Hi @karrisaarinen, please add a full screen chat feature for agent sessions in @linear. 🙏
Fix deployed only a few minutes after I raised the issue. 👏
Replicas team is special
Hi @connortbot 👋
My cursor agents within replicas can’t access global mcp. Could you have a look ?🙏
Well I guess that I did not want to wait...
Replying to @karrisaarinen @linear
3 mains agents : planner, executor and reviewer. I need them to have different model, skills and mcp access.
Probably as well custom agents for specific use cases, for example one marketing agent with access to specific tools and skills.
Highlights from "Your GTM belongs in git": @Kaarolus, @Cole_Dambra, @JohnKutay and Johnathon Kidd on why go-to-market is becoming software.
Hey @MatthiasBaccino 👋, TR pour les personnes morales c’est dans les cartons pour 2026? 🙏
A model provider allowing bringing another model provider subscription. Hopefully this is the beginning of a more open AI for all
This + an automatic order of horizontal tabs based on agent status?
Why horizontal tabs?
Vertical is navigation. Organizational. Hierarchical. A tree. It's "history". You don't need it on screen all the time.
Horizontal is the working set. The threads that are live. Always visible. Give it icons, colors, status. Context at a glance.
In apps like ChatGPT, Claude Code or T3 Code, horizontal space is expensive. Tabs at the top let you tuck away the sidebar and leave more room for the right panel: preview, browser, code view.
And you still see what's running, what's done, what needs your input.
Alexis Girard retweeted
Great night on thursday for "your GTM belongs in git". Thanks @thegtmengineer, @JohnKutay, @Kaarolus, @Cole_Dambra and johnathon.
More of these soon
Latest models from Anthropic and OpenAI are now available in @cargo_hq
Tomorrow, 6pm in SF.
Your GTM belongs in git.
Last chance to RSVP 👇
luma.com/6dy4fsfk
Ah!
Replying to @cognition
On FrontierCode 1.1, our benchmark for real-world engineering tasks, Grok 4.7 scores slightly below Grok 4.6.
While strong on many hard tasks, it tends to over scope on others, leading it to trail behind Grok 4.6 in the aggregate.
Read more: devin.ai/blog/grok-4-7













