Source: https://internal-agents.com/agents/atlassian-rovo-dev # Atlassian — Rovo Dev (RovoDev) Rovo Dev is Atlassian's coding agent, available internally on all Jira sites. It works from a Jira work item to a pull request, and the developer reviews the plan and the code at each step. It became generally available in October 2025. - Approach type: Task agent - Deployment stage: Scaled - Autonomy: Human in loop - Evidence strength: Detailed primary - Status: Commercialized - First reported year: 2024 - Work: Coding, Code review - Interfaces: Jira - Invocation: Interactive - Entry reviewed: 2026-09-15 ## Where people stay involved - **Jira issue → reviewed pull request** — Work product review · Level 3 ## Overview ### Summary Rovo Dev is Atlassian's coding agent, available internally on all Jira sites. It works from a Jira work item to a pull request, and the developer reviews the plan and the code at each step. It became generally available in October 2025. Fact · Reported · High confidence · `atlassian-rovo-dev--summary` Confidence reason: A linked first-party source states the claim. Evidence: - Supports · [1] [Improving the coding agent experience](https://www.atlassian.com/blog/atlassian-engineering/improving-coding-agent-experience) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/atlassian-rovo-dev-source-1/content.md) - Supports · [2] [Developer productivity improved with Rovo Dev](https://www.atlassian.com/blog/atlassian-engineering/developer-productivity-improved-with-rovo-dev) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/atlassian-rovo-dev-source-2/content.md) - Supports · [3] [HULA: Human-in-the-loop software development agents (arXiv 2411.12924)](https://arxiv.org/abs/2411.12924) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/atlassian-rovo-dev-source-3/content.md) ## Supervision evidence ### Operating model assessment Level 3 for Jira issue → reviewed pull request; human attention boundary: work-product-review. Inference · Catalog judgment · Medium confidence · `atlassian-rovo-dev--operating-models-0` Confidence reason: The HULA framework and engineering blog describe a human-in-the-loop cycle that ends in a reviewed pull request. Qualifications: - Observation date: 2024-11 Evidence: - Supports · [1] [Improving the coding agent experience](https://www.atlassian.com/blog/atlassian-engineering/improving-coding-agent-experience) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/atlassian-rovo-dev-source-1/content.md) ## Implementation details ### Harness Built on the HULA framework, which runs set context, generate plan, generate code, and raise PR Fact · Reported · High confidence · `atlassian-rovo-dev--architecture-harness` Confidence reason: A linked first-party source states the claim. Evidence: - Supports · [1] [Improving the coding agent experience](https://www.atlassian.com/blog/atlassian-engineering/improving-coding-agent-experience) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/atlassian-rovo-dev-source-1/content.md) ### Interfaces jira Fact · Reported · High confidence · `atlassian-rovo-dev--architecture-interfaces` Confidence reason: A linked first-party source states the claim. Evidence: - Supports · [1] [Improving the coding agent experience](https://www.atlassian.com/blog/atlassian-engineering/improving-coding-agent-experience) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/atlassian-rovo-dev-source-1/content.md) ## Reported metrics ### Headline claim Dogfooded across 1,900+ repositories with a 50,000+ comment internal dataset Metric · Reported · Medium confidence · `atlassian-rovo-dev--headline-metric` Confidence reason: Atlassian reported the dogfooding scale in its own engineering blog without independent verification. Qualifications: - The source does not report the denominator of this figure. - Reported by: Atlassian - Scope: Internal code-review dogfooding repositories and Rovo Dev-generated classifier training comments - Observation date: 2026 Evidence: - Supports · [2] [Developer productivity improved with Rovo Dev](https://www.atlassian.com/blog/atlassian-engineering/developer-productivity-improved-with-rovo-dev) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/atlassian-rovo-dev-source-2/content.md) · Preserved content.md, lines 66, 87 ### Key observation Dogfooded across 1,900+ repositories over more than a year Metric · Reported · Medium confidence · `atlassian-rovo-dev--key-metrics-0` Confidence reason: Atlassian reported the dogfooding scale in its own engineering blog. Qualifications: - The source does not report the denominator of this figure. - Reported by: Atlassian - Scope: Internal code-review evaluation across 1,900+ repositories spanning over a year - Method: Year-long online evaluation across internal repositories Evidence: - Supports · [2] [Developer productivity improved with Rovo Dev](https://www.atlassian.com/blog/atlassian-engineering/developer-productivity-improved-with-rovo-dev) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/atlassian-rovo-dev-source-2/content.md) · Preserved content.md, lines 87 ### Key observation Trained on a proprietary internal dogfooding dataset of 50,000+ Rovo Dev comments Metric · Reported · Medium confidence · `atlassian-rovo-dev--key-metrics-1` Confidence reason: Atlassian reported the dataset size in its own engineering blog. Qualifications: - The source does not report the denominator of this figure. - Reported by: Atlassian - Scope: ModernBERT classifier training dataset of internally sourced Rovo Dev-generated comments - Method: Internal dogfooding comments labeled by whether they led to a code resolution Evidence: - Supports · [2] [Developer productivity improved with Rovo Dev](https://www.atlassian.com/blog/atlassian-engineering/developer-productivity-improved-with-rovo-dev) · [Preserved copy](https://github.com/steel-experiments/internal-agents-map/blob/main/archive/sources/atlassian-rovo-dev-source-2/content.md) · Preserved content.md, lines 66 ## Sources 1. [Improving the coding agent experience](https://www.atlassian.com/blog/atlassian-engineering/improving-coding-agent-experience) - Engineering blog · First party · Evidence - Original URL: - Accessed: 2026-08-13 · Last verified: 2026-08-31 - Preserved copy in the repository: 2. [Developer productivity improved with Rovo Dev](https://www.atlassian.com/blog/atlassian-engineering/developer-productivity-improved-with-rovo-dev) - Engineering blog · First party · Evidence - Original URL: - Accessed: 2026-08-13 · Last verified: 2026-08-31 - Preserved copy in the repository: 3. [HULA: Human-in-the-loop software development agents (arXiv 2411.12924)](https://arxiv.org/abs/2411.12924) - Paper · First party · Evidence - Original URL: - Published: 2024-11 · Accessed: 2026-08-13 · Last verified: 2026-08-31 - Preserved copy in the repository: