AI systems foundations · Lesson 1 of 15 · 5 min

Map an AI application

An AI application is a chain of components, not just a model. Trace the request from input validation through retrieval, inference and response checks; each hop can fail independently.

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-systems-foundations-001.json. Separate the recorded facts from your assumptions.
Hint & worked example
An AI application is a chain of components, not just a model. Trace the request from input validation through retrieval, inference and response checks; each hop can fail independently.
The complete case JSON is read successfully.
```
cat /opt/ai-lab/cases/aiops-systems-foundations-001.json
```
Common mistake to avoid: A ready model proves that every component is healthy.
2
Isolate the deciding signal
Select the unhealthy_component field from the case JSON. What does it establish—and what does it not establish?
Hint & worked example
Inspect the retriever before changing the healthy model runtime.
A successful JSON query isolates unhealthy_component.
```
jq .unhealthy_component /opt/ai-lab/cases/aiops-systems-foundations-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: inspect-retriever, change-without-evidence, or ignore-the-signal. Save that one code followed by a newline in /home/learner/lab/aiops-systems-foundations-001-decision.txt.
Hint & worked example
Inspect the retriever before changing the healthy model runtime.
The decision artifact contains the correct code, not just a matching command in history.
```
printf '%s\n' 'inspect-retriever' > /home/learner/lab/aiops-systems-foundations-001-decision.txt
```
Common mistake to avoid: A ready model proves that every component is healthy.

Understand the pattern

An AI application is a chain of components, not just a model. Trace the request from input validation through retrieval, inference and response checks; each hop can fail independently.

Interpret the evidence

Inspect the retriever before changing the healthy model runtime.

A tempting mistake

A ready model proves that every component is healthy.

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-systems-foundations-001.json

{
  "fixture": "Fictional training data; not a live measurement.",
  "path": [
    "gateway",
    "retriever",
    "runtime",
    "validator"
  ],
  "unhealthy_component": "retriever",
  "runtime_status": "ready"
}

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

$ jq .unhealthy_component /opt/ai-lab/cases/aiops-systems-foundations-001.json

"retriever"

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

$ printf '%s\n' 'inspect-retriever' > /home/learner/lab/aiops-systems-foundations-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 “inspect-retriever” to stop being the justified action. Do not silently replace missing evidence with a guess.

Explain it

What does the evidence in “Map an AI application” justify?A ready model proves that every component is healthy.Make the change now and gather the missing evidence afterward.Inspect the retriever before changing the healthy model runtime.

Apply it elsewhere

A colleague concludes: “A ready model proves that every component is healthy.” 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: Separate model and application 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