tfw your ChatGPT app is controlling your Claude app is controlling your ChatGPT app
@danshipper
-
Building the Every agent with Claude Managed Agents
By
–
we couldn't have built the @every agent without Claude Managed Agents
— Dan Shipper (@danshipper) 6 octobre 2026
extremely fun to get to sit down and chat about it: https://t.co/RAsiCZwlZdwe couldn't have built the @every agent without Claude Managed Agents extremely fun to get to sit down and chat about it:
-
Every launches agentic AI coworker for Slack
By
–
BREAKING:
— Dan Shipper (@danshipper) 6 octobre 2026
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,… pic.twitter.com/sQOMhe4gzQBREAKING: 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, -
Ask AI to evaluate you and suggest workflow upgrades
By
–
if you want to get better at using AI, just ask it to evaluate you and regularly suggest upgrades to your workflow
-
Guide to orchestrating agents with Codex
By
–
use codex to go from prompting to orchestrating agents with this step-by-step guide by @ArielleShipper
-
User describes dot as persistent AI agent interface
By
–
dot has become my primary interface to AI over the last few weeks. my dot's name is boo. he's cute! in a year, i bet i'll still be interacting in this way with @ChatGPT
—e.g. as an always-on persistent agent—but boo will have disappeared. it reminds me a lot of early OpenClaw -
Reflection on AI models doing work and human roles
By
–
i def understand and agree with that im just reflecting the other end of the equation. the models are doing more of what humans used to do, and are humans doing more new work on top of that when i prompt with gpt-6 and it goes off and works for a few hours im not doing nothing.
-
AI models improving in autonomous high-fidelity task execution
By
–
that is definitely not my experience! the models can do more end to end, but the most important thing is whether it does what i want it to do (ideally even beyond what i originally asked) doing that in a high-fidelity, autonomous way is the dimension they're improving along,
-
Guide to getting started with open models
By
–
we published a sick guide to getting started with open models on @every
: -
OpenAI announces GPT-5.6 Sol with restricted US access
By
–
BREAKING: OpenAI announced GPT-5.6 Sol! As of today, by U.S. government directive, access is limited to only ~20 pre-approved companies and @every is not on the list. This appears to be a temporary situation while the government races to figure out a long-term policy for