Knowledge sources for Rovo agent scenarios
Knowledge, in the context of agents, is the information and resources that you provide to an agent to help improve the accuracy and helpfulness of its responses. Knowledge can include links to Confluence and Jira spaces, specific pages, Google Drive workspaces, and other relevant resources.
It’s important to remember all agents will have default knowledge, which is essentially everything the user who’s interacting with the agent has access to at the time they’re using it.
By electing to provide an agent with custom knowledge your agent will only be able to reference the knowledge sources you provide (whether it’s a specific link, a Jira space, or a collection of spaces across your organization’s tools) to ensure its ability to accurately read and write. Even with custom knowledge sources the agent is always subject to the user’s permissions.
エージェントにナレッジを提供する
When creating or editing a scenario, specify various sources of knowledge by selecting Knowledge from the left-side navigation.
First determine whether you want to give the agent specific sources or not. If you chose to provide specific sources, the agent won’t be able to use other sources to answer prompts.
To provide specific knowledge to an agent:
Switch on the toggle Only reference these sources.
Select the sources you want your agent to access using the checkboxes. Some sources allow more granular options like Jira and Confluence for which you can search specific pages, spaces, or projects.
For example, when selecting Confluence as a knowledge source, you can choose to either provide an entire space, or you can select Content under which includes the content on the page and on any of its child pages.
Skills and Knowledge
Agents use skills to retrieve and process information. There are some system skills that are tied to knowledge because, when you provide custom knowledge to your agent, we’ll customize the system skills your agent uses to fit. When you create an agent, you’re unable to configure the skills your agent can use.
Skills allow agents to access data from your other Atlassian apps and connected third-party apps in order to provide their full functionality. For example, while you may use the Work Item Organizer in Jira, it will be able to leverage information based on user permissions from Confluence pages to create a new epic in Jira.
These are the system skills your agent will have depending on the knowledge sources you provide it:
名前 | 関連ナレッジ | 説明 |
既読コンテンツ | すべてのソース | Retrieve the contents from certain URLs including Confluence, Jira, Google, SharePoint, Figma, GitHub, Loom, Microsoft, Confluence Whiteboards, Slack, and others. This also includes the current browser URL. |
ユーザー | すべてのソース | Fetches the account ID, email, name, location, job title, department/organization, recent activities, and profile picture based on a user's name. Do not call this function with a job title or team. |
検索 | すべてのソース | Search for information from all organization knowledge sources or custom knowledge sources including Confluence, Jira, and third parties. It returns relevant content and sources that were used to find the question. |
ページ検索 | Confluence ソース | 特定の検索フィルターに基づいて、特定の Confluence ページまたはブログ投稿を検索します。 |
Jira field search | Jira ソース | Search Jira for fields, their values, and functions in JQL expressions. |
Jira work item search | Jira ソース | Search Jira work items using a JQL expression. |
Jira space search | Jira ソース | Search Jira spaces based on user query. This tool can get you space details like space key, ID, title, and type. |
Jira recent space | Jira ソース | Get the user's most recently used Jira space. This tool can get you space details like space key, ID, title, and type. |
During the creation process if you select certain skills or knowledge sources for your agent, we’ll customize the agent’s skills to suit them. For example, if you create an agent that can create Jira work items, or point it to a Jira space as a knowledge source, we'll enable the Jira field search skill for that agent, so it can retrieve information from Jira efficiently. We do this to improve the performance of your agent. If the agent is attempting to use too many skills in response to a prompt, it can slow down performance.
この内容はお役に立ちましたか?