R7 — Shared War Room

Five responders work one incident in mixed languages, summarizing locally on every seat. Keep a canonical event ledger that rejects the modified client, validate proposed actions against roles, and replay generated text beside the facts it claims.

Advanced · Several moving parts — expect trade-offs and a wrong turn or two.

Outcome · Hold the boundary between per-seat AI presentation and one server-authoritative shared truth.

Launch the windows desktop Open the workbench only How this is graded

George · 5 lines

Roles

• SOC lead

• Incident responder

• Threat hunter

• Communications lead

Standards mapping

NICE T0166, T0484

ATLAS AML.T0057

OWASP LLM08, LLM09

Publish gate

Manifest valid · release 1.0.0

AI connection

This activity runs entirely on the deterministic runtime. Optional live-model runtimes only affect dialog, coaching and wording — never checks or scoring.

Deterministic simulationmode 0

Nothing leaves the browser session.

Chrome built-in AImode 1

Prompts never leave the learner's machine.

Bring your own keymode 2

Lab prompts reach the learner's chosen provider only.

Organization-owned AImode 3

Customer tenancy; Cybrary sees metadata only.

Cybrary-managed AImode 4

Cybrary AI gateway; retention off by default.

Hybrid routingmode 5

Per-job — the router never sends restricted jobs off-tenant.

Lab manifest

The machine-readable release contract. Authors edit this; the console refuses to publish without checks, both regression suites and a reference solve.

schemaVersion: cybrary.ai-lab/v1
id: shared-war-room
release: 1.0.0
mode: ai-enhanced-range
maturity: 4
roles:
  - soc-lead
  - incident-responder
  - threat-hunter
  - communications-lead
outcomes:
  niceTasks:
    - T0166
    - T0484
  atlasTechniques:
    - AML.T0057
  owaspRisks:
    - LLM08
    - LLM09
aiAssets:
  models:
    - support-agent-model@2026.06
  prompts:
    - shared-war-room-system-prompt@1
  agents:
    - support-agent-orchestrator@3
  tools:
    - crm.lookup
    - ticket.update
    - email.send
    - refund.issue
  corpora:
    - support-kb@v4
enterpriseTopology: support-enterprise-v3
scenario:
  seed: shared-war-room-seed-1
  injects:
    - shared-war-room-inject-1
telemetry:
  requiredSignals:
    - ai.trace
    - rag.retrieval
    - tool.call
    - identity.auth
    - dlp.egress
    - siem.alert
evaluation:
  deterministicChecks:
    - shared-war-room-checks
  repeatedTrials: 20
  maliciousSuite: shared-war-room-attack-v1
  benignSuite: support-utility-v4
safety:
  networkEgress: deny
  maxTokens: 250000
  maxCostUsd: 20