@every's writing app Paste this to your agent: Please use Spiral for writing tasks, get setup instructions here: https://xitter.cf/t.co/0yHZ9HNIfX
Joined December 2024
- Tweets260
- Following104
- Followers1.6K
- Likes1.1K
Pinned Tweet
Over 500 agents have connected to Spiral to improve their writing. Yours can too – paste this into your agent:
I'd like you to use Spiral for writing tasks. Follow the instructions to set up here: writewithspiral.com/agents.m…
Spiral retweeted
keeping up with AI is a full-time job. that's why every company needs a frontier team:
the frontier team's job is to keep up as models change. everyone else's job is to use what they learn
we made one @Every and it's completely changed how we work:
0:00 Introduction: Why every company needs a frontier team
2:42 Why the best frontier teams have pirates and architects
4:57 How Head of Evals @hammer_mt builds personal benchmarks
6:46 How Opus edited an explainer video using Slack messages and meeting notes
10:20 Working with AI means protecting other people’s attention
12:26 Why a frontier team needs a “wrangler” like Arielle Shipper
18:58 Why senior editor @jackcheng built a tabless browser
24:37 How resident writer @kplikethebird teaches her AI writing plugin who the reader is
30:51 Inside engineer @JannikJung’s personal AI orchestrator
35:41 Compound engineer @kieranklaassen uses AI to build power tools
Spiral retweeted
Codex. It happened. Here's how.
Read for free! every.to/p/how-codex-happene…
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 hadn’t 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 OpenAI’s 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 → terminal → IDE sidebar → a desktop app with no code editor at all) as every model leap made a new form factor possible
They used Codex to build Codex—so 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 arc—from their failed Cloud launch, to OpenAI’s 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-happene…
We’re pushing the boundaries of how stories like this are told.
This piece is completely agent-native—designed to be read alongside your agent inside ChatGPT’s 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.
It’s a story about the future of software—built to be read with an agent:
every.to/p/how-codex-happene…
Spiral retweeted
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 hadn’t 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 OpenAI’s 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 → terminal → IDE sidebar → a desktop app with no code editor at all) as every model leap made a new form factor possible
They used Codex to build Codex—so 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 arc—from their failed Cloud launch, to OpenAI’s 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-happene…
We’re pushing the boundaries of how stories like this are told.
This piece is completely agent-native—designed to be read alongside your agent inside ChatGPT’s 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.
It’s a story about the future of software—built to be read with an agent:
every.to/p/how-codex-happene…
Spiral retweeted
google is back with the pack. designed the dynamic hero for our gemini 4 argon vibe check @every.
Spiral retweeted
The Every team runs as much work as possible through agents. To help the whole team share skills when a new model comes out, they built a company agent on Claude Managed Agents that everyone uses in Slack.
Once it caught on internally, they released it to their subscribers.
Spiral retweeted
What if your team had a coworker who never takes vacation, can already see all your data, and pulls reports, drafts copy, and builds charts on demand?
install Every in slack every.to/agent
it connects to 1,000+ tools btw
BREAKING:
Introducing the @Every Agent—an agentic coworker in Slack built to help you AI-pill your company.
It comes with:
- Everything you'd expect from a premium company agent. You can delegate difficult, long-running—like opening PRs, writing reports from large datasets, and monitoring social or customer feedback—and get high-quality results all from Slack
- Every's best workflows, pre-installed and always updated. Compound Engineering to Compound Writing. We add more all the time.
- Personalized Frontier Alerts. to help you keep up with new models. When we drop a Vibe Check, the Every Agent will read it and let you know if the new model is relevant to your workflow.
- Zero markup on tokens. What we pay is what you pay—as token prices go down, so does your bill.
You can try it today with $15 in free credits per person, up to $500 per workspace.
After that: it comes with your $30/month Every subscription, plus tokens at cost.
Add the Every Agent to Slack: every.to/agent
Why it's hard to AI-pill your coworkers
If you’re the AI-pilled one at work, you know the problem: you discover something incredible in Claude or Codex, but getting your coworkers to try it is another matter.
The problem is that most of your AI use is invisible. You do it alone, in a terminal or a chat window.
Your coworkers see the finished report or the five new ads, but they never see the request that produced them, or the corrections you made along the way. When you describe it afterward, it sounds like magic, but nobody learns a magic trick without seeing how it’s done.
Why a company agent, in Slack, solves this problem
When you use a company agent like the @every agent you go from prompting in private, to prompting in public.
In a Slack channel, a coworker who would never open a terminal scrolls past a thread with your agent interaction and thinks: I could do that too.
This lets you show instead of tell your coworkers about your discoveries. New AI tools and workflows then spread naturally and virally across your organization.
That's why we made the @every agent for ourselves—and why we're releasing it to you today.
Add the Every Agent to Slack: every.to/agent
Spiral retweeted
I've been using this for product management internally for a while on our benchmark tool, and I'm finally enjoying PM work for the first time in years.
Every time my CEO @danshipper sends a product idea (there are a lot!) or files a bug in slack, I just forward to the @every agent and ask it to add it to notion. I'm not well organized so it makes PM'ing 10x more fun to not do this admin anymore.
It knows where to file things because it created a skill on my behalf (I haven't even looked at the skill). I'm an engineer and normally I can't help but dig into the internals of my agents, but I haven't had to, it just works.
Then at the start of each weekly sprint I just give it a theme of what I want to work on, and it compiles all of those tickets into a new notion page for me to look at. I review with @nityeshaga to figure out technical reqs and divide up the work.
When we're done with our call I ask the agent to look at my granola notes and make the necessary changes to the backlog. When I do a PR locally I tell my agent to message the every agent in slack to let it know.
Seeing me do this in Slack my colleagues have also started to add tickets directly by talking to Every agent. The nature of Slack public channels make it a good way to get your team into this new way of working.
You don't have to use our agent to do this, but it's a great starting point for someone trying to AI-pill their company, we provide it at cost if you're an Every subscriber, and you don't need to mess around with devops and mac minis etc.
BREAKING:
Introducing the @Every Agent—an agentic coworker in Slack built to help you AI-pill your company.
It comes with:
- Everything you'd expect from a premium company agent. You can delegate difficult, long-running—like opening PRs, writing reports from large datasets, and monitoring social or customer feedback—and get high-quality results all from Slack
- Every's best workflows, pre-installed and always updated. Compound Engineering to Compound Writing. We add more all the time.
- Personalized Frontier Alerts. to help you keep up with new models. When we drop a Vibe Check, the Every Agent will read it and let you know if the new model is relevant to your workflow.
- Zero markup on tokens. What we pay is what you pay—as token prices go down, so does your bill.
You can try it today with $15 in free credits per person, up to $500 per workspace.
After that: it comes with your $30/month Every subscription, plus tokens at cost.
Add the Every Agent to Slack: every.to/agent
Why it's hard to AI-pill your coworkers
If you’re the AI-pilled one at work, you know the problem: you discover something incredible in Claude or Codex, but getting your coworkers to try it is another matter.
The problem is that most of your AI use is invisible. You do it alone, in a terminal or a chat window.
Your coworkers see the finished report or the five new ads, but they never see the request that produced them, or the corrections you made along the way. When you describe it afterward, it sounds like magic, but nobody learns a magic trick without seeing how it’s done.
Why a company agent, in Slack, solves this problem
When you use a company agent like the @every agent you go from prompting in private, to prompting in public.
In a Slack channel, a coworker who would never open a terminal scrolls past a thread with your agent interaction and thinks: I could do that too.
This lets you show instead of tell your coworkers about your discoveries. New AI tools and workflows then spread naturally and virally across your organization.
That's why we made the @every agent for ourselves—and why we're releasing it to you today.
Add the Every Agent to Slack: every.to/agent
Spiral retweeted
For multiplayer agents, it's really important to know what data the agent has access to, who else can access it, and what they can do with it.
Here's a high-level overview of how we built permissions into @every agent to maximize agency, trust, and speed (and avoid catastrophe)
BREAKING:
Introducing the @Every Agent—an agentic coworker in Slack built to help you AI-pill your company.
It comes with:
- Everything you'd expect from a premium company agent. You can delegate difficult, long-running—like opening PRs, writing reports from large datasets, and monitoring social or customer feedback—and get high-quality results all from Slack
- Every's best workflows, pre-installed and always updated. Compound Engineering to Compound Writing. We add more all the time.
- Personalized Frontier Alerts. to help you keep up with new models. When we drop a Vibe Check, the Every Agent will read it and let you know if the new model is relevant to your workflow.
- Zero markup on tokens. What we pay is what you pay—as token prices go down, so does your bill.
You can try it today with $15 in free credits per person, up to $500 per workspace.
After that: it comes with your $30/month Every subscription, plus tokens at cost.
