Why doesn't Azure OpenAI automatically solve privacy?
Answer out loud or in your head first, then compare.
Answer
I still need to know what data I send, where it's processed and what gets stored. The specific service, configuration, region and organisational policies all matter. Confidential content can also end up in our logs, index and backups, not just in the model API.
So I don't promise “nothing is stored” based on the Azure name alone. I check the current terms and settings of the chosen solution. Network and identity protections help, but they don't replace checking whether the user may read the document. A harmful-content filter isn't a mechanism for granting rights to company data either.
Why it matters: The offer involves real data and internal integrations.
Possible follow-ups: Who can read the stored traces of model calls?
How did it go? Be honest — “Not yet” puts the question on your review list.
Start with
- E-P01 · What is cloud computing? — AWS, Cloudflare and infrastructure
- E-P03 · What is Cloudflare, and what is it for? — AWS, Cloudflare and infrastructure
- E-P04 · How does Cloudflare differ from AWS? — AWS, Cloudflare and infrastructure
Further reading
- Azure AI Search: Document-level access control(opens in a new tab)Docs; accessed 22.10.2026. Security filters, native ACLs and preview features; syncing permissions needs an explicit mechanism.
- Microsoft Graph: Overview of permissions(opens in a new tab)Docs; accessed 22.10.2026. Delegated and application permissions, and the limits of access.