About How it works Goal For experts Pricing

FAQ Log in Sign up

The wisdom layer for AI

Home About How it works Goal For experts Pricing FAQ Log in Sign up

Legal · Data Security

Data Security

Effective: 11 July 2026

ailetterbox is a letterbox. We package your AI output, we route it to the expert(s) you pick, and we delete it. The expert replies directly to your email — we never see the reply. Metadata only (who sent it, when, category) stays on our servers.

The data journey when you send a brief

You paste or attach content

Content is transmitted over HTTPS (TLS 1.3) to our servers. Encrypted in transit.

Our AI search engine packages the brief

A structured summary is generated by Anthropic Claude Haiku. Only the brief content is sent for classification — no email, no name, no persistent identifier. Anthropic does not train on the data (zero-retention mode).

You approve the packaged brief

You see exactly what the expert will receive before it’s sent. You can edit any field.

You pick your expert(s)

The brief is transmitted only to the expert(s) you select — one expert, or up to 3 if you want to compare opinions. No other expert sees it.

Delivered by email — your email is the reply-to

Sent to the expert’s registered address. The email header sets your address as Reply-To, so the expert’s reply goes straight to your inbox — not to us.

Brief content deleted from our servers

Immediately after delivery is confirmed. We hold it for up to 48 hours only if delivery has to be retried. Metadata (who sent it, when, category, delivery status) is retained. Content is not.

Expert replies directly to you

We never see the reply. Because the reply-to address is yours, the expert’s email flows expert-inbox → your-inbox, bypassing our servers entirely.

Encryption

In transit: HTTPS (TLS 1.3) for all connections between your browser, our servers, and the expert’s email provider.
At rest (metadata only): Supabase Postgres with AES-256 encryption at the database and storage layers. Brief content is not stored at rest.

Infrastructure

Hosting: Netlify (site & functions) — SOC 2 Type II certified.
Database: Supabase Postgres in EU-West — SOC 2 Type II certified.
Email: Resend — SOC 2 Type II certified. TLS enforced.
Edge / DNS: Cloudflare — ISO 27001 certified.
Routing brain: Anthropic API (Claude Haiku) — zero-retention mode; no training on submitted content.

Data retention

Brief content (your AI output): Deleted immediately once delivery to the expert is confirmed. Held up to 48 hours only if delivery has to be retried.
Brief metadata (sender email, expert id, timestamp, category, delivery status): Retained for 24 months for support, dispute resolution, and analytics.
Expert opinions / replies: Never on our servers. They flow expert → you directly.
Personal data (emails, names): Deleted on request or on account closure.

The one exception: Expert AI (future opt-in feature).

If an expert opts into Expert AI — a paid feature that builds a private AI knowledge base of their reasoning — briefs sent to that expert may be retained, with the seeker’s explicit consent disclosed at the point of send. Content is retained only for the expert who opted in, and only from the moment they enable it. Expert AI is not enabled at launch. When it is, this page will be updated to explain the exact terms.

What we don’t do

We do not sell your data.
We do not use your brief content to train AI models.
We do not read expert replies — we never receive them.
We do not share your brief with any expert other than the one you select.
We do not run advertising or analytics on your brief content.

Agentic keys and MCP

Every Expert-tier account is issued an agentic key — a public identifier of the form mcp.ailetterbox.com/<slug>. Clients paste this into an MCP-native AI assistant (Claude Desktop, Cursor, Zed and other MCP-native tools) to route briefs to that expert without opening a browser.

The key is public. Anyone who has it can attempt to call the MCP endpoint. Publishing it (e.g. on LinkedIn or an email signature) is the intended use.
Client-key gating. Experts can require a client-specific key before their inbox accepts a brief. Without the correct key, the call is rejected at the endpoint — no brief content is stored, no email is sent.
Brief content flows through the same rail. An MCP-originated brief is subject to the same package/route/delete lifecycle as a web-originated one. Content is deleted on delivery.
No credentials shared with the AI assistant. The client’s MCP config carries only the expert’s AI address + optional client key. It never carries any ailetterbox account credentials.

Incident response

In the event of a personal-data breach we will notify affected users within 72 hours in line with UK GDPR requirements, and report to the Information Commissioner’s Office where required.

Contact

Written security or data-controller correspondence to WeLINKanything Ltd, 21 Church Road, Poole, Dorset BH14 8UF, United Kingdom.