Map the AI System

A support-agent deployment is live and nobody has an inventory of it. Walk it end to end and record which model, whose prompt, which corpus and which tool token are in play, and where the trust boundaries actually sit.

Foundational · First contact with the concept — the evidence points at the answer.

Outcome · Produce an asset, trust-boundary, identity, data and tool map of a live AI application.

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

George · 5 lines

Roles

• AI security engineer

• Security architect

Standards mapping

NICE T0177, T0473

ATLAS AML.T0002

OWASP LLM03

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: map-the-ai-system
release: 1.0.0
mode: ai-lab
maturity: 2
roles:
  - ai-security-engineer
  - security-architect
outcomes:
  niceTasks:
    - T0177
    - T0473
  atlasTechniques:
    - AML.T0002
  owaspRisks:
    - LLM03
aiAssets:
  models:
    - support-agent-model@2026.06
  prompts:
    - map-the-ai-system-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: map-the-ai-system-seed-1
  injects:
    - map-the-ai-system-inject-1
telemetry:
  requiredSignals:
    - ai.trace
    - rag.retrieval
    - tool.call
    - identity.auth
    - dlp.egress
    - siem.alert
evaluation:
  deterministicChecks:
    - map-the-ai-system-checks
  repeatedTrials: 20
  maliciousSuite: map-the-ai-system-attack-v1
  benignSuite: support-utility-v4
safety:
  networkEgress: deny
  maxTokens: 250000
  maxCostUsd: 20