Work Sublime Security
Giving a security agent the right amount of control I lead design for ADÉ, Sublime’s agent that writes detection rules to address missed threats.
When 2025 to now
Role Staff Product Designer
Team 1 PM, engineers, 2 designers
Outcome New rule in under 2 hours, not days Agents ADÉ Action required: payroll profile verification Action required: payroll profile verification
Completed in 48mJob ID: 019f3d5a-ff42-7706-b615-a83297b00479 ADÉ Recommended Rule
99% match in a 14-day hunt, with 40 malicious matches and 2 possible false positives.
Accept Reject
Rule Name Credential phishing: payroll QR code lure with newly registered domain
Severity High Severity
Description Detects inbound payroll-themed messages that contain QR-code links to newly registered credential-harvesting domains.
Labels Credential Phishing QR code Social engineering
Rule MQL 1 type .inbound 2 and any (attachments ,3 .file_extension in~ ("png" , "jpg" , "jpeg" , "pdf" ) 4 and any (file.explode (.), 5 .scan.qr.type == "url" 6 and ml.link_analysis (.scan.qr.data ).credphish.disposition == "phishing" 7 ) 8 ) 9 and any (ml.nlu_classifier (body.current_thread.text ).intents ,10 .name in ("payroll" , "credential_theft" ) 11 and .confidence in ("medium" , "high" ) 12 ) 13 and network.whois (sender.email.domain ).days_old <= 45
ADÉ hunted across 14 days and found 0 message groups (0 total messages)
Recommended Rule is a 0% match with 0 malicious matches and may introduce 0 false positives (Benign). It meets the threshold to auto-accept the Rule.0 Malicious0 Spam0 BenignSubject Sender Received ASA Verdict
Action required: payroll profile verification payroll-security@adp-verify.com Jul 2 MaliciousNew direct deposit document shared with you hr-notify@payroll-docs.co Jul 1 MaliciousReminder: update your payroll information benefits@company-payroll-support.net Jun 29 BenignShowing 3 of 43 message groups
ADÉ worked for 48m
Collaborated with ASA Agent to generate a threat report Validated recommendation with 1 huntPatrick Morgan triggered ADÉ at Jul 3, 2026, 2:12 PM
Subject Action required: payroll profile verification Sender payroll-verify@employee-benefits.co Recipient alex.morgan@acme.com ASA Verdict MaliciousADÉ writes a rule your team can read Each missed threat needed a new rule An engineer wrote and tested each rule by hand, so a fix took days or weeks.
User Reports Action required: payroll profile verification Action required: payroll profile verification
From Payroll Operations <payroll-verify@employee-benefits.co>To alex.morgan@acme.com
Executive Summary This message impersonates Payroll Operations and urges the recipient to verify their payroll profile through an unfamiliar domain. The sender fails DMARC, does not align with the organization’s trusted HR infrastructure, and uses credential-harvesting language under the pretext of an upcoming pay cycle.
Matched Detection Rules (0)
No Detection Rules matched this message group.
Message Content
User View Text View HTML View EML View
CAUTION: This message originated outside of your organization.
From: Payroll Operations <payroll-verify@employee-benefits.co>
Action required
Your payroll profile requires verification before the next pay cycle. Review and confirm your direct deposit details to avoid a delay in payment.
Review Status
Review Status ⚠ Unreviewed
ASA marks the message malicious, and no rule caught it The agent writes rules that people can read and change Other vendors update a central model. ADÉ writes a rule each team can read, edit and turn off.
Agents ADÉ Action required: payroll profile verification Action required: payroll profile verification
Completed in 48mJob ID: 019f3d5a-ff42-7706-b615-a83297b00479 Patrick Morgan accepted and activated the recommended ruleJul 3, 2026, 3:00 PM
Rule Detail Credential phishing: payroll QR code lure with newly registered domain Flagged Message View Flagged Messages ADÉ Recommended Rule
99% match in a 14-day hunt, with 40 malicious matches and 2 possible false positives.
Accept Reject
Rule Name Credential phishing: payroll QR code lure with newly registered domain
Severity High Severity
Description Detects inbound payroll-themed messages that contain QR-code links to newly registered credential-harvesting domains.
Labels Credential Phishing QR code Social engineering
Rule MQL 1 type .inbound 2 and any (attachments ,3 .file_extension in~ ("png" , "jpg" , "jpeg" , "pdf" ) 4 and any (file.explode (.), 5 .scan.qr.type == "url" 6 and ml.link_analysis (.scan.qr.data ).credphish.disposition == "phishing" 7 ) 8 ) 9 and any (ml.nlu_classifier (body.current_thread.text ).intents ,10 .name in ("payroll" , "credential_theft" ) 11 and .confidence in ("medium" , "high" ) 12 ) 13 and network.whois (sender.email.domain ).days_old <= 45
ADÉ hunted across 14 days and found 0 message groups (0 total messages)
Recommended Rule is a 0% match with 0 malicious matches and may introduce 0 false positives (Benign). It meets the threshold to auto-accept the Rule.0 Malicious0 Spam0 BenignSubject Sender Received ASA Verdict
Action required: payroll profile verification payroll-security@adp-verify.com Jul 2 MaliciousNew direct deposit document shared with you hr-notify@payroll-docs.co Jul 1 MaliciousReminder: update your payroll information benefits@company-payroll-support.net Jun 29 BenignShowing 3 of 43 message groups
ADÉ worked for 48m
Collaborated with ASA Agent to generate a threat report Validated recommendation with 1 huntPatrick Morgan triggered ADÉ at Jul 3, 2026, 2:12 PM
Subject Action required: payroll profile verification Sender payroll-verify@employee-benefits.co Recipient alex.morgan@acme.com ASA Verdict MaliciousAccept Recommendation
This will create the recommended detection rule and apply an Auto-Quarantine action. You’ll be able to edit the Rule at any time after it’s created.
Leave a comment (optional) Comment
Cancel Accept & Activate Rule
ADÉ recommends a rule, with the hunt that tested it The agent starts where the team finds the threat One click beside the verdict starts a job, and the job page shows each step ADÉ does.
User Reports Action required: payroll profile verification Action required: payroll profile verification
From Payroll Operations <payroll-verify@employee-benefits.co>To alex.morgan@acme.com
Executive Summary This message impersonates Payroll Operations and urges the recipient to verify their payroll profile through an unfamiliar domain. The sender fails DMARC, does not align with the organization’s trusted HR infrastructure, and uses credential-harvesting language under the pretext of an upcoming pay cycle.
Matched Detection Rules (0)
No Detection Rules matched this message group.
Message Content
User View Text View HTML View EML View
CAUTION: This message originated outside of your organization.
From: Payroll Operations <payroll-verify@employee-benefits.co>
Action required
Your payroll profile requires verification before the next pay cycle. Review and confirm your direct deposit details to avoid a delay in payment.
Review Status
Review Status ⚠ Unreviewed
ADÉ (Autonomous Detection Engineer)
ADÉ recommends new Detection Rules for malicious, spam, or graymail messages that do not match any Detection Rules. One click starts ADÉ
In Progress Started on July 3, 2026 at 2:12 PM Started by Patrick MorganView Report ADÉ waits on the same page as the verdict Each rule shows what it would catch before it goes live ADÉ runs each rule on the last 14 days of email and shows what it catches and wrongly blocks.
Agents ADÉ Action required: payroll profile verification Action required: payroll profile verification
Completed in 48mJob ID: 019f3d5a-ff42-7706-b615-a83297b00479 ADÉ auto-accepted and activated the recommended ruleJul 3, 2026, 3:00 PM
Rule Detail Credential phishing: payroll QR code lure with newly registered domain Flagged Message View Flagged Messages ADÉ Recommended Rule
99% match in a 14-day hunt, with 40 malicious matches and 2 possible false positives.
Accept Reject
Rule Name Credential phishing: payroll QR code lure with newly registered domain
Severity High Severity
Description Detects inbound payroll-themed messages that contain QR-code links to newly registered credential-harvesting domains.
Labels Credential Phishing QR code Social engineering
Rule MQL 1 type .inbound 2 and any (attachments ,3 .file_extension in~ ("png" , "jpg" , "jpeg" , "pdf" ) 4 and any (file.explode (.), 5 .scan.qr.type == "url" 6 and ml.link_analysis (.scan.qr.data ).credphish.disposition == "phishing" 7 ) 8 ) 9 and any (ml.nlu_classifier (body.current_thread.text ).intents ,10 .name in ("payroll" , "credential_theft" ) 11 and .confidence in ("medium" , "high" ) 12 ) 13 and network.whois (sender.email.domain ).days_old <= 45
ADÉ hunted across 14 days and found 0 message groups (0 total messages)
Recommended Rule is a 0% match with 0 malicious matches and may introduce 0 false positives (Benign). It meets the threshold to auto-accept the Rule.0 Malicious0 Spam0 BenignSubject Sender Received ASA Verdict
Action required: payroll profile verification payroll-security@adp-verify.com Jul 2 MaliciousNew direct deposit document shared with you hr-notify@payroll-docs.co Jul 1 MaliciousReminder: update your payroll information benefits@company-payroll-support.net Jun 29 BenignShowing 3 of 43 message groups
ADÉ worked for 48m
Collaborated with ASA Agent to generate a threat report Validated recommendation with 1 huntPatrick Morgan triggered ADÉ at Jul 3, 2026, 2:12 PM
Subject Action required: payroll profile verification Sender payroll-verify@employee-benefits.co Recipient alex.morgan@acme.com ASA Verdict MaliciousWith automation on, the rule arrives with its hunt result Each team decides how much the agent does alone A team sets when ADÉ starts a job and the test score a rule needs to go live.
Agents ADÉ ADÉ Automation ADÉ Automation
Automatically run ADÉ and accept generated rules when validation meets your threshold.
Author Sublime Security
Status InactiveConfigure ADÉ Jobs
Choose, by verdict, when ADÉ starts on its own and when it accepts the rule it writes.
Verdict Auto-start ADÉ job Alerts Rule auto-acceptance threshold
MaliciousNo Alert Require review SpamNo Alert Require review GraymailNo Alert Require review At first, ADÉ runs only when someone starts it Missed threats now get a rule in under 2 hours A fix that took an engineer days or weeks now arrives as a rule ready to accept.
Agents ADÉ ADÉ (Autonomous Detection Engineer)
Creates detections tailored to your environment.
Go to Settings Performance (Last 30 days)
Jobs
All recommendation statuses Message Subject ASA Verdict Started By Started Report Status Recommendation Status
Invoice payment confirmation required today MaliciousADÉ 9h ago In Progress— Benefits enrollment form from rare sender GraymailADÉ 18h ago Completed Auto-AcceptedDocuSign: updated employee handbook signature request SpamAJ Williams 1d ago Completed AcceptedAction required: payroll profile verification MaliciousADÉ 1d ago Completed Needs ReviewCalendar invite with external benefits link SpamAJ Williams 1d ago Completed RejectedUrgent wire transfer details for review MaliciousADÉ 2d ago Completed Auto-AcceptedShared voicemail transcript is ready GraymailFatima Al-Sayed 12d ago Completed AcceptedPayroll QR credential harvest report MaliciousADÉ 15d ago Completed Auto-AcceptedADÉ’s page: the time to cover a missed threat, and the jobs behind it