Knowledge sources for Rovo subagents
A subagent contains the trigger, instructions, knowledge, and tools that guide it in specific situations.
Knowledge is effectively all the source information the agent can use to answer user prompts. Knowledge can include links to Confluence and Jira spaces, individual pages, Google Drive workspaces, and other relevant resources.
No matter the knowledge source, agent’s won’t return answers with information from sources the user doesn’t have clearance to view. It respects the permissions of the user who prompted it because it is acting on their behalf.
Configure knowledge scope
Every agent has access to all organizational knowledge unless you configure it differently. This constitutes all of the organization-wide resources that your org administrators have connected via Teamwork Graph and Rovo.
You can also choose to toggle on Web search, which allows the agent to search public websites for information. This is either an alternative to organizational knowledge or in addition to the scope you define.
To configure knowledge for a subagent:
Add or select a Subagent.
Scroll down to the Knowledge block.
Select one the following:
All organizational knowledge (everything the organization allows)
Custom knowledge (specific resources you choose)
No organizational knowledge.
(Optional) Toggle on Web search.
If you don’t see web search as an option, your organization admin hasn't enabled it.
Add custom knowledge
If you configure an agent with Custom knowledge, you narrow the scope of knowledge by specifying which resources it should look at. Although this may sound limiting, it can make responses more accurate and helpful by focusing the agent on information most relevant to the tools and tasks it was built for.
To add custom knowledge sources to a subagent:
Select Custom knowledge.
Select the Add knowledge button.
Select the checkboxes for the sources you want your agent to access.
Select Add.
(Optional) Toggle on Deep research mode.
If you select Confluence, Jira, or Jira Service Management, you can narrow the scope even further to certain spaces — or to a specific branch in a Confluence content tree.
When you choose Select content under for Confluence, you can search for parent content and add it along with all its child content.
Deep research mode
When you customize agent knowledge, you can also enable Deep research mode to improve how your agent “thinks” about that information. This mode is most useful in special subagents where your agent needs to conduct heavyweight evidence-based research.
It’s similar to selecting Deep research mode in Rovo Chat, effectively turning your agent into a research assistant. It considers user prompts more broadly and deeply, and responds with comprehensive reports that follow the formatting, tone, and structure you outline in the agent’s instructions.
You can only add Deep research to subagents because it is an exception to be triggered only when deeper thinking is warranted.
Considerations for Deep research
By tying an agent’s research capability to specific custom subagents, you control which questions trigger this mode, but the agent will respond in Deep research mode any time a user’s prompt triggers that subagent. This differs from Rovo Chat, where users select the mode as part of their prompt.
Agents with Deep research enabled subagents can also be triggered in automations, allowing agents to generate in-depth research reports as part of automated workflows or scheduled processes.
However, before you add Deep research, consider this:
Deep research mode takes longer to respond — up to 15 minutes — while it analyzes and compiles an in-depth report
Automation currently times out after 15-minutes, so if deep research runs for longer the automation will fail
Each user or automation is limited to 30 deep research requests a day
Was this helpful?