Atlassian uses cookies to improve your browsing experience, perform analytics and research, and conduct advertising. Accept all cookies to indicate that you agree to our use of cookies on your device.
Atlassian uses cookies to improve your browsing experience, perform analytics and research, and conduct advertising. Accept all cookies to indicate that you agree to our use of cookies on your device. Atlassian cookies and tracking notice, (opens new window)
No data is accessed or processed within your Confluence instance.
Functional data is stored within Atlassian’s platform using the storage API.
Prompts are anonymized and stored in a secure external database to improve the AI model via fine-tuning.
App runs server-side on Atlassian’s Forge platform.
No token/secret storage.
Ongoing vulnerability testing.
DATA FLOW DIAGRAM
APPS+ DETAILS
Transparent technical details of the secure data flows in/out of Apps+
What Prompts entered by the user. Where api.appsplus.co/ai running on Cloudflare. Why Sent to OpenAI GPT-4 model to return component mappings and insights. Note Refer to the OpenAI usage policies for more details.
What {app, host, user, prompt, result, timestamp} Where Cloudflare Workers KV. Note host and user are anonymous Atlassian IDs. The prompt is also anonymized.
FAQs
Due to technical limitations you’ll need to click the Toggle to refresh checkbox a few times in the macro config sidebar.
AI can be brilliant when it works, but often it'll return unexpected results. Here’s some tips: Try the examples listed when first inserting the macro. Keep your input message simple and literal. If it doesn’t work, try again with a different input message. If you still have problems, contact support@appsplus.co
We use a custom trained AI model to convert your natural language input into functional components that map onto Atlassian’s Forge UI kit components.
We will continue to improve the apps and release new feature improvements as Atlassian’s Forge platform matures. We’re also collecting training data to fine-tune the AI models so that they’ll become smarter and more useful.
Contact
Our team provide fast 24/7 support. We typically respond within minutes-hours and aim to resolve any problems in the same day.