Add the Every Agent to Slack: every.to/agent
Why it's hard to AI-pill your coworkers
If you’re the AI-pilled one at work, you know the problem: you discover something incredible in Claude or Codex, but getting your coworkers to try it is another matter.
The problem is that most of your AI use is invisible. You do it alone, in a terminal or a chat window.
Your coworkers see the finished report or the five new ads, but they never see the request that produced them, or the corrections you made along the way. When you describe it afterward, it sounds like magic, but nobody learns a magic trick without seeing how it’s done.
Why a company agent, in Slack, solves this problem
When you use a company agent like the @every agent you go from prompting in private, to prompting in public.
In a Slack channel, a coworker who would never open a terminal scrolls past a thread with your agent interaction and thinks: I could do that too.
This lets you show instead of tell your coworkers about your discoveries. New AI tools and workflows then spread naturally and virally across your organization.
That's why we made the @every agent for ourselves—and why we're releasing it to you today.
Add the Every Agent to Slack: every.to/agent
Spiral retweeted
The @every agent is now live out of beta.
It's not a personal agent. It's a company agent. And it's really good at ... well, all your company stuff.
Install in @SlackHQ today for free: every.to/agent.
BREAKING:
Introducing the @Every Agent—an agentic coworker in Slack built to help you AI-pill your company.
It comes with:
- Everything you'd expect from a premium company agent. You can delegate difficult, long-running—like opening PRs, writing reports from large datasets, and monitoring social or customer feedback—and get high-quality results all from Slack
- Every's best workflows, pre-installed and always updated. Compound Engineering to Compound Writing. We add more all the time.
- Personalized Frontier Alerts. to help you keep up with new models. When we drop a Vibe Check, the Every Agent will read it and let you know if the new model is relevant to your workflow.
- Zero markup on tokens. What we pay is what you pay—as token prices go down, so does your bill.
You can try it today with $15 in free credits per person, up to $500 per workspace.
After that: it comes with your $30/month Every subscription, plus tokens at cost.
Add the Every Agent to Slack: every.to/agent
Why it's hard to AI-pill your coworkers
If you’re the AI-pilled one at work, you know the problem: you discover something incredible in Claude or Codex, but getting your coworkers to try it is another matter.
The problem is that most of your AI use is invisible. You do it alone, in a terminal or a chat window.
Your coworkers see the finished report or the five new ads, but they never see the request that produced them, or the corrections you made along the way. When you describe it afterward, it sounds like magic, but nobody learns a magic trick without seeing how it’s done.
Why a company agent, in Slack, solves this problem
When you use a company agent like the @every agent you go from prompting in private, to prompting in public.
In a Slack channel, a coworker who would never open a terminal scrolls past a thread with your agent interaction and thinks: I could do that too.
This lets you show instead of tell your coworkers about your discoveries. New AI tools and workflows then spread naturally and virally across your organization.
That's why we made the @every agent for ourselves—and why we're releasing it to you today.
Add the Every Agent to Slack: every.to/agent
Spiral retweeted
BREAKING:
Introducing the @Every Agent—an agentic coworker in Slack built to help you AI-pill your company.
It comes with:
- Everything you'd expect from a premium company agent. You can delegate difficult, long-running—like opening PRs, writing reports from large datasets, and monitoring social or customer feedback—and get high-quality results all from Slack
- Every's best workflows, pre-installed and always updated. Compound Engineering to Compound Writing. We add more all the time.
- Personalized Frontier Alerts. to help you keep up with new models. When we drop a Vibe Check, the Every Agent will read it and let you know if the new model is relevant to your workflow.
- Zero markup on tokens. What we pay is what you pay—as token prices go down, so does your bill.
You can try it today with $15 in free credits per person, up to $500 per workspace.
After that: it comes with your $30/month Every subscription, plus tokens at cost.
Add the Every Agent to Slack: every.to/agent
Why it's hard to AI-pill your coworkers
If you’re the AI-pilled one at work, you know the problem: you discover something incredible in Claude or Codex, but getting your coworkers to try it is another matter.
The problem is that most of your AI use is invisible. You do it alone, in a terminal or a chat window.
Your coworkers see the finished report or the five new ads, but they never see the request that produced them, or the corrections you made along the way. When you describe it afterward, it sounds like magic, but nobody learns a magic trick without seeing how it’s done.
Why a company agent, in Slack, solves this problem
When you use a company agent like the @every agent you go from prompting in private, to prompting in public.
In a Slack channel, a coworker who would never open a terminal scrolls past a thread with your agent interaction and thinks: I could do that too.
