AGASTYA SHARMA Specialist

Discussions

    • How does Rovo handle conflicting or incomplete information?

      Hi everyone, One thing I've been wondering about is how Rovo deals with situations where the available information isn't perfect. For example, if different Confluence pages contain conflicting information, or if the documentation is incomplete, what does Rovo do? Does it try to identify the most reliable source, mention…

    • At what point do custom fields become a performance or maintenance problem?

      Hello everyone, I've seen Jira instances ranging from fewer than 100 custom fields to several thousand. I understand that excessive custom fields can affect administration and potentially impact indexing and search performance, but I'm curious about practical experience. Have you reached a point where custom fields became…

    • Could AI eventually create technical debt within Confluence knowledge bases?

      Software accumulates technical debt over time. Could enterprise documentation accumulate a similar form of AI Knowledge Debt, where repeated AI-generated summaries, duplicated explanations, and recursive content gradually reduce clarity and trustworthiness? If so, should Confluence introduce native metrics to detect and…

    • Is it better to create multiple JSM projects or a single project with multiple request types for ent

      Hello everyone, I'm designing a Jira Service Management instance for a growing organization with multiple departments (IT, HR, Finance, Facilities, etc.). Some recommend creating a separate JSM project for each department, while others suggest using a single project with multiple request types, queues, and permission…

    • Does Confluence need a native model for measuring knowledge entropy rather than simply tracking stal

      Most organizations identify outdated documentation based on the last modified date. However, documentation can become less trustworthy even when it is frequently edited due to contradictions, duplicated information, fragmented ownership, and inconsistent terminology. Should Confluence move beyond "stale page detection" and…

    • When would you choose MCP over native Rovo connectors?

      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…

    • How does Rovo choose between multiple Agents?

      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…

    • Should Rovo refuse to answer when organizational knowledge quality is too low?

      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?

    • Could Rovo detect organizational knowledge gaps before people notice them?

      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?

    • Should Rovo explain why it didn't choose other answers?

      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?

    • Should Rovo challenge users instead of always trying to help them?

      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?

    • Should Rovo remember how I work instead of only responding to prompts?

      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…

    • Should Rovo evolve toward collaborative multi-agent orchestration instead of isolated AI agents?

      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…

    • Should Rovo Agents support persistent memory independent of the LLM context window?

      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…

    • The Biggest Myth About the Atlassian Community (That Almost Stopped Me From Contributing)

      When I joined the Atlassian Community, I spent weeks just reading posts. Every time I wanted to ask a question or write an answer, I had the same thought: "There are so many experts here. What if I don't know enough?" So I stayed silent. Looking back, that was probably the biggest mistake I made. The truth is, the…

    • How does Rovo decide which documents are the most relevant?

      Hi everyone, I've been reading about Rovo's search capabilities, and something I'm curious about is how it decides which Jira issues or Confluence pages to include when answering a question. Is it mainly based on semantic similarity, keyword matching, or a mix of both? And if there are dozens of relevant documents, how…

    • How Does Rovo Decide Whether to Use Retrieved Knowledge vs. the LLM's Own Knowledge?

      Hi Community, I've been exploring Rovo recently, and one question keeps coming to mind. Let's say I ask Rovo something that could be answered in a few different ways: Using information from our Jira or Confluence content. Using the LLM's general knowledge. Or by combining both. How does Rovo decide which source to rely on?…

    • I Almost Stayed Silent.

      And honestly... That would've been the biggest mistake of my career. When I first joined the Atlassian Community, I felt like I didn't belong. I wasn't a Community Champion. I wasn't an Atlassian employee. I wasn't someone with 15 years of experience. I was just an engineering student trying to learn. So I did what many…

    • How does Rovo deal with large amounts of retrieved content?

      Hi everyone, I had a question while exploring how Rovo retrieves information. Let's say I ask a question that matches a lot of content across Jira issues and Confluence pages. Since every LLM has a context limit, I'm wondering what happens when there's simply too much information to include in a single response. Does Rovo…

    • Should Rovo expose reasoning confidence instead of only providing answers?

      Rovo currently returns responses without clearly communicating its confidence level. Would it be valuable if every response included confidence signals such as: Retrieval confidenceEvidence completenessKnowledge freshnessReasoning confidenceMissing information score Could confidence calibration improve enterprise trust and…

    • Where should the boundary exist between AI governance and human governance in enterprise Confluence?

      As Rovo becomes capable of generating content, restructuring documentation, and recommending edits, an important governance question emerges. Which responsibilities should remain exclusively human? For example: approving architectural decisions,resolving conflicting documentation,defining canonical knowledge,or validating…

    • How should organizations measure knowledge trustworthiness when using Rovo-generated content?

      As more teams use Rovo to generate and summarize Confluence content, how can organizations ensure the information remains accurate and trustworthy? Should Confluence introduce metrics like a Knowledge Trust Score based on content freshness, page ownership, AI confidence, and verification status? How are enterprise teams…

    • If Trello Could Read Your Mind... What Would You Want It to Do First?

      Imagine the next version of Trello is powered by AI that truly understands how you work. You can give it only ONE superpower. Would you choose for it to: Automatically prioritize your tasks?Predict overdue work before it happens?Build your daily plan?Organize messy boards?Generate Butler automations?Something completely…

    • Has AI Changed What "Customer Success" Actually Means?

      Traditional Customer Success measures adoption, engagement, and renewals. With Rovo embedded across Jira, Confluence, and Trello, should success instead be measured by the quality of decisions AI enables? If AI becomes part of every workflow, should Customer Success optimize for business outcomes rather than product…

    • If You Could Rebuild Jira Service Management From Scratch… What Would You Keep, What Would You Remov

      Imagine Atlassian invited you to help design the next generation of Jira Service Management. You have three challenges: Keep only 5 existing JSM features.Remove 3 features forever.Invent 1 brand-new capability that doesn't exist today. What would your ideal version of Jira Service Management look like? I'm interested in…

    • Should Confluence optimize for information retrieval or knowledge retrieval in the era of Rovo AI?

      Traditional Confluence search focuses on retrieving relevant pages. Rovo shifts the experience toward retrieving synthesized answers instead. These are fundamentally different objectives. Should enterprise knowledge management optimize for: finding documents,understanding concepts,or generating contextual answers? How…

    • How does Jira Cloud ensure data consistency between issue updates and JQL search results?

      I understand that Jira Cloud uses a search index for JQL instead of querying the primary database directly. After an issue is updated through Automation, the REST API, or a bulk operation, there can sometimes be a short delay before the changes appear in JQL search results. I'm curious about how this works internally. 1.…

Avatar