Updated June 17, 2026
How your mail data moves
A plain-language map of how nagu reads, processes, and stores your mail. The formal details live in the Privacy Policy and Terms; this page is the human version.
The short version
nagu reads your mail to help you, keeps the results as objects you own, sends nothing without your approval, and never lets an AI provider train on your content. Personalization is yours alone and you can clear it.
The path your mail takes
- 1
You connect a mailbox
You grant a minimum set of Google scopes — read mail, label it, send drafts you approve, and read calendar availability. Read-only is the default; we ask for nothing we do not use.
- 2
Your mail syncs into your account
We pull the messages, headers, and metadata needed to show your inbox, sort it, and prepare a brief. A local cache keeps things fast; it is never the system of record and clears when you sign out.
- 3
AI reads only what a feature needs
When you ask for triage, a brief, a summary, or a draft, the relevant excerpts — not your whole mailbox — go to an AI provider through our gateway, which carries a no-training, zero-retention posture.
- 4
Results become objects you own
Briefs, summaries, drafts, and receipts are saved in your account as things you can read, edit, and delete. Every AI answer carries source receipts so you can see what it read.
- 5
Nothing leaves without your say-so
Drafts are suggestions until you approve them. Sending mail always requires an explicit confirmation. Reversible actions like archive can be undone. nagu never sends on its own.
What we ask Google for, and why
We request the minimum scopes for the features you use, and we explain each one. Read-only is the default posture where it applies.
- Read your mail — so your inbox, briefs, summaries, search, and triage reflect what is actually there.
- Label and archive — so approved triage syncs back to Gmail (and stays reversible).
- Send drafts you approve — only after you confirm the send, never on our own.
- Read calendar availability — so briefs and drafts can be schedule-aware, without ever changing your calendar.
The full scope-by-scope justification is in the Privacy Policy.
Who processes the AI parts
When a feature needs a language model, the request goes through our gateway to one of these providers. Every route carries a no-training, zero-retention posture. This list is generated from the same runtime manifest that routes live traffic, so it matches what is actually in use.
- Vercel AI Gateway — Model routing only — the gateway in front of every provider. Not a model-training destination for your content.
- Anthropic — Language-model processing for triage, briefs, summaries, and reply drafts when routed through the gateway.
- OpenAI — Language-model processing for triage, briefs, summaries, and reply drafts when routed through the gateway.
The full table, with regions and retention, is on AI processors.
Three promises about training
These are three different things, and we keep them separate:
- We do not train general AI models on your mail.
- nagu learns your voice and habits only for your own features — a per-user model that is yours, account-scoped, and clearable any time.
- Every AI provider we use is contractually blocked from training on your content.
What is kept, and what is not
Retention is precise by surface — the providers keep nothing, the objects you create stay until you delete them, and the local cache clears on sign-out. The full breakdown is in the Privacy Policy. You can export or delete your data any time by contacting help@creative-int.com.