Safety, privacy, and governance · Lesson 1 of 15 · 9 min

Inspect guardrail policy

A guardrail policy names risks, checks and escalation boundaries. A policy document is not proof that those controls are actually enabled in the serving path.

Open the lab Course map

Mastery 0/3Run itExplain itApply it

learner@clairos:~ $

↑ history · Tab complete · Ctrl+C cancel · Esc, Tab to leaveExit 0

Your objectives

Hints are always available. Wrong turns never cost XP.

1
Read the case evidence
Read /opt/ai-lab/cases/aiops-safety-governance-001.json. Separate the recorded facts from your assumptions.
Hint & worked example
A guardrail policy names risks, checks and escalation boundaries. A policy document is not proof that those controls are actually enabled in the serving path.
The complete case JSON is read successfully.
```
cat /opt/ai-lab/cases/aiops-safety-governance-001.json
```
Common mistake to avoid: Written policy proves enforcement even when the control is disabled.
2
Isolate the deciding signal
Select the runtime_redaction_enabled field from the case JSON. What does it establish—and what does it not establish?
Hint & worked example
Resolve the disabled runtime redaction control before treating the policy as enforced.
A successful JSON query isolates runtime_redaction_enabled.
```
jq .runtime_redaction_enabled /opt/ai-lab/cases/aiops-safety-governance-001.json
```
Common mistake to avoid: Using a different case or an unrelated signal as the justification.
3
Record your operational decision
Choose the justified code: restore-redaction-control, change-without-evidence, or ignore-the-signal. Save that one code followed by a newline in /home/learner/lab/aiops-safety-governance-001-decision.txt.
Hint & worked example
Resolve the disabled runtime redaction control before treating the policy as enforced.
The decision artifact contains the correct code, not just a matching command in history.
```
printf '%s\n' 'restore-redaction-control' > /home/learner/lab/aiops-safety-governance-001-decision.txt
```
Common mistake to avoid: Written policy proves enforcement even when the control is disabled.

Understand the pattern

A guardrail policy names risks, checks and escalation boundaries. A policy document is not proof that those controls are actually enabled in the serving path.

Interpret the evidence

Resolve the disabled runtime redaction control before treating the policy as enforced.

A tempting mistake

Written policy proves enforcement even when the control is disabled.

All names, measurements, prices, versions, and thresholds in this exercise are fictional training data. The evidence supports this bounded scenario, not a claim about a live provider.

Worked example and expected result

$ cat /opt/ai-lab/cases/aiops-safety-governance-001.json

{
  "fixture": "Fictional training data; not a live measurement.",
  "policy_requires_redaction": true,
  "runtime_redaction_enabled": false
}

Exit status: 0. The command completed successfully in the training fixture.

$ jq .runtime_redaction_enabled /opt/ai-lab/cases/aiops-safety-governance-001.json

false

Exit status: 0. The command completed successfully in the training fixture.

$ printf '%s\n' 'restore-redaction-control' > /home/learner/lab/aiops-safety-governance-001-decision.txt

(no output; exit 0)

Exit status: 0. The command completed successfully in the training fixture.

Try a variation

Name the assumption that would have to change for “restore-redaction-control” to stop being the justified action. Do not silently replace missing evidence with a guess.

Explain it

What does the evidence in “Inspect guardrail policy” justify?Written policy proves enforcement even when the control is disabled.Make the change now and gather the missing evidence afterward.Resolve the disabled runtime redaction control before treating the policy as enforced.

Apply it elsewhere

A colleague concludes: “Written policy proves enforcement even when the control is disabled.” What should you do?Treat this fixture as a live measurement.Reject that conclusion; return to the case evidence and its stated limits.Accept it because the training command completed.

Keep the momentum.

Complete the lab, then explain and apply the pattern.

Next: Review input redaction Try an incident drill

Anonymous lesson and mastery progress lasts for this session. Sign in to keep synced lesson XP between sessions; mastery stays device-local. No speed bonus, lost lives, or hint penalties.

Keep learning

Case methodology: evidence, limits, decision