Safety, privacy, and governance · Lesson 2 of 15 · 5 min

Review input redaction

Input redaction limits sensitive data sent to a model or logged by an application. Verify the resulting payload rather than assuming that a redaction switch caught every field.

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-002.json. Separate the recorded facts from your assumptions.
Hint & worked example
Input redaction limits sensitive data sent to a model or logged by an application. Verify the resulting payload rather than assuming that a redaction switch caught every field.
The complete case JSON is read successfully.
```
cat /opt/ai-lab/cases/aiops-safety-governance-002.json
```
Common mistake to avoid: Removing the API token guarantees that no sensitive data remains.
2
Isolate the deciding signal
Select the sensitive_remaining field from the case JSON. What does it establish—and what does it not establish?
Hint & worked example
Review and redact the remaining email field according to the intended boundary.
A successful JSON query isolates sensitive_remaining.
```
jq .sensitive_remaining /opt/ai-lab/cases/aiops-safety-governance-002.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: redact-remaining-email, change-without-evidence, or ignore-the-signal. Save that one code followed by a newline in /home/learner/lab/aiops-safety-governance-002-decision.txt.
Hint & worked example
Review and redact the remaining email field according to the intended boundary.
The decision artifact contains the correct code, not just a matching command in history.
```
printf '%s\n' 'redact-remaining-email' > /home/learner/lab/aiops-safety-governance-002-decision.txt
```
Common mistake to avoid: Removing the API token guarantees that no sensitive data remains.

Understand the pattern

Input redaction limits sensitive data sent to a model or logged by an application. Verify the resulting payload rather than assuming that a redaction switch caught every field.

Interpret the evidence

Review and redact the remaining email field according to the intended boundary.

A tempting mistake

Removing the API token guarantees that no sensitive data remains.

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-002.json

{
  "fixture": "Fictional training data; not a live measurement.",
  "raw_fields": [
    "question",
    "email",
    "api_token"
  ],
  "outgoing_fields": [
    "question",
    "email"
  ],
  "sensitive_remaining": [
    "email"
  ]
}

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

$ jq .sensitive_remaining /opt/ai-lab/cases/aiops-safety-governance-002.json

[
  "email"
]

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

$ printf '%s\n' 'redact-remaining-email' > /home/learner/lab/aiops-safety-governance-002-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 “redact-remaining-email” to stop being the justified action. Do not silently replace missing evidence with a guess.

Explain it

What does the evidence in “Review input redaction” justify?Make the change now and gather the missing evidence afterward.Review and redact the remaining email field according to the intended boundary.Removing the API token guarantees that no sensitive data remains.

Apply it elsewhere

A colleague concludes: “Removing the API token guarantees that no sensitive data remains.” What should you do?Reject that conclusion; return to the case evidence and its stated limits.Accept it because the training command completed.Treat this fixture as a live measurement.

Keep the momentum.

Complete the lab, then explain and apply the pattern.

Next: Review output 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