Some setup — keys, settings, or a connected account
Worth knowing: The free walkthrough starts in demo mode with fake sample data — real protection requires connecting a Google Workspace or Microsoft 365 mailbox via API (no MX record changes needed).
Summarized from 2 community tutorials · July 2026
Highlights
Autonomous alert triage (ASA)An agent reviews flagged emails with full environment context and shows its reasoning, e.g. catching a Google Classroom-based callback phishing attack.
Auto-generates and back-tests detection rulesThe autonomous detection engineer (Aday) writes a new detection rule from a missed attack, back-tests it against historical mail, and iterates before you approv
Deep per-message forensic viewEach flagged email shows open/reply/forward counts, an attack-score verdict with the specific suspicious signals, extracted QR-code links, and a safe screenshot
Org-wide IOC hunting and searchSearch historical mail across the whole organization for a known-bad indicator (URL, attachment hash, sender) to see who else received it.
Email-bomb detection and cleanupBaselines normal mailbox volume, detects spam-bomb spikes, and auto-separates the flood of subscription spam from legitimate mail received during the attack win
Summarized from 2 community tutorials · July 2026
i
No approved reviews yet. Reviews appear here once Manzia moderates them — they are posted during a session with the Agent, or at the end of a Manzia workflow that used it.
