PROJECT 10 / Creative production

Compare generations without moving the goalposts

Open entry · 4h estimated · six activities

Open editable workspace →Complete practice pack ↓Handbook ↓

Before you begin

Open entry; inspect the worked fixture before beginning.
A text editor/spreadsheet for the manual route. Hosted Python/Jupyter for code exercises; applicable dependencies are in requirements.txt.
For actual AI calls, a legitimate available cloud service and authorised learner credentials; no particular provider or country is mandatory.

Free original, non-accredited practice. Self-review is not independent assessment. No particular provider, payment platform or country is mandatory; use a legitimate available route or explicitly labelled manual practice.

ACTIVITY 1 / 35 MIN ESTIMATED

Freeze the source and rubric

Generation is a candidate-making step, not verification. Fix a brief and factual source before changing prompts. A more vivid sentence can score worse if it adds an unsupported price or guarantee. The supplied candidates are authored examples, not claimed model runs. Choose the factual boundary and scoring rule before comparing prompts. Inspect the supplied input before using any tool. Write the decision rules in your own words and calculate one small result independently. The reference output is an answer key for this deliberately bounded fixture, not proof of general capability. Policy for this project: Score factual grounding, required structure and prohibited claims independently. Real provider results must be labelled with date and model; no-service examples stay labelled constructed. For learners across regions underserved or excluded by mainstream providers: verify country eligibility, language, account/identity requirements, data terms, cost, quota and connectivity before choosing a cloud service. Use only legitimate available alternatives; never bypass restrictions or invent a country/account. No service access? Complete the labelled manual/fixture route without claiming a live AI run.

Worked example

SOURCE (authored fixture):
{
  "required": [
    "two sentences",
    "no invented discount"
  ],
  "candidates": [
    {
      "id": "A",
      "facts": true,
      "format": true,
      "invented_discount": false
    },
    {
      "id": "B",
      "facts": false,
      "format": true,
      "invented_discount": true
    }
  ]
}
INDEPENDENT FIXTURE TARGET:
{
  "scores": {
    "A": 3,
    "B": 1
  },
  "selected": "A"
}

Your practical task

Choose the factual boundary and scoring rule before comparing prompts.
Open input.json and expected.json from the practice pack; keep an unmodified original.
Record a manual prediction and the relevant rule before consulting the answer key.
Perform one small change and predict its effect before rerunning.
Keep the result and your reasoning in the lesson notes; do not mark a simulated run as live.

Evidence to keep

Freeze the source and rubric — a saved, inspectable artefact tied to the supplied rule.
A baseline or change-test record with expected/observed results and a limitation.

Mistakes to watch for

Give B a convincing style: its factual failure still remains.
Treating a supplied answer key, an authored example or self-review as independent field validation.

Check your understanding

Which exact input, rule and expected value would let another learner falsify your conclusion in this activity, and what remains untested?

No-service / offline route

Use the supplied fictional JSON, expected results and paper/text evidence log without a provider account. Manual or constructed completion is labelled; it is not a live cloud integration or trained-model run.

ACTIVITY 2 / 35 MIN ESTIMATED

Score two constructed candidates

Worked example

MANUAL BASELINE / compare every named field
{
  "scores": {
    "A": 3,
    "B": 1
  },
  "selected": "A"
}
Keep a separate observed-result column; the answer key is not a model response.

Your practical task

The attractive but invented offer loses on grounding.
Open input.json and expected.json from the practice pack; keep an unmodified original.
Record expected and observed values separately; explain every mismatch.
Perform one small change and predict its effect before rerunning.
Keep the result and your reasoning in the lesson notes; do not mark a simulated run as live.

Evidence to keep

Score two constructed candidates — a saved, inspectable artefact tied to the supplied rule.
A baseline or change-test record with expected/observed results and a limitation.

Mistakes to watch for

Remove the source price: do not fill it from general knowledge.
Treating a supplied answer key, an authored example or self-review as independent field validation.

Check your understanding

Which exact input, rule and expected value would let another learner falsify your conclusion in this activity, and what remains untested?

No-service / offline route

ACTIVITY 3 / 35 MIN ESTIMATED

Run a controlled generation

Worked example

PROJECT CONTRACT:
Score factual grounding, required structure and prohibited claims independently. Real provider results must be labelled with date and model; no-service examples stay labelled constructed.
HOSTED REFERENCE: open hosted-lab.ipynb or run reference.py with all fixture files together.
EXPECTED CONSTRUCTED RESULT:
{
  "scores": {
    "A": 3,
    "B": 1
  },
  "selected": "A"
}

Your practical task

Change one prompt variable; save original responses if a service is available.
Open hosted-lab.ipynb and the reference code from the practice pack; keep an unmodified original.
Record expected and observed values separately; explain every mismatch.
Perform Repeat a live prompt if access permits; keep every result rather than only the favourite.
Keep the result and your reasoning in the lesson notes; do not mark a simulated run as live.

Evidence to keep

Run a controlled generation — a saved, inspectable artefact tied to the supplied rule.
A baseline or change-test record with expected/observed results and a limitation.

Mistakes to watch for

Repeat a live prompt if access permits; keep every result rather than only the favourite.
Treating a supplied answer key, an authored example or self-review as independent field validation.

Check your understanding

Which exact input, rule and expected value would let another learner falsify your conclusion in this activity, and what remains untested?

No-service / offline route

ACTIVITY 4 / 35 MIN ESTIMATED

Test unsupported additions

Worked example

CHANGE TESTS — predict before running:
1. Give B a convincing style: its factual failure still remains.
2. Remove the source price: do not fill it from general knowledge.
3. Repeat a live prompt if access permits; keep every result rather than only the favourite.
Keep the original expected.json unchanged.

