{"resourceId":"usd-agentic-ai-soc-hybrid-ops-20260911","versions":[{"version":"external-5917e24dff7b0817fd5b4f4cdc2f9c447809669cbd7621fdc3156ce45719b4da","resource":{"id":"usd-agentic-ai-soc-hybrid-ops-20260911","title":"University of South Dakota documents hybrid Agentic AI SOC with human-gated decisions","organization":"University of South Dakota Information Security / TeamDynamix KB","sector":"Higher education cybersecurity / campus SOC operations","geography":"United States (South Dakota public university)","publishedAt":"Published 2026-08-04; materially updated 2026-09-11 (KB article:modified_time)","publicationDate":"2026-09-11","eventDate":null,"sourceName":"University of South Dakota TeamDynamix knowledge base","sourceLabel":"Institutional KB describing USD Agentic AI SOC architecture and oversight","sourceUrl":"https://td.usd.edu/TDClient/33/Portal/KB/Article/10421/USD-Agentic-AI-SOC","evidenceClass":"independent-reporting","outcomeClass":"emerging","topics":["developers-agents","data-security","operating-model","infrastructure","governance-procurement"],"finding":"USD’s Security Team describes a deployed Agentic AI SOC that layers (1) USD-built agents in Microsoft Copilot Studio/AI Foundry, (2) Microsoft Sentinel/XDR/Security Copilot agents, and (3) Red Canary MDR agents. Specialist agents cover orchestration (SOOA), identity, network, vulnerability prioritization, data governance/FERPA-HIPAA-GLBA context, third-party/HECVAT reviews, and a ghost-student fraud POC. Workflows gather evidence and recommend actions, but consequential decisions—risk acceptance, software approval, disruptive containment, legal notification—remain with humans. Why now: the KB shows article:modified_time 2026-09-11 after the stream’s 2026-09-19 published edition, documenting a concrete hybrid campus SOC operating model amid agentic-attack pressure covered in prior issues.","sledRelevance":"Campus-operations cyber evidence of an agent-augmented SOC with explicit human approval gates, vendor MDR co-management, and compliance-aware specialist agents—transferable to thin higher-ed SOCs evaluating Security Copilot/MDR stacks.","evidence":"Primary institutional HTTPS KB page enumerating agent inventory, orchestration pattern, Red Canary/Microsoft layers, and human-oversight prohibitions. No MTTD/MTTR, false-positive rates, or independent audit metrics are published.","architectureImplications":"Design campus SOCs as multi-layer agent fabrics (institution-specific agents + native cloud security agents + MDR) coordinated by an orchestration agent, with Sentinel/data-lake evidence correlation and tool permissions scoped per specialty rather than one general chatbot.","governanceImplications":"Codify which agent outputs are decision-support versus authoritative; require human approval for risk acceptance, exceptions, disruptive containment, and public statements; document agent contributions in tickets for auditability.","securityPrivacyImplications":"Minimum-necessary data, least-privilege agent identities, no secrets in prompts, and retention of agent output in approved systems; DGSA maps FERPA/HIPAA/GLBA/PCI to incidents—still depends on correct classification and human validation.","caveats":"Operator-authored KB, not an independent evaluation. Publication originally 2026-08-04 with Sept 11 modification; effectiveness metrics absent. Transferability assumes Microsoft + MDR contracting and staff capacity to validate agent output.","streamIds":["campus-operations"],"roles":{"sales":"Campus CISOs need SOC capacity without claiming agents replace analysts. USD’s story is a hybrid Microsoft+MDR agent fabric with explicit human gates on consequential actions—not a proven MTTD cut. Use specialist-agent and orchestration detail as a discovery scaffold for thin SOCs; bound value to faster evidence assembly under human command. Do not sell unsupervised containment or guaranteed alert reduction from this KB alone.","engineering":"Pre-sales should map orchestration plus specialty agents (identity, network, vuln, data-governance, TPRM) onto Sentinel/XDR and MDR evidence planes. Prerequisites: identity for agent service principals, data classification, HECVAT workflow hooks, and approval workflows for disruptive actions. Constraints: source omits measured detection outcomes. Proof of value is human-gated playbooks with logged agent contributions—not a demo chat.","delivery":"Delivery stands up agent identities/permissions, orchestration routing, ticket templates that capture agent evidence, and co-managed MDR runbooks. Ownership: CISO/SOC lead with IAM, network, and compliance partners. Train analysts to validate and escalate. Acceptance criteria: documented human-approval matrix, agent permission reviews, and sample tickets showing evidence-backed recommendations. Risks: over-trust in agent risk scores and permission creep."},"roleDetails":{"sales":{"customerProblem":"Thin campus SOCs face agentic-attack volume and need capacity without unsupervised automation risk.","stakeholders":["CISO","SOC manager","CIO","IAM lead","Compliance/privacy","MDR provider"],"discoveryQuestions":["Which consequential actions are hard-blocked from agent execution today?","Is MDR already co-managing detections with campus analysts?","Can tickets show which agent produced each finding?","Which data classes may agents query under FERPA/HIPAA/GLBA?"],"valueHypothesis":"A hybrid agent-augmented SOC can expand investigative reach while keeping risk acceptance human-owned, as USD describes—without measured MTTD/MTTR in this source.","potentialEngagement":"Bounded discovery workshop to map agent specialties, approval matrix, and MDR integration against the campus tool stack.","unsupportedClaims":["Guaranteed percentage reduction in alert volume or MTTR","Agents safely replace SOC headcount","Ghost-student fraud agent accuracy (POC only)"]},"engineering":{"fit":"Fit for Microsoft-centric campuses with MDR already or planned; weaker fit if SOC lacks identity/data-classification foundations.","architectureIntegration":"Orchestration agent coordinating specialty agents over Sentinel data lake, Defender/Entra/Purview native agents, Cisco network telemetry, and MDR timelines.","prerequisites":["Sentinel or equivalent SIEM with usable data lake","Managed agent identities and least-privilege plugins","Documented data classification and owners","Ticket system able to retain agent outputs"],"constraints":["No published detection-performance metrics","Microsoft/Red Canary feature names change","Jurisdictional privacy rules still require human legal judgment"],"security":"Enforce min-necessary data, no secrets in prompts, human approval for disruptive changes, and periodic agent permission reviews.","proofOfValue":["Sample incidents where agent evidence was validated against logs","Approval matrix exercised for a containment action","Vendor assessment ticket completed with TPRM agent assist under human sign-off"]},"delivery":{"work":"Configure agents, orchestration, MDR handoffs, analyst validation SOPs, and audit logging of agent contributions.","dependencies":["IAM","Network security","Data governance","MDR contract","ITSM/TeamDynamix"],"ownership":"CISO/Security Operations owns the Agentic SOC; system/data owners remain accountable for their assets.","skillsAdoption":"Train analysts to treat agent output as decision-support, verify against authoritative telemetry, and escalate conflicts.","governanceCheckpoints":["Agent permission and prompt review cadence","Change-control for new agent actions","Compliance review of DGSA escalation paths"],"acceptanceCriteria":["Written list of actions agents may not take unilaterally","At least one end-to-end ticket with correlated multi-agent evidence","Documented MDR escalation path with campus final authority"],"risks":["Analyst over-reliance on agent risk scores","Permission creep across specialty agents","Shadow use of consumer AI for investigations"]}},"retrievedAt":"2026-09-21T22:06:05-05:00","enrichedAt":"2026-09-21T22:08:00-05:00","enrichmentBasis":"retrieved source","accessibilityWorkforceImplications":"Agents are framed as expanding analyst capacity and reducing repetitive work without replacing Security Team accountability; staff must still review tickets and report inaccurate agent recommendations—implying verification labor and training.","procurementImplications":"Stack spans Microsoft Security Copilot/XDR/Sentinel, Cisco XDR, and Red Canary MDR; procurement must cover agent permissions, data residency claims (Red Canary asserts customer data stays in its infrastructure and is not used to train external models), and co-managed escalation paths.","operatingModelImplications":"Hybrid co-managed SOC: retain strategy/incident command internally, buy scale/MDR externally, automate repeatable analysis with agents. IT staff will see agent-generated summaries in TeamDynamix and must treat them as Security Team work product subject to validation.","sourceVerification":{"openedUrl":"https://td.usd.edu/TDClient/33/Portal/KB/Article/10421/USD-Agentic-AI-SOC","referenceExcerpt":"The USD Security Team retains strategic control, institutional knowledge, incident leadership, and final decision-making.","promptVersion":"sled-research-v4.0","model":null,"basis":"agent-reported inspection"}}}]}