Rovo エージェントのナレッジ ソース
Aside from being able to read and summarize via URLs from some connected apps (Google and SharePoint), Rovo agents currently doesn’t support connected apps. We're actively working on enabling support for connected apps in agents.
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 spaces, specific pages, Jira projects, 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 full Jira project, or a collection of projects and spaces across your organization’s tools) along with it’s training material to ensure it’s ability to accurately read and write. Even with custom knowledge sources the agent is always subject to the user’s permissions.
Providing knowledge to an agent
When creating or editing an agent, you can specify various sources of knowledge by selecting Knowledge from the navigation items on the left side of the screen.
First determine wether 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.
プラグインとナレッジ
Agents use plugins to retrieve and process information. They’re tied to knowledge because, when you provide custom knowledge to your agent, we’ll customize the plugins your agent uses to fit. When you create an agent, you’re unable to configure the plugins your agent can use.
Plug-ins 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 Issue 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 plugins 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 | All sources | 特定の URL (Confluence、Jira、Atlas、Google、SharePoint、Slack を含む) からコンテンツを取得します。これには、現在のブラウザの URL も含まれます。 |
ユーザー プラグイン | All sources | ユーザーの名前に基づいて、アカウント ID、電子メール、名前、場所、プロファイル写真を取得します。役職やチームを指定してこの関数を呼び出さないでください。 |
QA 検索 | All sources | Confluence データ ソースから回答を検索します。検索された質問の回答とソースを返します。 |
アクティビティ プラグイン | All sources | Jira と Confluence におけるユーザーの最新のアクティビティを取得します。 |
次に行うべきタスク | All sources | ユーザーが次に取り組むのに最適なタスクを検索します。 |
ページ検索 | Confluence sources | 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 JQL | Jira sources | JQL クエリを使用して、ユーザーのすべての Jira 課題を検索します。 |
Jira Software | Jira sources | アクティブな Jira Software プロジェクトのボードとバックログに関する情報を提供します。Jira プロジェクトのボードとバックログを直接参照するときに使用されます。 |
During the creation process, if you select certain actions or knowledge sources for your agent, we’ll customize the agent’s plugins to suit its knowledge sources and actions. For example, if you create an agent that can make Jira issues, or give it a Jira project as a knowledge source, we'll enable the JQL plugin for that agent, so it can retrieve information from Jira efficiently. The reason we do this is to improve the performance of your agent, if the agent is attempting to use too many plugins to respond to a prompt, it can slow down its performance.
この内容はお役に立ちましたか?