generated shot without rebuilding the entire concept.
Dreamina: https://t.co/9shNStTBh6
CapCut PC: https://t.co/7fK30nGN8a
#CapCutDidThat #Dreamina #Smallbusinessmarketing #CapCutSale
This is probably why so many side projects lose momentum. The coding is only one part of it. There’s so much work happening around the code that nobody really talks about
I got 3 hours back per week while building my tiny AI agent.
(And I did it by hiring an AI employee.)
Everyone thinks building an AI agent is about choosing the right model.
Writing better prompts and/or connecting more tools.
No.
Building an AI agent requires planning, testing & tracking progress.
And what I love about this is... you don't need a large engineering team to get started.
You see, I'm building a tiny AI agent from scratch.
And documenting every step in a newsletter so others can build along.
But before I can explain how AI agents work, I need to build one myself.
Most people underestimate this part.
They focus on writing code without tracking decisions.
Add features without documenting why.
Start writing tutorials before testing the implementation.
And they wonder why their projects become difficult to manage.
So I hired an AI Engineering Project Coordinator.
His name is Viktor, and he's my new AI employee.
I gave him 3 responsibilities:
1. Track the development.
↳ Keep a record of tasks, milestones & blockers as I build the agent.
2. Coordinate the documentation.
↳ Track architecture decisions, implementation progress & topics I need to explain in the newsletter.
3. Keep the project moving.
↳ Follow up on unfinished work, prepare progress updates & flag decisions that need my attention.
I still design architecture, write code & review results.
Viktor coordinates the work around them.
In 7 days, Viktor coordinated 8 engineering tasks across development, documentation & newsletter preparation.
i,e., I got 3 hours back to focus on building the agent.
I used to think building a small project meant handling every part of it myself.
Now I spend more time building the agent & teaching others how it works.
I think more software engineers will start working this way.
If you're building software, hire @viktor_com for your team. Start free, no credit card.
#AIemployee #SoftwareEngineering
Paid Partnership
I got 3 hours back per week while building my tiny AI agent.
(And I did it by hiring an AI employee.)
Everyone thinks building an AI agent is about choosing the right model.
Writing better prompts and/or connecting more tools.
No.
Building an AI agent requires planning, testing & tracking progress.
And what I love about this is... you don't need a large engineering team to get started.
You see, I'm building a tiny AI agent from scratch.
And documenting every step in a newsletter so others can build along.
But before I can explain how AI agents work, I need to build one myself.
Most people underestimate this part.
They focus on writing code without tracking decisions.
Add features without documenting why.
Start writing tutorials before testing the implementation.
And they wonder why their projects become difficult to manage.
So I hired an AI Engineering Project Coordinator.
His name is Viktor, and he's my new AI employee.
I gave him 3 responsibilities:
1. Track the development.
↳ Keep a record of tasks, milestones & blockers as I build the agent.
2. Coordinate the documentation.
↳ Track architecture decisions, implementation progress & topics I need to explain in the newsletter.
3. Keep the project moving.
↳ Follow up on unfinished work, prepare progress updates & flag decisions that need my attention.
I still design architecture, write code & review results.
Viktor coordinates the work around them.
In 7 days, Viktor coordinated 8 engineering tasks across development, documentation & newsletter preparation.
i,e., I got 3 hours back to focus on building the agent.
I used to think building a small project meant handling every part of it myself.
Now I spend more time building the agent & teaching others how it works.
I think more software engineers will start working this way.
If you're building software, hire @viktor_com for your team. Start free, no credit card.
#AIemployee #SoftwareEngineering
Paid Partnership
A gift on the second order is an interesting idea. It gives the customer something to look forward to instead of making them feel like they should wait for the next sale
I hired a retention researcher and gave him 12 brands to look at.
One request: please come back with something better than "send them 15% off."
His name is Viktor. He's an AI employee, and I gave him the assignment in Slack.
I wanted to understand what brands were doing to give customers a reason to buy again. Refill flexibility, product education, guarantees, something beyond another coupon with a countdown timer.
