# Rovo Agents Configurable team agents for Jira, Confluence and connected work knowledge. Canonical profile: https://ki-agentenkompass.de/en/agents/rovo/ Editor: [Michael Meierhoff](https://ki-agentenkompass.de/en/about/) Sources reviewed: 2026-10-26 Basis: provider documentation. Examples are editorial suggestions, not hands-on product tests. ## Overview Available offering; access methods and prerequisites are described separately in this profile. - Provider: Atlassian - Product family: Rovo Agents - Profile type: Agent platform - Environment: Cloud workspace - Connections: Team knowledge, Edit Jira, Maintain Confluence, Automations, Configure agents - Setup: Eligible Atlassian Cloud subscription and enabled AI features. - Pricing model: Included in eligible cloud subscriptions with credit allowances. Additional usage is listed at USD 0.01 per credit; base subscription separate. ## Key features ### Team knowledge Use knowledge from Atlassian and connected apps. Source: https://support.atlassian.com/rovo/docs/agents/ ### Edit Jira Create and edit Jira work items with granted permissions. Source: https://support.atlassian.com/rovo/docs/agents/ ### Maintain Confluence Create and edit Confluence pages. Source: https://support.atlassian.com/rovo/docs/agents/ ### Automations Invoke agents in automation rules. Source: https://support.atlassian.com/rovo/docs/agents/ ### Configure agents Define specialized goals and knowledge sources. Source: https://support.atlassian.com/rovo/docs/agents/ ## Example workflows ### Team knowledge - Your input: Use knowledge from Atlassian and connected apps. - Possible result: A work product for your review. - What to check: Review results and write actions before accepting them. ### Edit Jira - Your input: Create and edit Jira work items with granted permissions. - Possible result: A work product for your review. - What to check: Review results and write actions before accepting them. ## Requirements and limits ### Setup Requirement: Eligible Atlassian Cloud subscription and enabled AI features. Source: https://support.atlassian.com/rovo/docs/agents/ ### Usage costs Limitation: Included in eligible cloud subscriptions with credit allowances. Additional usage is listed at USD 0.01 per credit; base subscription separate. Source: https://www.atlassian.com/licensing/rovo ### Output quality Not yet confirmed: Review results and write actions before accepting them. Source: https://support.atlassian.com/rovo/docs/agents/ ## A good fit if … - your team uses Jira or Confluence on a Standard, Premium or Enterprise cloud plan - agents should have their own account with an audit trail and admins should limit access and creation rights - you want to limit who can create agents through groups and choose knowledge sources deliberately ## Less suitable if … - you are not on an Atlassian Cloud plan; the reviewed admin page names Standard, Premium and Enterprise - you need automated agents that have a person approve every write action beforehand Editorial assessment based on provider documentation. Not a product test. ## Usable AI models Fixed choice across providers According to Atlassian, Rovo Agents run on GPT, Gemini and open models such as Llama. In Studio you set "Quick answers" or "Think deeper" per agent, and each level has a default model tested by Atlassian; the choice can change. The checked pages do not name individual models, own keys or own models. - Model families named: OpenAI (GPT), Google (Gemini), Meta (Llama, Muse) - Model choice: Automatic or your choice - Your own API key: Not stated - Router or custom endpoint: Not stated - Local models: Not stated Documented · Sources accessed on: 2026-11-05 - [Atlassian: AI transparency](https://www.atlassian.com/trust/ai/transparency?tab=chat) - [Atlassian: Set a reasoning tier for a Rovo agent](https://support.atlassian.com/studio/docs/set-a-reasoning-tier-for-a-rovo-agent/) ## Europe & regional availability Consider installation and provider access separately. A complete regional feature matrix is not published. Reviewed scope: Product access in Germany and the EU Reviewed on: 2026-10-26 ### Access and connected services Availability still unclear Eligible Atlassian Cloud subscription and enabled AI features. Region covered: Germany / EU Documented reason: The reviewed sources document no specific restriction caused by the AI Act, DMA or GDPR. Model and service access depend on country and contract. Official source: https://support.atlassian.com/rovo/docs/agents/ Official source: https://www.atlassian.com/licensing/rovo ## Accounts & permissions Based on provider documentation. Permissions depend on the account, integration and organization policies. Review the permissions actually requested before use. Configuration covered: Rovo Agents in Atlassian Cloud (Standard, Premium or Enterprise) with Rovo Studio Sources reviewed: 2026-11-05 ### Account used Documented: An agent acts either with the account of the person using it or with its own Atlassian account. In the first case it inherits that person's rights and changes appear under their name; in the second they are credited to the agent. Evidence: https://support.atlassian.com/studio/docs/understand-rovo-agent-accounts/ ### Admin approval Documented: Organisation admins manage Studio access in Atlassian Administration and can limit creation rights to specific groups. The Studio settings allow permissions to be restricted. Evidence: https://support.atlassian.com/organization-administration/docs/use-rovo-studio-in-your-organization/ ### Data access & team sharing Documented with conditions: Reach depends on knowledge sources and the account choice. With an agent account, app and space admins grant access to spaces, and any person can give agents access to their own content. Agents can be shared; the page does not state the permission model for that. Evidence: https://support.atlassian.com/studio/docs/understand-rovo-agent-accounts/ Evidence: https://support.atlassian.com/rovo/docs/agents/ ## Prices and included usage Pricing checked: 2026-10-26 Included in eligible cloud subscriptions with credit allowances. Additional usage is listed at USD 0.01 per credit; base subscription separate. Included in eligible cloud subscriptions with credit allowances. Additional usage is listed at USD 0.01 per credit; base subscription separate. Pricing details: https://www.atlassian.com/licensing/rovo ## Operation & oversight Based on public provider documentation. Assessments are editorial inferences from the stated properties. Actual time requirements and reliability have not been measured. Deployment covered: Rovo Agents in interactive use and in Atlassian Cloud automation rules Sources reviewed: 2026-11-05 ### Files and working state Open in reviewed sources: The reviewed pages do not describe which files or state an agent keeps between runs. Agent conversations can be reviewed as transcripts. Evidence: https://support.atlassian.com/rovo/docs/agents/ ### Sign-ins Documented with conditions: If a third-party app is not authenticated, the agent keeps working but cannot use that tool. The pages give no validity periods for connections. Evidence: https://support.atlassian.com/studio/docs/best-practices-to-automate-agents-safely/ ### Starting further runs Documented with conditions: Agents run interactively with a person or in the Use agent step of an automation rule. Which triggers and schedules are available is not stated on the reviewed pages. Evidence: https://support.atlassian.com/studio/docs/best-practices-to-automate-agents-safely/ ### Human intervention Documented with conditions: With interactive use, work items, pages and emails are only changed or sent after a human approves. Automations have no approval step; there an agent can be limited to read-only actions. Evidence: https://support.atlassian.com/studio/docs/best-practices-to-automate-agents-safely/ ### Detecting errors Documented with conditions: With an agent account, changes appear under the agent's name and are easier to trace in audit logs. A run history or failure notifications for automations are not described on the reviewed pages. Evidence: https://support.atlassian.com/studio/docs/understand-rovo-agent-accounts/ ### Resuming after failures Open in reviewed sources: The reviewed pages contain nothing on retrying or resuming after failures. Evidence: https://support.atlassian.com/studio/docs/best-practices-to-automate-agents-safely/ ### Editorial assessment For automations the choice between user and agent account is the key decision, since no confirmation takes place there. Run history and retry are not described on the reviewed pages. ## Memory and conversation continuity Scope: Rovo Agents; personal memory controls in Rovo Chat Sources accessed: 2026-11-04 Personal summary from Teamwork Graph plus explicit conversation instructions. ### Storage and scope Partly documented: Rovo distinguishes an implicit activity summary and explicitly saved instructions. The specific storage backend is not named. - [What is Rovo memory management?](https://support.atlassian.com/rovo/docs/what-is-rovo-memory-management/) - [Rovo Agents](https://support.atlassian.com/rovo/docs/agents/) ### Selection and timing Documented: Teamwork Graph automatically supplies personal background; chat can save explicit remember instructions and shows an edit link. - [What is Rovo memory management?](https://support.atlassian.com/rovo/docs/what-is-rovo-memory-management/) - [Rovo Agents](https://support.atlassian.com/rovo/docs/agents/) ### Inspect, edit and delete Documented: Settings and memory shows both types. Explicit entries can be edited and deleted; activity-summary edits are suggested and applied within 24 hours. - [What is Rovo memory management?](https://support.atlassian.com/rovo/docs/what-is-rovo-memory-management/) - [Rovo Agents](https://support.atlassian.com/rovo/docs/agents/) ### Agent and channel boundaries Partly documented: Personal memories are isolated per user and Atlassian site; even admins cannot see them. Use by every custom agent is not separately guaranteed. - [What is Rovo memory management?](https://support.atlassian.com/rovo/docs/what-is-rovo-memory-management/) - [Rovo Agents](https://support.atlassian.com/rovo/docs/agents/) ### Retrieval Partly documented: Rovo uses the summary and instructions for personalization. Teamwork Graph knowledge search is distinct; technical memory selection remains unspecified. - [What is Rovo memory management?](https://support.atlassian.com/rovo/docs/what-is-rovo-memory-management/) - [Rovo Agents](https://support.atlassian.com/rovo/docs/agents/) ### Session reset and compaction Partly documented: Disabling memory prevents new explicit memories and use of existing entries. This guide does not explain behavior during conversation reset or context compaction. - [What is Rovo memory management?](https://support.atlassian.com/rovo/docs/what-is-rovo-memory-management/) - [Rovo Agents](https://support.atlassian.com/rovo/docs/agents/) ## Context Review results and write actions before accepting them. Official sources reviewed. Example tasks are editorial suggestions; hands-on testing is outstanding. ## Open points Europe, availability still unclear: - Access and connected services Requirements and limits, not yet confirmed: - Output quality ## Sources - https://support.atlassian.com/rovo/docs/agents/ - https://www.atlassian.com/licensing/rovo ## Provider Configurable team agents for Jira, Confluence and connected work knowledge. - Operator: Atlassian - Organization: Provider - Website: https://support.atlassian.com/rovo/docs/agents/ - Reviewed: 2026-10-26 - Provider source: https://support.atlassian.com/rovo/docs/agents/ - Provider source: https://www.atlassian.com/licensing/rovo [Sources and method](https://ki-agentenkompass.de/en/sources/)