This page explains how AI features in Capacities handle your data. It is written for anyone who wants a clear picture of what is shared with AI providers, how you stay in control, and where to find our legal commitments.

Legal documents

For legally binding terms and our commitments on data processing, see:

• Terms and Conditions – Service terms and user agreements, including AI use.
• Privacy Policy – How we collect, use, and protect your data.
• Data Processing Agreement (DPA) – For business customers who process personal data under regulations like GDPR.

For a broader overview of how we protect your data, see Data protection at Capacities and Data Protection and Security.

Core principles: opt-in, no training, no storage

AI features in Capacities are fully opt-in. If you do not activate AI, no data from your spaces is shared with any third-party AI services.

When you do use AI features, we rely on enterprise-grade APIs with Data Processing Agreements (DPAs) that ensure:

• No training on your data – your content is not used to train models.
• No storage of your content on third-party AI services – it is not retained after processing.
• Processing only – your data is used solely to generate responses and is then discarded.

When using Capacities AI (our default) these commitments always apply. If you bring your own API keys, the data-protection standards of your own provider and your settings on their platform apply.

Some features will route traffic through our infrastructure even if you're using your own API keys, but these data-protection standards apply throughout our entire system. You can see the full breakdown of how Capacities deals with each different AI feature below.

What data is shared, and when

The following data is shared when you use AI features:

• Strict data access constraints: AI features can't use any data outside of the spaces that are configured to use AI. In the AI settings you can configure which spaces are allowed to use AI.
• Data minimization per feature: We design our features and algorithms so that only the data necessary for each AI request is sent.

By feature

• AI Chat – Whatever you choose as context (e.g. selected blocks, one or more objects), plus backlinks and, when the feature is used, results from full-text search and full content of notes the AI decides to read. Chat messages (your questions and the model’s answers) are also sent. To support richer answers, the AI can access content across your space (search and read notes), thus all notes in the space can potentially be used.
• AI Panel (e.g. summarize, translate, improve writing) – The selected text (and any context you provide) is sent to the model.
• Ask AI command – The question you type and any context (e.g. current object) are sent.
• AI auto-tagging – The content relevant to the object (and your existing tags) is sent so the AI can suggest tags.
• AI collection selection – The content relevant to the object (and your existing collections) is sent so the AI can suggest collections.
• AI Property Auto-Fill – The current object’s properties and related content (as configured) are sent as context for filling the property.

Scope of access when extended context is used

For features that use “extended context” (e.g. AI Chat with search and read capabilities):

• The AI can search your space to find relevant notes.
• The AI can read the full content of notes (e.g. from backlinks or search results) to answer your question.

You control where AI is allowed to run: you can enable or disable AI per space. So you can limit which spaces’ content can ever be used by AI. See the Summary below.

Capacities AI

When using AI features, you are using Capacities AI. To provide these features, we use our own algorithms and model providers.

• Our AI system use a combination of different providers and models tuned for the best performance and quality. More details below.
• You can extend the Capacities AI and fine tune model-usage by adding your own API keys. More details below.

Bring your own API key (BYOK)

You can use AI in Capacities with your own API keys from supported providers. This gives you:

• No budget limit – usage is billed to your account with the provider. You may still want to configure a budget limit for your API key from Settings > AI Assistant.
• Choice of provider and model – e.g. OpenAI, Gemini (Google), Anthropic, Mistral, xAI, Perplexity.
• Optional European provider – e.g. bring your own Mistral API key and set Prefer my own keys so that your traffic goes to your European model provider instead of Capacities AI.

When you provide multiple API keys, we will filter them based on the space they are configured to work in and their consumed budget (if a maximum budget has been configured for the key). If multiple keys are available we try them in the order they appear within the AI Settings screen. If they don't work, or are out of budget, Capacities AI will be used.

Please keep in mind, that some features will route traffic through our infrastructure even if you're using your own API keys. More details above.

How key preference works

• Default – Capacities AI is used until you hit your daily budget; then your added keys are used according to your order and constraints.
• Prefer my own keys – Your keys are preferred for AI chat, panel, and auto-fill. If your keys return an errors outside of the AI Chat (out of budget, provider temporarily unavailable, ...) Capacities AI will attempt to complete the action.

Your responsibility when using your own provider

When you add your own API key, you have a direct relationship with that provider. We recommend:

• Review the provider’s terms and conditions and data usage policies before generating an API token.
• Check whether they store or use your data for training and, if needed, opt out in the provider’s settings.

Capacities does not control how third-party providers handle data once they receive it; our commitments (no training, no storage, processing only) apply to how we use enterprise-grade APIs and DPAs when we send data to providers on your behalf (Capacities AI). When the request goes via your key, the provider’s policies apply to that request.

Restricting a key to specific spaces

You can restrict an API key to one specific space in Settings > AI Assistant (key preferences). That way, only that space’s usage can go through that key.

This is a useful option if your company shares AI keys with you and you want to restrict the usage to your "work" space.

Providers for Capacities AI per feature

The following table lists the AI features in Capacities and which providers/models are used. When you use Capacities AI (included with your subscription), we use our default provider; when you bring your own API key, the feature uses the provider and model you select (subject to the note below about infrastructure).

The exact model names and versions used for Capacities AI are updated over time for quality, efficiency and performance. For the current default, see in-app settings and release notes. This table will be kept in sync as we add or change features and providers.

Summary (quick reference)

• Opt-in – No AI data sharing unless you use AI features.
• No training, no storage – We use APIs with DPAs; your content is only processed to generate responses.
• Legal docs – Terms and Conditions, Privacy Policy, Data Processing Agreement.
• Control – Turn AI on or off per space, limit AI to selected spaces only, or disable it entirely; you can also bring your own keys and prefer your own provider.