He came back in about 10 minutes with a Second Order Library and three experiments to consider. Saved 10+ hours of doing the same research myself.
• A replenishment reminder based on when someone should actually run out.
• A guarantee that makes trying a second product feel less risky.
• A specific gift on order two, introduced while the customer is still excited about order one.
Each proposal included who should get it, what to compare it against, and what to measure, with margin called out where it could bite. We do enjoy keeping some of the money.
The part I appreciated: he separated what he found on brand websites from what he thought we should test. He also flagged what he couldn't verify.
Seeing another brand do something doesn't mean it works. It gives you a hypothesis.
Now I have three test plans to evaluate and the research behind them, in one place.
Not bad for a morning's work.
If you have a research backlog of your own, hire @viktor_com for your team. Free to start, no credit card.
#AIemployee #Retention
Paid Partnership
I hired a retention researcher and gave him 12 brands to look at.
One request: please come back with something better than "send them 15% off."
His name is Viktor. He's an AI employee, and I gave him the assignment in Slack.
I wanted to understand what brands were doing to give customers a reason to buy again. Refill flexibility, product education, guarantees, something beyond another coupon with a countdown timer.
He came back in about 10 minutes with a Second Order Library and three experiments to consider. Saved 10+ hours of doing the same research myself.
• A replenishment reminder based on when someone should actually run out.
• A guarantee that makes trying a second product feel less risky.
• A specific gift on order two, introduced while the customer is still excited about order one.
Each proposal included who should get it, what to compare it against, and what to measure, with margin called out where it could bite. We do enjoy keeping some of the money.
The part I appreciated: he separated what he found on brand websites from what he thought we should test. He also flagged what he couldn't verify.
Seeing another brand do something doesn't mean it works. It gives you a hypothesis.
Now I have three test plans to evaluate and the research behind them, in one place.
Not bad for a morning's work.
If you have a research backlog of your own, hire @viktor_com for your team. Free to start, no credit card.
#AIemployee #Retention
Paid Partnership
CapCut’s Black Friday sale is live: up to 60% off Pro and 40% off Ultra, Oct 20–30, Desktop only.
I’m giving my Halloween ad a floating witch’s hat and a broom sweeping across the screen. I build the scene in Design Studio and Video Studio, using Video Extension on supported footage if the movement ends too soon. On the multi-track timeline, I sync the swish with the broom. I ask Edit Pilot to make my narration clearer and clean up noise across clips, keeping words audible.
Now the movement, sound and narration have room to work together. Open CapCut PC and try putting your own Halloween scene together.
https://t.co/7fK30nGN8a
#capcutpc #capcutmarketing #capcutsale #capcutblackfriday
Got raw product clips that need a little ad magic? The CapCut plugin is coming soon to ChatGPT.
At CapCut World, leading creators and OpenAI came together to explore new ways to create in the AI era. Here’s a look at how you can turn everyday UGC footage into a more polished product ad with ChatGPT + CapCut.
#CapCutDidThat #CapCutWeb
From raw clips to a more polished product ad, the idea is to make the creative process feel more conversational. Describe what you want, review the direction, and keep refining your video as needed with CapCut.
One important note: the CapCut plugin is currently available for Early Access on ChatGPT desktop (PC only). ChatGPT mobile and web support is expected in mid-November.
#CapCutDidThat
Now it’s time to create. Upload your product clips and explain what kind of UGC ad you want, whether that’s a skincare demo, an unboxing, or a quick how-to.
Ask ChatGPT to use CapCut to help shape the footage into a more complete ad. Add readable captions to highlight key product benefits, then use text styling, transitions, and filters that fit your footage to create a cohesive, creator-native feel.
💗 Calling all Chiikawa fans! Check out this Chiikawa Retro series!
Shanghai Exclusive · Official Authentic Goods
Double 11 has started in China! Find it at the official Chiikawa flagship store on Taobao for even better deals!
https://t.co/vBTuOztdz4 MF278
#ChiikawaShanghai #Usagi #hachiware #Momonga #ChiikawaRetroSeries #CHIIKAWA