Before you enable file capture for AI memory
Check attachments, sharing permissions, destination access, and retention before allowing files to be copied into an AI memory service.
Choose what gets shared 2 min read
Where does AI memory data go?
The path depends on the product. In Dray, chosen conversations are kept in a local browser archive. They also go to Dray’s server, which stores them and turns them into memory. Connected assistants may then retrieve context. Local storage does not mean all processing stays on your device.
ON THIS PAGE
Follow the content through each service
Start with the original AI provider, then identify the capture tool, memory backend, processing providers, and any destination assistant. Ask what each one receives and why. A single label like “private memory” does not explain that path.
Dray’s privacy policy says outside model providers process conversation content to pull out lasting facts and prepare memory for search. The server keeps the text of captured conversations, plus memory records and their sources. Files and images go to Dray’s storage too while their switch is on, and it starts on for new installs.
Ask about the deployed policy
A product may support several processing policies. What matters for your data is the active deployment and endpoint, not a capability that exists somewhere in the code. Confirm retention and access terms before connecting sensitive work.
Keep website analytics separate from conversation processing in your review. They involve different data and controls. Depending on where you are and your cookie choice, Dray’s website sends Meta and Google details of your visit and sign-up steps to measure its ads; in the UK, the European Economic Area and Switzerland that happens only after you accept. The privacy policy says none of this includes your conversations or memory. An analytics opt-out does not mean the product stops processing the conversation content you choose to capture.
TAKE THIS WITH YOU
Data-flow questions
An illustrative template. Replace the details with material you are allowed to share.
What is stored locally? What conversation content reaches the server? Which model services process it? What is the active retention policy? Are files included, and can I leave them out? What can a connected destination retrieve? How do removal and access revocation work? Who can confirm these answers for this deployment?
USING THIS WITH DRAY
Keep the context. Check the source.
Dray stores your conversations to build memory, so it is not zero-retention itself, and it is not end-to-end encrypted. The AI model providers it sends them to have agreed not to store them. Read the privacy policy or ask support before you connect sensitive conversations.
Available sources and connections depend on your setup. Read the privacy policy before granting access.
Sources & next reads
Product details are grounded in the guides below. Example projects and prompts are illustrative, not customer results.