R1 — The Range Without AI

This is the control case for the whole suite, run with no inference at all. Work the lab on authored dialog and deterministic evidence rules, and prove it is complete and assessable before any model is added.

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

Outcome · Work a full identity incident, and grade it, with no model anywhere in the loop.

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

George · 5 lines

Roles

• SOC analyst

• Incident responder

Standards mapping

NICE T0258, T0166

ATLAS AML.T0057

OWASP 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: runtime-baseline-no-ai
release: 1.0.0
mode: ai-lab
maturity: 1
roles:
  - soc-analyst
  - incident-responder
outcomes:
  niceTasks:
    - T0258
    - T0166
  atlasTechniques:
    - AML.T0057
  owaspRisks:
    - LLM09
aiAssets:
  models:
    - support-agent-model@2026.06
  prompts:
    - runtime-baseline-no-ai-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: runtime-baseline-no-ai-seed-1
  injects:
    - runtime-baseline-no-ai-inject-1
telemetry:
  requiredSignals:
    - ai.trace
    - rag.retrieval
    - tool.call
    - identity.auth
    - dlp.egress
    - siem.alert
evaluation:
  deterministicChecks:
    - runtime-baseline-no-ai-checks
  repeatedTrials: 20
  maliciousSuite: runtime-baseline-no-ai-attack-v1
  benignSuite: support-utility-v4
safety:
  networkEgress: deny
  maxTokens: 250000
  maxCostUsd: 20