← Unovie.AI
Technical Whitepaper · AI SOC Modernization

Modernizing the SOC for the Agentic Era: Edge-Native, Identity-Driven Security for Distributed IT/OT

For CISOs who run security across many sites and both IT and OT. Why the cloud SIEM model breaks now that AI agents are on both sides of an attack, and how a security operations center that runs on site keeps detection and response under your control.

Abstract

For twenty years the Security Operations Center moved toward one model: send all the logs to a cloud SIEM and let a managed service watch them. That model assumed two things. Data could leave the site, and attacks were run by people. Neither is true any more. AI agents now act on both sides. Your teams use them to run operations, and attackers use them to automate attacks. Sites that mix IT and OT also cannot send large, sensitive data streams to a cloud that charges by the query.

This paper makes the case for an AI SOC that runs on site. It spots threats as data arrives and learns from your own environment. A knowledge graph links each alert to the people, systems and devices it touches, so you can see how far an attack could spread. Every person, service and AI agent gets its own identity and limits, whether the site is connected or air-gapped. Response keeps working when the network link drops, and your data stays on site.

1The 2025+ inflection: agents everywhere

The SOC has been climbing the same ladder for twenty years. In 2025 the ladder ended, and the ground changed.

Each rung added capability to a fundamentally reactive posture: the network operations center became a security operations center; rules gained machine-learning assists; threat intelligence enriched alerts; and SOAR automated the runbooks. Useful, incremental, human-paced. The 2025+ inflection is not another rung — it is a change in who acts. Agents are now on both sides of the wire. Adversaries automate reconnaissance, exploitation and lateral movement at machine speed; defenders deploy their own agents to triage, hunt and remediate. The volume, velocity and autonomy of action all step up at once.

BEFORE 2025 — INCREMENTAL, REACTIVE NOC SOC + AI / ML + ThreatIntel + SOAR 2025+ — AGENTS EVERYWHERE agent agent agent agent agent agent agentic threats · agentic defenders
Figure 1 — Two decades of incremental, reactive evolution meet an inflection: action becomes autonomous and bidirectional. The SOC must defend at machine speed against — and with — agents.
The shift

The SOC's job is no longer to collect logs and correlate them later. It is to reason over relationships in the ingestion path, act autonomously within guardrails, and govern an estate where humans, services and agents all take actions that must be attributed.

2Why the cloud-SIEM model breaks for IT/OT

The 2022–2025 reference design was a cloud-SIEM, managed-service model: ship everything to a regional SIEM, correlate centrally, bill per query. For a distributed IT/OT enterprise that model now works against you.

Assumption of the cloud-SIEM modelReality for distributed IT/OT in 2026+
Telemetry can leave the siteOT, IoMT, video and process data are large, sensitive and often regulated — egress is a data-exfil and compliance risk
Cost scales gracefullyCloud-SIEM fees recur on every event and query; agentic volume multiplies them without a ceiling
The link is always upPlants, depots, substations and vehicles operate through outages; a cloud round-trip stalls incident response
Generic detections are enoughVendor rules miss your environment; OT protocols and device behavior need locally-learned models
Detection is a search problemAt machine speed, delayed search and scheduled correlation are too late — detection must happen at ingest

The OT estate compounds every one of these: long-lived devices, brittle protocols, safety constraints, no patch window, and air-gapped or intermittently-connected enclaves where a cloud dependency is simply unavailable. A modern SOC for this world has to run where the data is born.

3From 20 tools to four cognitive platforms

The traditional SOC is twenty fragmented tools, each a console and a silo. The modern architecture consolidates them into four cognitive platforms feeding a single reasoning core that takes autonomous action.

TELEMETRY COGNITIVE PLATFORMS REASONING CORE AUTONOMOUS ACTION Cloud & workloads Code & pipelines Endpoints & network Identity &IT/OT assets Unified Cloud & Workload FabricCSPM · CWPP · CASB · Containers · Registry Intent-Driven DevSecOps CopilotShift-left · SAST · DAST · SCA · SDLC Autonomous Cyber Ops · XDR/SOARSIEM · SOAR · EDR · MITRE · IR Dynamic Identity & Asset IntelCMDB · IDAM · MEC · FHIR · NIST Self-learning reasoning core learns on site, every change tested on owned silicon Remediation-as-Codetested, auto PRs Blast-radius containmentgraph-traced isolation Adaptive policycontext-aware Compliance evidencecontinuous proof RUNS ON-SITE · NVIDIA JETSON AGX THOR · 128 GB UNIFIED · BLACKWELL · NO CLOUD
Figure 2 — The 2026++ SOC. Four telemetry domains feed four cognitive platforms, which feed one self-learning reasoning core that drives four autonomous actions — entirely on owned silicon, with no cloud dependency.

Each legacy control does not disappear; it is absorbed into a platform and made cognitive. The point is consolidation of data flows, not just consoles:

ControlWhat it wasWhat the reasoning core makes it
CSPMFinds cloud misconfig & driftGenerates and tests infrastructure-as-code PRs to auto-close drift
SIEMCentralized log search & retentionCorrelates events as a graph, not sequential log scans
SOARHard-coded mitigation playbooksPlaybooks reason over live topology instead of static scripts
EDREndpoint detect & remediateExplains endpoint anomalies and auto-scopes remediation
MITRE ATT&CKManual tactic mappingAuto-maps detections to adversary tactics in real time
MEC (edge)Compute at the network edgeCompiles hyper-local models that detect anomalies at the edge
IDAMIdentity, RBAC, MFAAdapts access policy to user, service and agent context in real time

4The self-learning, edge-native SOC analyst

The core of a modern SOC is a model that reasons over events as they arrive and learns from your own environment. It runs entirely on site.

Detection happens in the ingestion path, on the GPU, while events are still moving. Each event is classified and enriched before it is stored, by a small model trained for the job instead of long chains of hand-written rules. That means threats are flagged in seconds, not found later by a scheduled search.

The model also learns your environment over time. The hard part is learning without drifting, so that a change never makes detection worse. The safe rule is simple: no change goes live until it has proven itself on cases it has never seen, and every change can be undone.

What this means for you

Detection gets better on your attacks, on site. Each change is tested before it goes live and can be rolled back. Your data never leaves the boundary.

Throughput figures, the detection pipeline and how Unovie's learning loop works are covered in our technical brief. Want to see how Unovie does this in practice? talk to our engineers.

5From alerts to a knowledge graph

Isolated alerts hide multi-stage attacks. A knowledge graph models the enterprise as a web of relationships, so a low-severity signal can be traced to its true blast radius.

Identityuser · service · agent Endpoint Workloadcontainer / pod Edge nodeIT / OT Vulnerabilityexposed CVE ownstalks toruns onexposes AI traces blast radiusacross the relationships
Figure 3 — Relationship semantic context. When a low-severity anomaly fires on a workload, the core queries the graph — who owns the identity, what it talks to, where it runs, what it exposes — and traces the blast radius to catch the multi-stage attack the isolated alert would have missed.

6The identity-driven core

Distributed IT/OT and agentic workloads share one root requirement: every actor needs a verifiable identity and a scoped policy — whether the site is connected or air-gapped. That is the job of a thin identity edge.

Rather than operate a heavy identity provider at every site, the architecture uses a thin authentication edge (an OAuth2/OIDC proxy with server-side sessions and edge RBAC) that delegates identity to the right issuer and injects a consistent identity context downstream. One pluggable setting selects the issuer; everything behind it stays identity-agnostic.

Connected sitesAir-gapped / disconnected enclaves
IssuerThe enterprise IdP — SSO, MFA and lifecycle stay where they already live; no local IdP to runA self-contained on-prem OIDC issuer with its own user/group store — no external database, no cloud reach
EdgeSame thin proxy; same server-side sessions; same RBAC on a roles claim; downstream services receive identity via standard headers
SwitchOne pluggable issuer setting — applications and the SOC never change
Identity-driven core

A portable identity edge gives humans, services and agents one scoped identity model across the whole distributed estate — connected or air-gapped — and becomes the control point the SOC and the gateway both reason over.

7Governing agentic workloads

Agents are a new class of actor. They act on behalf of users, call tools, read sensitive data and spawn sub-agents — at machine speed. Each action must carry an identity, a scoped credential, a policy and an audit trail.

This is where identity, the gateway and the SOC meet. The GPU EdgeGateway governs the agent's traffic: it routes each request to the right model on owned silicon, runs tools and code in policy-governed sandboxes (no unauthorized file, credential or network access), checks for sensitive-data leakage and prompt injection inline, and meters every call. The AI SOC governs the agent's behavior: it watches agent actions the way UEBA watches users, and uses the knowledge graph to bound what a compromised or misbehaving agent can reach.

