This section describes a Forge preview feature. Preview features are deemed stable; however, they remain under active development and may be subject to shorter deprecation windows. Preview features are suitable for early adopters in production environments.
We release preview features so partners and developers can study, test, and integrate them prior to General Availability (GA). For more information, see Forge release phases: EAP, Preview, and GA.
Build powerful Rovo Agents tailored to your team's needs. With Forge for Rovo, you can build Agents that are highly tuned to your unique workflows and data to enhance your team’s productivity.
Imagine an AI Agent that seamlessly connects to your unique datasets, enabling you to leverage critical information from private databases, bespoke solutions, or even legacy systems. This connection allows AI to adapt to your team’s ecosystem, ensuring that your team does not need to adjust to the AI, thereby enhancing efficiency and productivity. You can securely connect your Forge Agent to these data sources, ensuring that sensitive information remains protected while still being accessible for AI processing.
See the Weather forecast Rovo Agent example app of how this works in practice.
Generative AI is optimised towards natural language processing, not strict or complex logic. Simple logic may be expressed in a prompt, but as with all generative AI, the results will be subject to hallucination. But, with Forge your Agent can delegate to your app to execute the logic that can’t be compromised.
Being a virtual teammate, your Agent needs to understand your data clearly. Often, cryptically named custom fields like “lat” for “latitude” or issue links with specific meanings, such as “ownership,” can obscure this understanding. By using Forge, you can surface this information more clearly, enhancing the natural language processing capability and enabling it to arrive at more accurate results.
Forge offers numerous features that enhance the capabilities of Agents by leveraging their results. By capturing information from the Agent and prompting the user for operations based on Agent output, users can make more informed decisions, such as identifying the correct state to transition an issue to.
See the Build a Q&A Rovo Agent for Confluence tutorial to see how the Agent inserts a Confluence macro into a page.
Your Forge Agent can provide valuable functionality that other teams might benefit from. This allows other teams to use the Agent’s capabilities, enhance their workflows, and increase overall productivity.
Forge simplifies the process of sharing your Agent, either by making it publicly available on the Atlassian Marketplace or by distributing it privately through direct linking.
For more details visit selling Forge apps or distributing apps directly.
Rate this page: