🔥 take: your AI isn’t dumb. You’re starving it of context.
A smaller model that knows your codebase, Jira, and past decisions can beat a frontier model flying blind.
Better context fewer re-prompts, fewer tokens, better answers.
What does your AI keep making you repeat?
That’s what changed for me: I stopped pasting context by hand. Rovo now pulls it from my repo + Jira before the agent starts.
The result: fewer re-prompts, less token waste, and better answers.
The model didn’t change. What it knew did.
@PetrSavchenkooo Thats the thing human brain captures images and pictures and this on confluence remix helps a lot especially when summing up something or sending it to a wider group
@sona_j19 Agreed, the thing is real, with AI based PR, the number of lines of code added can be extremely high, but setting a systematic process for Reviewing and Raising PRs definitely help
@wabzqem Desktop apps provides great abstraction compared to CLI, and on top of that, Desktop app seems like much easier to goto compare to CLI(instinctively)
5M+ daily agent actions. 1M+ monthly active users.
We launched the Atlassian Rovo MCP Server to give agents like @Claude, @ChatGPTapp, and @Cursor direct access to team context.
Here’s what we’ve learned about the future of AI at work since... 🧵
🚀 Working in @OpenAI 's ChatGPT? A user asks ChatGPT to review a @Atlassian 's Jira epic, and it finds the gaps, creates the missing tasks, and links everything back together.
💨 No prompting gymnastics. Just an agent doing real work.
🚀 That’s happening at scale right now. The @Atlassian Rovo MCP Server is seeing 5M+ tool calls every working day. Nearly a third are writes.
🔑 Agents aren’t reading your work system. They’re participating in it.
Check out some stats:
💡 44% of users aren’t on software teams. PMs and C-level execs are using MCP just as intensely as engineers, because their entire job is connecting dots across teams.
🏹 More than 50% of monthly active users are enterprise customers. Enterprises almost never move first. They’re moving here because the bigger the org, the more a connected context layer is worth.
🔥 The flywheel is already spinning. Every agent write enriches the Teamwork Graph. A richer graph makes the agent smarter. We’re seeing 44% more accurate answers with 48% fewer tokens.
And its not just one - agents like @claudeai Code by @AnthropicAI , @ChatGPTapp by @OpenAI , @cursor_ai , @figma , and more are actually being used in enterprise work.
Jira just entered the @SlackHQ chat.
Turn any conversation into a tracked work item the moment it happens. Just mention @𝙹𝚒𝚛𝚊 to create, update, and assign work items without leaving the conversation.
Chandrayaan-3 Mission:
'India🇮🇳,
I reached my destination
and you too!'
: Chandrayaan-3
Chandrayaan-3 has successfully
soft-landed on the moon 🌖!.
Congratulations, India🇮🇳!
#Chandrayaan_3#Ch3
सोनू सूद इस आपदाकाल मे अलग-अलग राज्य प्रवासियों को उनके गृह प्रदेश भेजने के लिए दिन-रात कार्यरत है.. @SonuSood सोनू आपदाकाल में किए गए कार्यों के लिए देश में याद किए जाएँगे..@Umeshnni top work brother man 🇮🇳✅🙏
The Election Dates are announced today. And as a common citizen I do wish for a good, neat and clean Election Contest. Please don't do politics on Election Dates.
#StandWithEC#ElectionCommission#ElectionWar2019
@TheViralFever This is a web Series I would love to see on the top of IMDb Charts even if not this has topped the list in My heart.Hats Off @TheViralFever for such a lovely and Heart Touching #YehMeriFamily