Prompt and configuration operations · Lesson 1 of 14 · 9 min

List prompt versions

A prompt registry separates the active revision from drafts and rollback candidates. A listed draft should not receive traffic until its rollout is deliberate.

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-prompts-config-001.json. Separate the recorded facts from your assumptions.
Hint & worked example
A prompt registry separates the active revision from drafts and rollback candidates. A listed draft should not receive traffic until its rollout is deliberate.
The complete case JSON is read successfully.
```
cat /opt/ai-lab/cases/aiops-prompts-config-001.json
```
Common mistake to avoid: The latest listed revision automatically becomes active.
2
Isolate the deciding signal
Select the active_revision field from the case JSON. What does it establish—and what does it not establish?
Hint & worked example
Treat p7 as active while p8 remains a candidate.
A successful JSON query isolates active_revision.
```
jq .active_revision /opt/ai-lab/cases/aiops-prompts-config-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: keep-p7-active, change-without-evidence, or ignore-the-signal. Save that one code followed by a newline in /home/learner/lab/aiops-prompts-config-001-decision.txt.
Hint & worked example
Treat p7 as active while p8 remains a candidate.
The decision artifact contains the correct code, not just a matching command in history.
```
printf '%s\n' 'keep-p7-active' > /home/learner/lab/aiops-prompts-config-001-decision.txt
```
Common mistake to avoid: The latest listed revision automatically becomes active.

Understand the pattern

A prompt registry separates the active revision from drafts and rollback candidates. A listed draft should not receive traffic until its rollout is deliberate.

Interpret the evidence

Treat p7 as active while p8 remains a candidate.

A tempting mistake

The latest listed revision automatically becomes active.

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-prompts-config-001.json

{
  "fixture": "Fictional training data; not a live measurement.",
  "active_revision": "p7",
  "draft_revision": "p8",
  "rollback_revision": "p6"
}

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

$ jq .active_revision /opt/ai-lab/cases/aiops-prompts-config-001.json

"p7"

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

$ printf '%s\n' 'keep-p7-active' > /home/learner/lab/aiops-prompts-config-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 “keep-p7-active” to stop being the justified action. Do not silently replace missing evidence with a guess.

Explain it

What does the evidence in “List prompt versions” justify?The latest listed revision automatically becomes active.Make the change now and gather the missing evidence afterward.Treat p7 as active while p8 remains a candidate.

Apply it elsewhere

A colleague concludes: “The latest listed revision automatically becomes active.” 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: Inspect a prompt manifest 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