Your practical task

Try missing facts, contradictory instructions and an invented discount.
Open failure-tests.md from the practice pack; keep an unmodified original.
Record expected and observed values separately; explain every mismatch.
Perform Give B a convincing style: its factual failure still remains.
Keep the result and your reasoning in the lesson notes; do not mark a simulated run as live.

Evidence to keep

Test unsupported additions — a saved, inspectable artefact tied to the supplied rule.
A baseline or change-test record with expected/observed results and a limitation.

Mistakes to watch for

Give B a convincing style: its factual failure still remains.
Treating a supplied answer key, an authored example or self-review as independent field validation.

Check your understanding

Which exact input, rule and expected value would let another learner falsify your conclusion in this activity, and what remains untested?

No-service / offline route

ACTIVITY 5 / 35 MIN ESTIMATED

Separate mechanism from capability

Generation is a candidate-making step, not verification. Fix a brief and factual source before changing prompts. A more vivid sentence can score worse if it adds an unsupported price or guarantee. The supplied candidates are authored examples, not claimed model runs. Using a generation API is not training a GAN or proving general intelligence. Review what the fixture cannot establish. Explain who owns the decision, where human approval is needed and which access or professional constraints remain. Do not describe a small educational success as production readiness, certification, legal compliance or a guarantee. Policy for this project: Score factual grounding, required structure and prohibited claims independently. Real provider results must be labelled with date and model; no-service examples stay labelled constructed. For learners across regions underserved or excluded by mainstream providers: verify country eligibility, language, account/identity requirements, data terms, cost, quota and connectivity before choosing a cloud service. Use only legitimate available alternatives; never bypass restrictions or invent a country/account. No service access? Complete the labelled manual/fixture route without claiming a live AI run.

Worked example

REVIEW BOUNDARY:
Score factual grounding, required structure and prohibited claims independently. Real provider results must be labelled with date and model; no-service examples stay labelled constructed.

ACCESS / NOT TESTED: unavailable provider, unsupported language and absent external feedback must remain explicit.

Your practical task

Using a generation API is not training a GAN or proving general intelligence.
Open README.md and your evidence log from the practice pack; keep an unmodified original.
Record the human decision owner, limitations and any untested service access.
Perform one small change and predict its effect before rerunning.
Keep the result and your reasoning in the lesson notes; do not mark a simulated run as live.

Evidence to keep

Separate mechanism from capability — a saved, inspectable artefact tied to the supplied rule.
A baseline or change-test record with expected/observed results and a limitation.

Mistakes to watch for

Remove the source price: do not fill it from general knowledge.
Treating a supplied answer key, an authored example or self-review as independent field validation.

Check your understanding

Which exact input, rule and expected value would let another learner falsify your conclusion in this activity, and what remains untested?

No-service / offline route

ACTIVITY 6 / 65 MIN ESTIMATED

Publish a comparison with limits

Worked example

HANDOFF MANIFEST:
input.json — immutable source
expected.json — fixture answer key
actual.json — result actually observed
evidence-log.csv — baseline plus three changes
README.md — reproduction and access route
limitations.md — unresolved failures, rights, approvals and scope
Never bundle a credential.

Your practical task

Keep the full candidate set and explain why the chosen draft still needs approval.
Open README.md and your evidence log from the practice pack; keep an unmodified original.
Record the human decision owner, limitations and any untested service access.
Perform one small change and predict its effect before rerunning.
Keep the result and your reasoning in the lesson notes; do not mark a simulated run as live.

Evidence to keep

Publish a comparison with limits — a saved, inspectable artefact tied to the supplied rule.
A baseline or change-test record with expected/observed results and a limitation.

Mistakes to watch for

Repeat a live prompt if access permits; keep every result rather than only the favourite.
Treating a supplied answer key, an authored example or self-review as independent field validation.

Check your understanding

Which exact input, rule and expected value would let another learner falsify your conclusion in this activity, and what remains untested?

No-service / offline route

Capstone self-review

Score each criterion 0 (missing), 1 (partial), or 2 (demonstrated). A self-review pass needs at least 8/10 and 2/2 on the critical safety/limits criterion. This is learner practice feedback, not verified assessment.

Defined task and preserved input: Original input and the project policy are retained; the actual question is clear.
Checked baseline: The supplied baseline reconciles field by field; unsupported live-run claims are absent.
Three failure/change tests: All three specified changes have predictions, observed results and explanations.
Repeatable handoff: Another person can follow the README; supporting practice evidence and unresolved limits are included.
Safety, rights and access honesty — critical: Score factual grounding, required structure and prohibited claims independently. Real provider results must be labelled with date and model; no-service examples stay labelled constructed. Regional access route is legitimate; credentials and private data are absent; manual/constructed work is clearly labelled.

Review questions

For the supplied fixture, what is the expected scores?

{"A": 3, "B": 1}

The independent answer key only validates this constructed fixture. Preserve the source, rerun counterexamples, and disclose what was not tested.

How should you handle the project rule: Score factual grounding, required structure and prohibited claims independently. Real provider results must be labelled with date and model; no-service examples stay labelled constructed.

State the rule, test it, and record exceptions or unresolved failures.

Rules, source provenance and counterexamples make an output inspectable; an attractive result does not override policy.

If mainstream providers do not serve your region, what is the honest route?

Check legitimate available alternatives, or label the manual/fixture route and its limits.

Access includes country, identity, language, cost and data terms. Do not bypass restrictions or invent a live result.

Practice files

References and editorial limits

Original authored practice material; deterministic fixtures build-tested. Not independently expert-reviewed or learner-validated. Time estimates unvalidated.

NIST generative AI profile

Browse all build paths → · Curriculum overview