Guides
How email works for AI agents and humans, and how to keep both safe.
Agent inboxes
What is an agent inbox?
An agent inbox is an email address an AI agent owns and works through an API. How it differs from a human mailbox and a sending API, and what to check.
Email for AI agents
Why AI agents need email, the five ways to give an agent an address, what can go wrong when a model reads mail, and what to look for before you choose.
How to give an AI agent an email address
A hands-on guide: get an address for your AI agent with one call, wait for mail, read it safely and reply, with working Python and TypeScript examples.
What an email API for AI agents must do
What an email API for AI agents does that a sending API does not: receive and store mail, keep threads, wait for a message, extract codes and screen.
Agent identity and email: why an agent needs its own address
Why an AI agent should have its own email address instead of borrowing a human's, what an address proves and does not prove, and how to make it trusted.
Human in the loop email for AI agents
Keep a human in the loop for an AI agent's mail: held mail, drafts only, send approval and write levels, and why the control must sit outside the prompt.
Screening and email security
What is pre-delivery email screening?
Pre-delivery email screening checks a message during the SMTP conversation, before it is accepted. How it works, the three outcomes and the limits.
Pre-delivery vs post-delivery email security
Pre-delivery screening decides before a message is accepted. Post-delivery remediation cleans up after it lands. What each can do, and why order matters.
SPF, DKIM and DMARC explained
What SPF, DKIM and DMARC each prove about an email, what they do not prove, how the three fit together, and sample DNS records for each one.
What is a secure email gateway, and how does a pre-delivery inbox differ?
What a secure email gateway does, where it sits in the mail path, how API-based tools differ, and how an inbox that screens at its own door compares.
Held mail: what email quarantine means
What it means when an email is held in quarantine, who can release it, what an AI agent sees in the meantime, and how to review held mail well.
Email security checklist for teams with agents and humans
A practical email security checklist for teams that run AI agents and humans on email: authentication, access, review, outgoing checks and drills.
AI agent security
What is prompt injection?
Prompt injection is text that makes an AI model follow an attacker's instructions. How direct and indirect injection work, and what reduces the risk.
Indirect prompt injection
Indirect prompt injection hides instructions in content an AI agent reads. Why email is the most open channel, a worked example, and what reduces the risk.
The OWASP Top 10 for LLM Applications, mapped to email
The ten risks in the OWASP Top 10 for LLM Applications 2026, each mapped to what it means when an AI agent has an inbox, with the 2025 numbers.
Zero-click AI attacks
A zero-click AI attack needs no click because the assistant reads the message itself. EchoLeak (CVE-2025-32711) explained, and what changes for defenders.
AI agent security
The main risks when AI agents act for you: untrusted input, excessive agency, data leaving and identity. A layered defense, and why the inbox matters most.
LLM data exfiltration
How AI agents leak data: steered sends, links and images that carry data, replies to the wrong party. And the controls that limit what leaves.
Building with agent email
MCP email servers: tools, authorization and safety
What an MCP email server is, which tools it should expose, OAuth versus API keys, the risks when a model reads and sends mail, and how to connect one.
How an AI agent receives a verification code by email
How an AI agent gets a sign-up code or confirmation link by email: its own inbox, a wait call, the extracted code, the risks, and what must stay sealed.
Email webhooks vs polling: four ways an agent learns that mail arrived
Polling, long polling, webhooks and live event streams compared for inbound email: delay, cost, signatures, retries, and when an agent should use each.
How to test email flows end to end with a real inbox per test run
Test sign-up, password reset and notification emails end to end: a real inbox per test run, a wait call instead of sleeps, and a worked Playwright example.
Multi-tenant agent inboxes: one isolated workspace per customer
How to give each customer or agent its own isolated inboxes inside one account: tenant boundaries, scoped API keys, webhooks, domains and plan limits.
How to put AI agent inboxes on your own domain
Put AI agent inboxes on your own domain: what the MX, SPF, DKIM and DMARC records do, subdomain or main domain, and how to check that the setup worked.