CYBRARY Read the Trace
A single agent run has been fully instrumented, start to finish. Follow one user sentence through policy, retrieval, the model call, the tool broker and the CRM write, and explain exactly why the agent did what it did.
Foundational · First contact with the concept — the evidence points at the answer.
Outcome · Reconstruct an AI action from prompts, retrieval, tool calls and enterprise logs.
AI connection
This activity runs entirely on the deterministic runtime. Optional live-model runtimes only affect dialog, coaching and wording — never checks or scoring.
Nothing leaves the browser session.
Prompts never leave the learner's machine.
Lab prompts reach the learner's chosen provider only.
Customer tenancy; Cybrary sees metadata only.
Cybrary AI gateway; retention off by default.
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: read-the-trace
release: 1.0.0
mode: ai-lab
maturity: 2
roles:
- soc-analyst
- ai-security-engineer
outcomes:
niceTasks:
- T0258
- T0166
atlasTechniques:
- AML.T0057
owaspRisks:
- LLM09
aiAssets:
models:
- support-agent-model@2026.06
prompts:
- read-the-trace-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: read-the-trace-seed-1
injects:
- read-the-trace-inject-1
telemetry:
requiredSignals:
- ai.trace
- rag.retrieval
- tool.call
- identity.auth
- dlp.egress
- siem.alert
evaluation:
deterministicChecks:
- read-the-trace-checks
repeatedTrials: 20
maliciousSuite: read-the-trace-attack-v1
benignSuite: support-utility-v4
safety:
networkEgress: deny
maxTokens: 250000
maxCostUsd: 20