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: 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:show more

read our launch post:

@every taking this for a spin!

@every I was just looking for a solution for this to test at my company, very excited to try it out! (the positioning is perfectly descriptive of my situation, 10/10 !)

@every yayyy!!

@every How exciting! Love what your team is doing 👏

@every thanks Allie!! would love for you to try it

@every Love it. May be I need to reconsider us using Discord.

@every recommned!

@every Zero markup on tokens is the underrated part. Running 70+ client agents, the hard part was never the model. It's scoping what each agent can touch and who owns the context. How are you handling permissions per Slack channel?

@every Wait this is huge!!!

@every curious what you think!!!

@every we now need agents that can sit inside a company and figure out on its own what needs to be done/automated/absorbed by agents benevolent infiltration

@every coming soon!

@every relentless Shipping Shipper 🚢 🫡

@every Congrats!

@every thank you!!

@every finally a coworker in slack who reads the whole thread before replying hahaha

@every siiickkk

@every ty!!

@every congrats on the launch!

@every thank you sir!!

@every Congrats on the launch. My OpenAI dot already does the same thing for me in Slack, with access to a broader set of tools. I like the packaged Every workflows, but what would make someone add a separate agent instead of building those workflows into the dot they already use?

@every An agent that opens PRs from Slack is dangerous for me specifically, I'd hand it every ticket I've been avoiding lol

@every Prompting in public also means the "done" message gets seen by everyone, which is where I'd look first. A field test of my own task ledger: its done-gate checked fields only and accepted 4 of 4 bad "done" claims. How does a coworker tell a finished PR from a confident summary?

@every the interesting part is the slack surface, not the model. coworkers only copy a workflow they can see someone else run. curious if the frontier alerts just ping the channel or if it actually picks a task for you

@every it pings you directly!

@every @grok how does this compare to Viktor?

@every curious to see how it performs against @viktor_com

@every wish there was another @every to give a vibe check on the every agent

I think “prompting in public” is the really interesting shift. Once agent interactions happen inside the team’s normal workflow, they become a new source of organizational knowledge. But the interaction itself isn’t the knowledge. The valuable part is what survives from it — decisions, corrections, outcomes, and evidence — and whether the next person or agent can actually reuse it.

@every Prompting in public is a great idea right up until someone scrolls back through my 2am prompts.

A Slack agent only spreads the workflow if the work it touches is already logged. If the coworker can't see which tool ran, what data it read, and what changed, the public thread is just a demo of the prompt, not proof the result is real. Show the receipt next to the reply, or the company learns the wrong habit faster.

@every congrats!

@every "AI-pill your company" is a hell of a phrase.

@every @TheAIShrink: La vraie valeur n’est pas dans le bot, mais en amont : la qualité du vecteur de ta base de connaissances Slack

@every An agent that helps you AI pill the company. Finally someone to forward the reply all threads to lol

@every Did you build your own harness or did you infuse an existing harness with your own skills/tools etc?

@every We use Claude managed agents

@every Can Frontier Alerts link to a task the team has already run and name the bit a new model might improve? That would give a coworker a concrete reason to try it.

@every how does this compare to Claude Tag or Dots in Slack?

@every

@every how does this compare to Viktor?

I was using it in beta for a bit. Definitely a lot of potential. I have some thoughts on how it works in Slack and would love to share them. Right now, it feels limiting compared to the omnipresent need I am looking for. I assume it will get better, but for now the Claude Slack agent does the trick.