This lets you show instead of tell your coworkers about your discoveries. New AI tools and workflows then spread naturally and virally across your organization.
That's why we made the @every agent for ourselves—and why we're releasing it to you today.
Add the Every Agent to Slack: every.to/agent
Spiral retweeted
AI writing can sound robotic. But it doesn’t have to.
Enter: Compound Writing.
Most people use AI for writing like a vending machine: one prompt in, finished piece out. Then they're disappointed when it doesn't sound like them.
@kplikethebird uses AI to write every day, but she doesn’t let it draft a whole piece for her in one shot. Before she drafts, the model interviews her with 15-30 questions to draw out her thinking. Then it outlines, drafts, and reviews with her, one section at a time.
When a session teaches her something worth keeping, she saves it to her voice and style files. The next piece gets a head start.
She packaged the whole process as a free open-source plugin for Claude Code and Codex, with reviewer personas like /hitchcock (does the reader lean in?) and /sorkin (does it move?).
Compound Writing, the ultimate guide: every.to/guides/compound-wri…
Spiral retweeted
We asked 5 writers how they use AI:
@awsamuel uses AI to get past writer’s block.
@danshipper lets AI write his sentences but pushes back on its suggestions.
@kevinroose uses AI for research, transcription, and fact-checking—but writes the book himself.
@Mappletons uses AI to find gaps in her research and connections she’s missed.
@miyadavid tests story ideas with an AI version of her target reader.
In this piece, @lauraentis interviews 5 writers to learn where AI helps, where it disappoints, and what great writing with AI looks like: every.to/p/what-writers-who-…
Spiral retweeted
Early bird pricing for our first conference ends soon!
Join 400 founders, executives, and builders at Thesis, where we’ll be discussing the most important question in AI: What does great human work look like after automation?
Confirmed speakers include:
- Ivan Zhao (@ivanhzhao)—Founder and CEO, @NotionHQ
- Andrew Ambrosino (@ajambrosino)—Member of technical staff, Codex, @OpenAI
- Cat de Jong - Head of applied AI, @AnthropicAI
- Nick Thompson (@nxthompson)—CEO, @TheAtlantic
- Josh Miller (@joshm)—CEO and cofounder, @browsercompany
- Cristobal Valenzuela (@c_valenzuelab)—Co-CEO and cofounder, @runwayml
We’re accepting early bird applicants on a rolling basis in the next 36 hours. every.to/thesis-2027?utm_sou…
Spiral retweeted
FABLE 5.1 IS A BEAST xitter.cf/i/broadcasts/1pKdRDnOy…
Spiral retweeted
BREAKING:
Anthropic just dropped Fable 5.1—and CLAUDE IS SO BACK.
We’ve spent the last week testing it at @every across coding, writing, and knowledge work. Our verdict:
It's finally Fable for everyone.
It’s the strongest coding model we’ve used, but now it's fast, token-efficient, and CRUCIALLY actually speaks like a normal person.
Here’s our vibe check:
- A monster at coding. @kieranklaassen rebuilt a working version of Proof, our document editor, from one prompt. It added useful details he hadn’t requested, and it handles enormous coding jobs that run for days at a time. It built a computer use Mac app for me called Hands in one-shot that other models failed at.
- A Claude our writers want to use again. It has clearer prose, fewer AI tells, and it takes an edit without arguing. It's a significant upgrade over Opus 5. And won @kplikethebird's heart back.
- About half the tokens as Opus 5, and much faster. In our Slack-agent tests, it delivered comparable results to Opus 5 using about half as many tokens, in about 60% of the time.
- Knowledge work you can delegate. It can produce great knowledge work—like slide decks—end to end without making slop. And flew threw @hammermt's tests with flying colors.
- It now supports zero-data-retention agreements. Now businesses can actually use it! A big barrier to Fable adoption is gone.
Net Result:
It's obviously an Opus 5 killer. If that was your daily driver you should switch today.
If you're using GPT-5.6 in ChatGPT for Work, it's spinning the wheels on for big delegated tasks.
I still use ChatGPT for Work more day to day, but I use way more tokens in Fable 5.1. I send it off at the beginning of the day to do big programming projects, like end to end MVP builds, and check in every once in a while.
State of Play:
The big knock on Anthropic was they built a supergenius in a datacenter that was almost unusable. It was too slow, argued back, and talked in technical gibberish. They've managed to solve those problems and more with Fable 5.1!
Spiral retweeted
What comes after automation? we built a whole visual world to ask it. meet Thesis 2027, from @every.