---
title: From Ambiguous Questions to Action: Research Mode in Rovo Dev CLI
source: Atlassian Engineering
source_slug: atlassian
url: https://www.atlassian.com/blog/development/ambiguous-questions-to-action-research-mode-rovo-dev-cli
published: 2026-05-22
fetched: 2026-05-22T14:01:11+00:00
ingested: true
---

Not every developer question starts as a coding task.

Sometimes the hard part is figuring out where to look: Jira for work history, code for implementation truth, Confluence for product context, or pull requests for how decisions landed. Research Mode in Rovo Dev CLI came from that experience.

* * *

## **What shipped**

We shipped Research Mode as a structured workflow for investigation before action: it breaks an ambiguous question into research domains, chooses top-down or bottom-up direction per domain, sends subagents to investigate, runs another round when dependencies exist, and returns a final report with references and next-step options.

See how research mode works:

* * *

## **The pain points**

Users were asking questions that were bigger than “edit this file”:

  * Which work items are ready for automation?
  * Why does this problem happen, and what mitigations exist?
  * Which bugs or security issues keep resurfacing across work items?
  * What decision led to this architecture?
  * What evidence do we have for a launch or roadmap decision?



Prompt tuning helped the agent ask better questions, search more sources, and write cleaner summaries. But the core problem was not just prompt quality. It was research strategy.

* * *

## **From better prompts to a research workflow**

We borrowed from how research is normally done: define the question, split it into subquestions, gather evidence, compare findings, and write a synthesis. In Research Mode, those subquestions become **research domains**.

Each domain starts with a search direction. That direction gives the agent a path through the available evidence.

  * For some domains, the right path is top-down: Built on the permissions you already have, Research Mode only reads from the sources a developer already has access to. It runs on demand when a developer invokes it for a specific question, not in the background, and not across teammates’ private work. The agent’s scope is bounded by the same access controls that govern Jira, Confluence, and Bitbucket today.
  * For other domains, the right path is bottom-up: start in code or pull requests to understand what the system actually does, move into Jira to understand the work history, then trace back to Confluence to find the broader product or architectural context.



The direction is not a hard boundary. A domain can use both top-down and bottom-up research when needed. The important part is that the agent has a deliberate search sequence instead of searching every source the same way.

* * *

## **How Research Mode works**

![](https://atlassianblog.wpengine.com/wp-content/uploads/2026/05/screenshot-2026-05-22-at-3.09.32-pm-scaled.png)
    
    
    flowchart LR
        A[Ambiguous question] --> C[Research domains]
        C --> D1[Domain A: top-down]
        C --> D2[Domain B: bottom-up]
        C --> D3[Domain C: top-down]
        D1 --> E[Round 1 findings]
        D2 --> E
        D3 --> E
        E --> F{Need dependency follow-up?}
        F -- Yes --> G[Round 2: e.g. mitigation after cause]
        F -- No --> H[Final report]
        G --> H
        H --> I[Final report + references]
        I --> J[Jira tickets / deep-dive reports / Confluence pages]

  1. **Analyze the query.** Identify the global objective and what decision the research should support.
  2. **Break it into domains.** Split the work into 2–4 focused areas.
  3. **Pick direction per domain.** Choose top-down or bottom-up based on what that domain needs.
  4. **Delegate to domain subagents.** For each domain, Research Mode launches a focused investigator with a clearly scoped objective and a bounded set of sources to consult. Subagents report back to the main workflow, they don’t take actions or make changes on their own. Developers review the synthesised report before any follow-up steps (creating a Jira ticket, publishing a Confluence page, etc.) are taken.
  5. **Run another round if needed.** Some questions are sequential: first find causes, then research mitigations.
  6. **Synthesize a final report.** Merge findings by theme, resolve overlaps, cite sources, and recommend next steps.
  7. **Turn research into action.** After the report, Research Mode presents next-step options: create Jira epics and tasks for each workstream, export deeper reports for specific topics, share a summary on Confluence, or create follow-up Confluence sub-pages when a topic needs more detail.



* * *

## **What we observed**

In sessions where users invoked Research Mode, more than 84% rated the experience as helpful. We do not treat this as causal proof, since Research Mode is often used for different kinds of tasks than standard Rovo Dev sessions.

Still, it is an encouraging signal that structured research makes Rovo Dev more effective when users need serious context investigation before acting.

* * *

## **What we learned**

  * **Discovery is a first-class developer workflow.** Many valuable engineering tasks start before implementation.
  * **Search direction matters.** Top-down and bottom-up research uncover different evidence.
  * **Subagents need clear domain boundaries.** Parallelism helps only when each agent has a focused scope.
  * **Some research needs multiple rounds.** Cause and mitigation, problem and solution, or context and recommendation are often sequential.
  * **The final artifact matters.** A report with themes, references, and next actions is more useful than raw search results.



The next frontier for AI developer tools isn’t writing more code for developers. It’s helping developers cut through the noise of fragmented tools so they can focus on the judgment calls only they can make.