Agentic riskControl
An agent acts with no attributable identityIdentity-driven core issues a scoped identity per agent and human-on-behalf-of relationship
An agent over-reaches its tools or dataEdgeGateway sandboxes tools/code and enforces policy-as-code on every call
A prompt injection or leak rides the requestInline safety classifiers (PII, jailbreak, injection) on every turn at the gateway
A compromised agent moves laterallyAISOC traces blast radius on the graph and contains by relationship
Spend and action go unauditedEvery route metered and attributed; every action logged for review

8The Unovie offering: EdgeGateway + AISOC

Unovie delivers this architecture as two offerings bound by the identity-driven core, all on Unovie's custom-built hardware accelerators.

GPU EdgeGateway — govern the agentic AI

A gateway for all AI agent traffic. It sends each request to the right model, local where possible. It runs agent tools in a locked-down space and checks every policy change before it goes live. It is also where each agent's identity and limits are enforced.

AI SOC (AISOC) — detect and respond on your floor

Security operations that run on your site. It flags threats as data arrives and uses a knowledge graph to show how far an attack could spread. It learns from your own environment, and it can act within limits you set: proposing fixes, isolating affected systems and keeping compliance evidence up to date. Telemetry never leaves the site.

Want the detail? How these pieces are built and how they fit with the rest of Unovie's platform is something our engineers can walk you through: talk to our engineers.

9Deployment for the distributed enterprise

  1. An edge SOC node per site. Place a Blackwell-class node (Jetson AGX Thor / DGX Spark) where the data is — plant, depot, substation, clinic, vehicle bay — running detection-at-ingest and the reasoning core locally.
  2. One pipeline for IT and OT. IT telemetry (logs, identity, network, cloud) and OT/device telemetry land on the same local pipeline, so anomalies on the floor are correlated beside IT threats.
  3. Connected or air-gapped, same design. The identity edge points at the enterprise IdP where connected and a self-contained issuer where isolated; nothing downstream changes.
  4. Local autonomy, central correlation. Each node detects and responds on its own; a thin central layer correlates across sites without ever pulling raw telemetry off-site — only enriched, scoped findings travel.
  5. Govern agents through the gateway. All agentic AI traffic flows through EdgeGateway for routing, sandboxing, safety and metering.
  6. Own the model, not a subscription. Capacity is owned silicon; marginal cost approaches electricity; there is no per-query SIEM meter and no egress bill.
100%
On-site — telemetry never leaves the boundary
$0/query
No recurring cloud-SIEM or per-event fees
24/7
Detection & response survive link and provider outages
Local
Detections learn from your own environment

10Governance, compliance & reversibility

Owning the detection and inference path is the strongest governance posture available to a distributed enterprise. Sensitive IT/OT and regulated data never leaves the site, so data-exfil and cross-border transfer risk are removed at the source. Controls map continuously to frameworks — NIST guidelines, sector standards such as FHIR for health data — producing continuous compliance evidence rather than point-in-time audits. No change to the detection model goes live until it has proven itself on cases it has never seen, and every change can be undone. A cloud detection set, by contrast, changes on the vendor's schedule. A live asset inventory (CMDB) tracks device firmware, end-of-life and protocol risk across the IT/OT estate, and the knowledge graph keeps identity, asset and vulnerability context joined.

Capability without exposure. Hard problems still reach a large on-prem model, and the rare request that genuinely needs a frontier model can take that path by explicit, attributed exception through the gateway — so you keep the ceiling while keeping the data home.

11Recommendations for the CISO


12References

  1. Thin authentication edge pattern. OAuth2/OIDC proxy with server-side sessions and edge RBAC; pluggable issuer — enterprise IdP (connected) or a self-contained on-prem OIDC issuer (air-gapped); identity-agnostic downstream.
  2. MITRE ATT&CK. Adversary tactics & techniques mapping used for real-time detection-to-tactic correlation.
  3. NIST guidance (incl. SP 800-190, container/IoT security) and sector standards (e.g., FHIR for health data interoperability). Continuous control mapping for compliance evidence.
  4. NVIDIA. Jetson AGX Thor & DGX Spark (Blackwell). On-site, 128 GB unified memory: the owned-silicon target for edge SOC nodes.