Measure whether the CLI LLM summarizer works

Translate the claim into assertions or a tiny eval harness. The metric to protect is: contract-test pass rate, latency, retry count, output length. Always record the denominator (how many cases) beside any rate. A percentage without a denominator is marketing, not measurement.

function parse(r){const t=r?.choices?.[0]?.message?.content;if(typeof t!=='string'||!t.trim()) throw new Error('invalid response');return t.trim();}
console.log(parse({choices:[{message:{content:' Ready. '}}]}));

Expected evidence: unreliable LLM API call. A passing assertion proves only the behavior it names; broader usefulness still needs the chapter’s full limits.

Be explicit: beating the baseline (offline fake transport producing a fixed summary) on this fixture does not prove behavior under missing choices array treated as empty success, or retries on 400. Label observations separately from conclusions so the next page inherits honest evidence about the CLI LLM summarizer.

Compute contract-test pass rate, latency, retry count, output length with the denominator written beside the rate every time. For this chapter, the evaluation set is intentionally tiny; that is allowed only if you say so in the evidence. Compare against offline fake transport producing a fixed summary before celebrating.

Add one negative case aimed at missing choices array treated as empty success, or retries on 400. A suite with only happy cases cannot protect the CLI LLM summarizer when the characteristic failure appears in review.

If a check is expensive or flaky, shrink it until it is deterministic on system+user job object for an embeddings definition sentence. Flaky green builds teach the team to ignore gates. Record what this page does not prove so security-ops and mastery-ship inherit honest limits.

At the evaluation stage for llm-api-hello, the job is narrower than finishing a product demo. You are creating one progressive evidence piece about system+user job object for an embeddings definition sentence that later pages inherit without redefining success. Keep that fixture small enough to inspect by hand, keep outputs copy-pasteable as text, and refuse to narrate this baseline as if it were a production SLA: offline fake transport producing a fixed summary.

For this page specifically, success looks like metrics with explicit denominators and a negative case while still centering the user decision to turn one user passage into a bounded one-sentence summary via an HTTP-shaped client. If you cannot point to a file, command, or assertion that proves that for the CLI LLM summarizer, stay on this page instead of advancing.

API: chat completions · Glossary: API key

Previous · Next

Return to the llm api hello scenario and restate what this chapter proved on page validation.mdx. Name one metric, one ownership rule, and one regression test you will keep. Explain how this page connects to the previous page without repeating earlier paragraphs. If you cannot name a falsifier, the chapter is still a story rather than a controlled practice. Write the falsifier as an observable event with a threshold.

Return to the llm api hello scenario and restate what this chapter proved on page validation.mdx. Name one metric, one ownership rule, and one regression test you will keep. Explain how this page connects to the previous page without repeating earlier paragraphs. If you cannot name a falsifier, the chapter is still a story rather than a controlled practice. Write the falsifier as an observable event with a threshold.