AegisAI Perspectives · 144

How AegisAI investigates an email, step by step

AegisAI reads each email through the API after delivery, checks it in parallel, sandboxes its links and files, gives one verdict, and removes what fails.

TL;DR
Answer
AegisAI investigates each email after delivery: it reads it through the API, runs four checks in parallel, opens links and attachments in a sandbox, gives one verdict with evidence and pulls convicted mail.
Who it's for
If you run IT for a company of 20 to 500 people on Microsoft 365 or Google Workspace, with a small IT or security team and no SOC.
Watch out for
Removal needs write access, so grant read access first and review the verdicts before you grant it.
What AegisAI does
Reputation, intent, policy and headers are checked in parallel. Convicted mail is pulled from every mailbox, forwards included.
Book a demo

See it on your own Google Workspace or Microsoft 365 tenant. No MX change.

Or get the Q3 2026 State of the AI Attack report (free, instant download)

Not ready for a demo? Check your domain.

How AegisAI investigates an email, step by step

AegisAI connects to Microsoft 365 or Google Workspace through the API, judges every message by its intent, and removes what fails from every mailbox it reached1. The steps below follow one email from arrival to removal.

If you run IT for a company of 20 to 500 people on Microsoft 365 or Google Workspace, with a small IT or security team and no SOC, this page shows what happens when a tool investigates one suspicious email, and what evidence you get back. The product side is on the email phishing prevention page. What a team of agents is, as a category, is in multi-agent AI email security. How to judge a tool that investigates is in how to pick AI agents that investigate phishing emails. One evasive link, start to finish, is in the evasive links and attachments post. This page is the full path of one message.

What you can do by the end

  • Name what each check reads in one email and the evidence it records.
  • Read a verdict: its confidence score and evidence, then its next step.
  • Grant read access for monitoring first, then write access for removal.

Key takeaways

- The message is read through the Microsoft 365 or Google Workspace API after delivery2.

- Four checks run on each message at the same time3.

- Links and attachments are opened in a sandbox4.

- Every verdict comes with a confidence score and plain-language evidence5.

- Convicted mail is pulled from every mailbox, forwards included6. Nothing is removed until you grant write access7.

The short answer

QuestionAnswerSource
How does AegisAI investigate an email, step by step?It reads the message through the API after delivery and runs four checks in parallel. It opens links and attachments in a sandbox. It gives one verdict with its evidence, then pulls convicted mailPlatform overview, aegisai.com
What evidence does a verdict carry?A confidence score and plain-language evidence. For a link, the redirect chain is recorded in the verdict10. An alert adds the warning signs found and a recommended next step15Three aegisai.com pages
How long does a verdict take?AegisAI reports on its inbound email security page that the median verdict takes 1.9 seconds, and a convicted message is removed from every mailbox it reached within seconds8Inbound email security page, aegisai.com
How is a convicted email removed?It is pulled from every mailbox it reached, once you have granted write accessPlatform overview, aegisai.com
What API access does moving a message need?On Microsoft 365, the Graph message move call lists Mail.ReadWrite as its least privileged permission17. In Gmail, the trash call takes the mail.google.com or gmail.modify scope20Microsoft Learn, Google for Developers

Read the rows in order: they follow the email from arrival to removal.

Short on time? Watch the explainer, or book a demo.

What are email investigation agents, and what does each one check?

Email investigation agents are separate checks that read the same message at the same time. There are four: reputation, intent, policy and headers. Links and attachments are opened in a sandbox. Each check feeds one verdict.

Intent matters most when a message carries nothing to detonate (open in a sandbox to see what it does). Business email compromise is a scam aimed at businesses and individuals who perform a transfer of funds25. Such a message often has no link and no file. Intent is one of the four checks that run on every message.

Ask for the intent evidence first when a payment or bank detail change is flagged.

How do email investigation agents analyze a threat, step by step?

  1. The email is delivered to the mailbox. AegisAI reads mail through the Microsoft 365 or Google Workspace API after delivery.

  2. The mail platform has already stamped its authentication results. The email authentication results (SPF, DKIM, DMARC) are recorded in the Authentication-results header of inbound messages24.

  3. Four checks start at once: reputation, intent, policy and headers.

  4. Links are opened in a sandbox. Each link is followed hop by hop in an isolated browser, and the chain is recorded in the verdict.

  5. Per the evasive links and attachments post, attachments of all kinds are pulled apart in secure, sandboxed environments14.

  6. The checks end in one verdict, with its score and its evidence.

  7. The platform overview states that convicted mail is pulled from every mailbox, forwards included. This step needs write access.

Keep this order in mind when you read a verdict: each piece of evidence comes from one of these steps.

What evidence does each step record?

StepWhat is checkedEvidence recordedSource
Read after deliveryThe delivered message, through the Microsoft 365 or Google Workspace APIThe delivered message, read through the API
AuthenticationSPF, DKIM and DMARC, checked by the mail platform itselfThe Authentication-results header, stamped by the platform for every reader alike
Four checks in parallelReputation, intent, policy, headersEach check feeds the one verdict
LinksEvery link, followed hop by hop in an isolated browserThe redirect chain, recorded in the verdict
Gated pagesA page hidden behind a gateThe gate itself, treated as evidence11
QR codesA QR code in the messageDecoded to a URL and detonated like any other link12
AttachmentsAttachments of all kindsPulled apart in secure, sandboxed environments
VerdictEverything aboveA confidence score and plain-language evidence
AlertThe convicted messageWarning signs found, with a recommended next step
RemovalEvery mailbox the message reached, forwards includedRuns only after write access is granted

The authentication row gives no reader an edge: the platform stamps the same header for every tool that reads the message. Use the evidence column as your checklist when you review a verdict.

What happens when a link hides behind a gate or a QR code?

The email phishing prevention page states that AegisAI treats the gate itself as evidence and never scores a hidden page clean. A QR code is decoded to a URL and detonated like any other link. The redirect chain of each link is recorded in the verdict.

The case of one evasive link is in the evasive links and attachments post. Open the redirect chain in the verdict before you release a gated link.

What integration and deployment do teams without a SOC need?

The integration is an API connection to Microsoft 365 or Google Workspace. Removal waits for write access, and each verdict shows its evidence, so a small team can review it.

Write access is what lets a tool move mail. On Microsoft 365, the Graph move call creates a new copy of the message in the destination folder and removes the original18. Its least privileged permission is Mail.ReadWrite. In Gmail, the trash call moves the specified message to the trash. The gmail.modify scope does not allow immediate, permanent deletion of threads and messages, bypassing the trash19.

Grant read access first, review the verdicts, then grant write access.

How does the agentic workflow differ from legacy detection rules?

The difference shows in three answers: when the tool reads the message, what evidence it returns, and whether it can remove mail after delivery. Ask any detection tool, legacy rules or agents, the same three questions. When does it read the message? What evidence does it return? Can it remove mail after delivery? For this workflow the answers are: after delivery, through the API; a scored verdict with its evidence; and removal from every mailbox it reached.

Microsoft 365 also acts after delivery. Zero-hour auto purge (ZAP) retroactively detects and neutralizes malicious phishing, spam or malware messages delivered to cloud mailboxes23. Automated investigation in Defender for Office 365 Plan 2 analyzes the alert and the message, with the evidence around it21. Its Evidence tab shows the entities analyzed and the results22.

Put the three questions to every tool that investigates your mail, including the ones already in your tenant.

What audit trail does a verdict leave for compliance in regulated industries?

The trail is the verdict itself: its score and its evidence. For a link, it holds the redirect chain. The alert adds the warning signs found and a recommended next step.

This page names no regulation or standard for this record. Ask your auditor which fields they need, then check them against one real verdict.

How AegisAI handles this

AegisAI reads mail through the Microsoft 365 or Google Workspace API after delivery. Reputation, intent, policy and headers are checked in parallel. Every verdict comes with a confidence score and plain-language evidence. Convicted mail is pulled from every mailbox, forwards included.

Book a demoSee phishing prevention

See your own records: Check your domain.

How do you get a live walkthrough of the investigation agents?

Run it on your own mail. In monitoring mode the agents investigate live mail and remove nothing, while your team reads each verdict. To set that up, ask to start in monitoring mode on your own tenant.

Pick three recent suspicious emails and read their verdicts side by side.

How to measure it in 30 days

Track three numbers from your own verdicts and alerts.

  • Verdicts your team reviewed where the plain-language evidence matched what they found.
  • Time from arrival to removal for each convicted message, next to the 1.9 second median verdict on the inbound email security page.
  • Mailboxes each convicted message reached, forwards included.

Compare the three numbers on day 1 and day 30.

Questions people ask

How does AegisAI investigate an email, step by step?

AegisAI reads mail through the Microsoft 365 or Google Workspace API after delivery. Four checks run in parallel. Links and attachments are opened in a sandbox. One verdict follows, with its evidence. Convicted mail is pulled from every mailbox, forwards included.

Is every redirect in a link followed?

Yes, hop by hop in an isolated browser, and the chain is recorded in the verdict.

How are QR codes in an email handled?

The QR code is decoded to a URL and detonated like any other link.

Is email removed before I grant write access?

No. Nothing is removed until you grant write access. Once it is granted, convicted mail is pulled from every mailbox, forwards included.

What does an alert contain?

Alerts give a summary, the warning signs found and a recommended next step. The verdict behind the alert holds the evidence.

Does moving a message through the API delete it for good?

Not in one step. The Graph move call creates a new copy in the destination folder and removes the original. The Gmail trash call moves the message to the trash, and gmail.modify does not allow immediate, permanent deletion.

Sources

  1. (Platform overview, aegisai.com)
  2. (Email phishing prevention, aegisai.com)
  3. (Inbound email security, aegisai.com)
  4. (Evasive phishing links and attachments, aegisai.com, 20 October 2026)
  5. (AI agents that investigate phishing emails, aegisai.com, 2 November 2026)
  6. (Microsoft Learn, Anti-spam message headers, 27 July 2026)
  7. (Microsoft Learn, message: move, 4 April 2024)
  8. (Google for Developers, users.messages.trash, 15 April 2026)
  9. (Google for Developers, Choose Gmail API scopes, 10 September 2026)
  10. (Microsoft Learn, Zero-hour auto purge, 1 June 2026)
  11. (Microsoft Learn, Automated investigation and response, 2 June 2026)
  12. (Microsoft Learn, View the results of an automated investigation, 10 January 2025)
  13. (FBI IC3, Business Email Compromise, opened 14 November 2026)

Recent posts

Every email, investigated.