Prompt and configuration operations · Lesson 2 of 14 · 5 min

Inspect a prompt manifest

A prompt manifest records ownership, variables and intended use. Missing metadata makes future evaluation and rollback harder even when the prompt text itself is readable.

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-002.json. Separate the recorded facts from your assumptions.
Hint & worked example
A prompt manifest records ownership, variables and intended use. Missing metadata makes future evaluation and rollback harder even when the prompt text itself is readable.
The complete case JSON is read successfully.
```
cat /opt/ai-lab/cases/aiops-prompts-config-002.json
```
Common mistake to avoid: Invent undeclared variable names and silently drop the missing ones.
2
Isolate the deciding signal
Select the variables field from the case JSON. What does it establish—and what does it not establish?
Hint & worked example
Supply the declared question and context variables before rendering this prompt.
A successful JSON query isolates variables.
```
jq .variables /opt/ai-lab/cases/aiops-prompts-config-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: validate-two-variables, change-without-evidence, or ignore-the-signal. Save that one code followed by a newline in /home/learner/lab/aiops-prompts-config-002-decision.txt.
Hint & worked example
Supply the declared question and context variables before rendering this prompt.
The decision artifact contains the correct code, not just a matching command in history.
```
printf '%s\n' 'validate-two-variables' > /home/learner/lab/aiops-prompts-config-002-decision.txt
```
Common mistake to avoid: Invent undeclared variable names and silently drop the missing ones.

Understand the pattern

A prompt manifest records ownership, variables and intended use. Missing metadata makes future evaluation and rollback harder even when the prompt text itself is readable.

Interpret the evidence

Supply the declared question and context variables before rendering this prompt.

A tempting mistake

Invent undeclared variable names and silently drop the missing ones.

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-002.json

{
  "fixture": "Fictional training data; not a live measurement.",
  "revision": "p7",
  "owner": "ops-team",
  "variables": [
    "question",
    "context"
  ],
  "purpose": "source-grounded summary"
}

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

$ jq .variables /opt/ai-lab/cases/aiops-prompts-config-002.json

[
  "question",
  "context"
]

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

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

Explain it

What does the evidence in “Inspect a prompt manifest” justify?Make the change now and gather the missing evidence afterward.Supply the declared question and context variables before rendering this prompt.Invent undeclared variable names and silently drop the missing ones.

Apply it elsewhere

A colleague concludes: “Invent undeclared variable names and silently drop the missing ones.” 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: Separate system and user input 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