Atlassian Community

I have created a Custom ROVO agent . Purpose of the agent is if tidal job is an input means response should return all the informatica components if exist and suc/TDD documents confluence link . scenario1: If TDD link doesn’t exist for a legacy job it should check all jira stories does anything have this tidal job…

Because Rovo no longer generates dashboard reports using a smart prompt—it takes too long and fails to produce results for a dashboard with more than 50 cases. It used to work fine, and I had barely even used it to avoid burning through tokens, yet it still doesn't work the way it used to.

Hello everyone, I’ve created a Rovo Agent in Atlassian Studio and integrated it into our Slack channel. While the native Jira and Confluence skills are working perfectly, I’m having trouble with the GitHub MCP (Model Context Protocol) integration. The Goal: I want the Rovo Agent to be able to retrieve logs and status…

Hi Community, I've been learning about both native Rovo connectors and the new MCP integration, and I'm trying to understand where each one fits best. If both can give Rovo access to external information, when would you choose an MCP server instead of using a native connector? Are there specific use cases where MCP…

Hi Community, I was thinking about a scenario where an organization has several custom Rovo Agents, and more than one of them could potentially answer the same question. How does Rovo decide which Agent should respond? Does it automatically route the request based on the prompt or the Agent's description, or is there some…

Does the Data Center license need to be active for the Jira/Confluence Data Center Rovo connectors to work? For companies who don't want to migrate their legacy data to Cloud, this could be an ideal setup: While the DC instance remains available in Read Only mode (no active DC license), the Data is accessible via Rovo.…

Hello Team, We are looking for guidance on implementing a human handoff workflow for our Rovo agent in Slack. We have developed an FAQ Rovo agent for our Slack channel. Currently, the agent responds to every message posted within a thread. Our desired behavior is as follows: * The Rovo agent provides the initial response…

I'm not able to connect Rovo in Slack with my atlassian acocunt. The Rovo in Slack asks me to Sign up. When I click on the button it opens atlassian login page but with incorrect email address being prefilled. The login page offers "or continue with" option to sign in using SSO account. So I click on "Microsoft" and…

Atlassian MCP Integration authentication failing on Claude code with the following error. Existing OAuth client information is required when exchanging an authorization code Claude Code v2.1.212

Hi, I am finding it impossible to add connectors to ROVO in a new organisation. I have done the process before in another org, so I'm confident it's not a process issue. The Org has Paid Access, has only company domain users, BUT it was originally created with a personal email which is the only thing I can think of. Rovo…

I am trying to limit the content, for this Rovo agent, to a single folder in a Sharepoint site. The connector shows synced with a couple thousand objects indexed. The connector only has one site allowed. When I try to filter the agent's Sharepoint knowledge source, nothing populates. I tried searching by the source's…

Hi, Since yesterday, I can not load the Spaces information in the Jira automation Publish a confluence page step. How can I fix this? Regards, Hung

I created a prompt to reuse at the end of each sprint to calculate epic movement, but the results always come back inaccurate or Rovo dies silently and never generates an error. I had tried to create an agent but that failed. What can I do to better improve the results from either my prompt or even get my agent working?

Hi Team, I would like to understand whether ROVO is capable of building automated Reports. As a Scrum Master I would like to see what is the "Predictability of Story Completion" of my scrum teams. So when I give it the instructions as "Consider stories from last 5 Sprints and generate me a Report" can ROVO do? or is there…

Am I trying to overwork Rovo?!? :) I have an agent I created to help with root cause analysis over a time period (i.e. prior month or quarter). I'm still in the process of testing and refining my prompt and output, and I'm more often than not getting "input too large". Weird thing is, I can set it aside and come back in a…

Hi My account and workspace appear to be deactivated on the 23rd July. Due to personal reasons I have not been able to log into my account Is there anyway to speak to someone about restoring the data. A love an AI chat bot but they are not assisting and it just appears to link to pages that are not helpful. Is there an…

Hi, I am unable to add enable toggle for the API Token for Atlassian, my admin tried opening that page and every time it says, something went wrong. For my application, I wanted to use ROVO MCP Server and I am facing issues to access this now, initially it worked but I don't know it's not working now, and I want to raise a…

Hi Community! This is my very first post here in the Atlassian Community. I’ve been a long-time lurker, but I finally decided to jump in because my team is currently tackling a rather tough nut to crack, and I’d love to get your insights. We’ve been trying to roll out Atlassian Rovo, and honestly, it’s been quite a…

* Whether Mercury’s ROVO/Jira instance supports a native executable action for: * create release notes in Jira * save release notes * attache/save the generated note under Related Work for a release * In that ticket, included the following: * the current agent skill screenshot * the release-notes UI screenshots from your…

To reproduce: * Go to a Confluence page or Jira ticket. * Click "Ask Rovo" in top-right of header. * Select a Rovo agent (any agent). * Just above the chat textbox there should be a "Context" line showing the Confluence page you were looking at when you clicked "Ask Rovo". * Instead of typing something, click one of the…

Hi everyone, I’m experiencing a critical change in behavior with a custom Rovo Agent created within Atlassian Studio. I’m trying to figure out if this is a platform-wide restriction or a recent change. The Situation: I have an automation flow for a Company-managed project where a Rovo Agent is responsible for managing the…

Atlassian has decided after a year of automatic logins on my app on laptop that all of a sudden I have to log in. Only catch is that they want to send me a code to my email, and of course it does not send the code, after multiple times trying. 

Sometimes Rovo has enough information to generate an answer—but not enough to generate a reliable one. Should it explicitly say: "I don't have enough trustworthy organizational knowledge to answer." instead of producing a potentially incorrect response?

Instead of answering questions, should Rovo proactively identify: undocumented processes,isolated teams,missing documentation,duplicated knowledge,outdated ownership.Could AI eventually become a knowledge architect instead of just a search assistant?

Rovo usually provides a single response. Would it improve trust if it also explained: * Why alternative documents weren't selected? * Why certain Jira issues were ignored? * Why one Confluence page was considered more authoritative? Could this reduce hallucinations and increase confidence?

Today's AI assistants are designed to answer questions. But should enterprise AI also question assumptions? For example: "This requirement conflicts with an existing Jira Epic." or "This architecture contradicts your documentation." Would a "critical thinking mode" make Rovo more valuable, or would it become intrusive?

Rovo remembers context within a conversation, but every new interaction still requires significant prompting. Should Rovo gradually learn a user's preferred writing style, Jira workflows, documentation patterns, and decision-making preferences while remaining privacy-safe? Where should the boundary between personalization…

Today, most Rovo Agents execute tasks independently. Would enterprise automation benefit if specialized agents (Planning, Development, QA, Security, Documentation) could collaborate, critique each other's outputs, and reach a consensus before returning a result? Would this architecture improve reliability, or simply…

Current Rovo Agents primarily rely on prompts and retrieved context during execution. As enterprise workflows become longer and more complex, should Rovo introduce a persistent memory architecture that stores verified organizational knowledge independently of each conversation? How should Atlassian balance: Context…

Feature Request: Rovo AI should track and report its own health metrics When Rovo fails to complete an action — like creating a Jira ticket — the only feedback loop is the user noticing, retrying, and eventually giving up or contacting support. There's no mechanism for the AI itself to recognize patterns in its own…