
Building media agents šØš»āš» Prev product manager @watchplayback, @squarespace, founder @dancingastro
San Francisco
Joined June 2008
- Tweets6.8K
- Following475
- Followers1.4K
- Likes28.8K
Every feature becomes a commodity in the AI era.
Competitors quickly add the latest innovations weeks apart from each other.
When you accept that dots aren't good at using Codex, then you can use them effectively.
I stopped relying on my dot exclusively to drive Codex. I've since reorganized how threads operate and I take over threads when my dot is getting stuck.
This requires more work than just letting your dot do everything but I think it's important until dots get good at Codex.
Hopefully soon!
How dot started: Codex output multiplied.
How dot is going: Codex usage bill multiplied. Codex threads broken.
Media agents can write a bespoke version of the story for you and engage you in a discussion.
Codex is one of the most important untold stories in the history of technology.
A year ago, it was a scrappy effort in a quiet corner of @OpenAI. Its cloud product hadnāt found PMF, and the team was starting over from scratch.
Less than 12 months later:
- Codex swallowed the flagship ChatGPT desktop app from the inside (it literally runs as com.openai.codex on your Mac)
- Codex and ChatGPT for Work hit 40M+ weekly users across engineering and knowledge work
- Its leader @thsottiaux was elevated to run all of OpenAIās core products, including ChatGPT, Codex, and the API
How did they pull it off?
They trained their own dedicated model line, separate from ChatGPT, with researchers and product builders sitting on the same team
They built four different products in a single year (cloud ā terminal ā IDE sidebar ā a desktop app with no code editor at all) as every model leap made a new form factor possible
They used Codex to build Codexāso a handful of people could prove a new product in weeks instead of arguing for it in meetings
I had a front-row seat to the whole arcāfrom their failed Cloud launch, to OpenAIās offices the night before GPT-5 dropped, to the day Codex took over ChatGPT.
And I spent months interviewing @gdb, @thsottiaux, @embirico, @mia_glaese, @aambrosino, and @edbayes to get inside how it all went down.
Here is the full, behind-closed-doors story of the team that remade OpenAI:
every.to/p/how-codex-happeneā¦
Weāre pushing the boundaries of how stories like this are told.
This piece is completely agent-nativeādesigned to be read alongside your agent inside ChatGPTās in-app browser:
- Every interview transcript is included in full: Click any quote and you (or your agent) can see the exact conversation it came from.
- Built for your agent to explore: Ask your agent to pull out product lessons for your team, cross-examine the transcripts, or find insights I missed when writing the piece.
Itās a story about the future of softwareābuilt to be read with an agent:
every.to/p/how-codex-happeneā¦
San Francisco is like a college campus but more studying than partying
More SF observations:
1. Seeing the word "inference" on billboards in SF still blows my mind. 99.9% of america has no idea what inference is and I wonder how many know what an agent is. Will Muse, Instinct, Dots etc will change that over the next 12 months?
2. You know who doesn't get enough credit? Manus. In March 2025 they shipped the blueprint for AI agents: every task gets its own computer in the cloud, you can watch it work, it writes a todo list and checks it off, and you walk away while it finishes. So much of what we use today runs on those ideas!
3. Your product now has to sell itself twice. First the agent has to pick it, then the human has to trust that pick enough to say yes.
4. I was talking to a guy who told me we should just destroy all the data centers. I think that sentiment is more common than people in SF realize. You can already see some of the big AI companies adjusting positioning their AI as something that helps people and gives them more time/cures for cancers etc.
5. AI is making people work 5x faster (at least), so for freelancers/agencies that charge per hour you're earning 5x less per unit of work. But your rate is the same? I think a lot of freelancers and agencies are about to have to rethink how they price.
6. Running a company now feels kinda dystopian sometimes, especially with a small team of a few humans and a lot of agents. Some days the Slack channel is mostly bots reporting to each other, and you're the only one in the room with a pulse.
7. Every product company is turning into a product studio. I see it firsthand as a co-founder of @meetLCA , which is basically a Labs as a Service company incubating new products for companies. (DM me if you want to work together in 2027).
8. Personal software is exploding. People at every company are building their own little tools for their own jobs. It's amazing for productivity and a nightmare for IT, because nobody knows what's running or who owns it.
9. Revenue per human is the new flex. Founders used to brag about headcount. Now they brag about how much they're doing with how few people.
11. More founders are using agents for customer research. Agents run the interviews, read every support ticket and summarize what people are begging for. Synthetic market research is the new thing.
12. Shipping technology that actually takes 3-6 months with unique partnerships that are hard to replicate. So, partnerships are sooo back!
13. Insane amount of young people (22 or younger) making absurds amounts of money. At least it feels that way. Never seen anything like that, even during mobile era.
14. Only 2% of the US is paying for AI products, but it feels like 110% SF is.
15. Advice for college grads used to be āfollow your passionā and now itās follow careers that are not document- driven, rules-bound and verifiable
16. Seeing the word inference on billboards in SF still blows my mind.
17. Agents paying for things feels futuristic. I think its coming, only a matter of time, but Iām wondering when it becomes mainstream. 2027?
18. Lots of talk about proactive agents being the next phase of personal agents. Right now you ask your agent to do something. In 2027, itās all going to be about noticing things (context/memory) and acting first. "Your flight got delayed, I already rebooked you."
19. The quote "what the smartest people do on the weekend is what everyone else will do during the week in 10 years." by Chris Dixon. It feels like that length of time isnt 10 years anymore, its 12 months.
20. This is the most asymmetric window I've ever seen in business.
My DMs are open. Respond to the most interesting ones.
Loved my trip to SF. Until next time. Maybe NYC next?
Thank you for everything.
I'm rooting for you.
Dots started out so strong but it's become a mess. Voice calls fail handoffs to Codex. Every minuscule task requires approval even when you ask to make rules to pre-approve various types of tasks.
This is why Iām building an agentic consumer media app.
Media made for you > doomscrolling media made for everyone.
Yes, dot is the biggest upgrade to my Codex workflow. My output has accelerated significantly and my AI psychosis has subsided. š
Working with my dot is a vastly more pleasant way to use Codex.
I spend much less time chatting because it works much longer without needing my babysitting.
I provide more in depth commands via voice calls.
I am going for more walks during the day because I can get a lot done on voice calls.
Using Dots in Codex is much better than those clunky chief of staff threads I had previously set up.
I find that I am doing most of my communication to Codex there and I'm spending less time in worker threads.
There hasn't been this much cinema in keynote presentations since Steve Jobs Apple days. Thank you @vladtenev and Robinhood. š
Robinhood Presents: Engines of Creation xitter.cf/i/broadcasts/1oKMvvPMRā¦
This is a major friction remover for developers and consumers.
The barrier is no longer technical skills. Itās imagination and taste.
Wondering how to build full experiences like this with AI agents and the Rive CLI?
Itās as simple as pointing your agent to the Rive website and telling it to install the Rive CLI. Then tell it to build something with it and use the CLI preview feature for you to test and for it to inspect and validate as it builds. No sign-in, no account required to get started.
The CLI uses our new text-based markup language, so agents can write Rive files directly. That makes Rive the best format for agents to build interactive experiences that run natively on web, mobile, consoles (Switch, PlayStation, Xbox), desktop, smart TVs, vehicles, and any custom hardware.
People have an aversion to AI-generated media because they conflate it with low human effort.
Making great AI-media still requires human expertise and creativity. The best creators will make incredible art with AI.
When people started using computers to add graphics to films or to produce music, people were initially skeptical. Over time these became viewed as normal tools for the job.
Human artists are still as essential as ever.



















