Assistant and cloud data

Adam Kershner
Adam KershnerCEO
5 min read

Assistant and cloud data

High-level: what leaves the device (chat to model, voice audio to transcribe endpoint, usage events) vs what stays local (IndexedDB chats, local training progress).

What this is

Chat prompts, model completions, voice audio, and usage telemetry may leave the device to Kahana-operated services. IndexedDB chats and some training progress stay local until synced by future features.

How to use it

  • Assume cloud processing for signed-in chat unless an in-product banner says otherwise.
  • Voice audio is transmitted for transcription; do not dictate highly sensitive secrets.
  • Clear browsing data to remove local IndexedDB threads.

Notes and limits

Exact data map evolves; trust the privacy policy and in-product disclosures over this summary.

Related topics

About the Author

Adam Kershner
Adam Kershner
CEO

I'm the CEO of Kahana, bringing a unique perspective from my management consulting experience at Clarkston Consulting and biomedical engineering background from Duke University. I'm focused on making the future of work more elegant through innovative technology solutions that prioritize user well-being and productivity.