Create a campaign pack without invented performance

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.

Define a truthful offer and audience

Advertising work combines creative claims with measurement. A click-through rate is observed clicks divided by impressions; it does not establish sales lift or causality. Use consented assets and fictional performance data until a legitimate real test exists. Use a real problem and approved claims, not sensitive-feature targeting. 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: Calculate CTR and cost per click from the supplied fixture. No protected-characteristic targeting, unauthorised tracking, fabricated testimonials or guaranteed returns. 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):
{
  "impressions": 1000,
  "clicks": 20,
  "spend": 10
}
INDEPENDENT FIXTURE TARGET:
{
  "ctr": 0.02,
  "cpc": 0.5,
  "sales_lift": "not established"
}

Your practical task

1. Use a real problem and approved claims, not sensitive-feature targeting.
2. Open input.json and expected.json from the practice pack; keep an unmodified original.
3. Record a manual prediction and the relevant rule before consulting the answer key.
4. Perform one small change and predict its effect before rerunning.
5. Keep the result and your reasoning in the lesson notes; do not mark a simulated run as live.

Evidence to keep

• Define a truthful offer and audience — 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

• Zero clicks: CPC is undefined, not zero.
• 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.

Build a factual creative brief

Advertising work combines creative claims with measurement. A click-through rate is observed clicks divided by impressions; it does not establish sales lift or causality. Use consented assets and fictional performance data until a legitimate real test exists. Link every price, feature and testimonial to permission and evidence. Establish a baseline before changing prompts or code. Keep the original input immutable. Record expected values, observed values and whether each comparison passed. If the expected file conflicts with a justified policy, investigate rather than forcing a convenient match. Policy for this project: Calculate CTR and cost per click from the supplied fixture. No protected-characteristic targeting, unauthorised tracking, fabricated testimonials or guaranteed returns.

Worked example

MANUAL BASELINE / compare every named field
{
  "ctr": 0.02,
  "cpc": 0.5,
  "sales_lift": "not established"
}
Keep a separate observed-result column; the answer key is not a model response.

Your practical task

1. Link every price, feature and testimonial to permission and evidence.
2. Open input.json and expected.json from the practice pack; keep an unmodified original.
3. Record expected and observed values separately; explain every mismatch.
4. Perform one small change and predict its effect before rerunning.
5. Keep the result and your reasoning in the lesson notes; do not mark a simulated run as live.

Evidence to keep

• Build a factual creative brief — 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

• More clicks do not establish more profit without sales, costs and attribution evidence.
• 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.

Calculate a campaign baseline

Advertising work combines creative claims with measurement. A click-through rate is observed clicks divided by impressions; it does not establish sales lift or causality. Use consented assets and fictional performance data until a legitimate real test exists. Reconcile observed denominators and costs before generating commentary. Build one inspectable transformation or bounded AI prompt. Keep calculation and validation deterministic where possible. If you make a permitted hosted call, save the actual response separately from the authored examples and verify its material claims; the supplied reference never simulates a live model. Policy for this project: Calculate CTR and cost per click from the supplied fixture. No protected-characteristic targeting, unauthorised tracking, fabricated testimonials or guaranteed returns.

Worked example

PROJECT CONTRACT:
Calculate CTR and cost per click from the supplied fixture. No protected-characteristic targeting, unauthorised tracking, fabricated testimonials or guaranteed returns.
HOSTED REFERENCE: open hosted-lab.ipynb or run reference.py with all fixture files together.
EXPECTED CONSTRUCTED RESULT:
{
  "ctr": 0.02,
  "cpc": 0.5,
  "sales_lift": "not established"
}

Your practical task

1. Reconcile observed denominators and costs before generating commentary.
2. Open hosted-lab.ipynb and the reference code from the practice pack; keep an unmodified original.
3. Record expected and observed values separately; explain every mismatch.
4. Perform An AI-written testimonial is not a customer review.
5. Keep the result and your reasoning in the lesson notes; do not mark a simulated run as live.

Evidence to keep

• Calculate a campaign baseline — 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

• An AI-written testimonial is not a customer review.
• 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.

Challenge a flattering narrative

Advertising work combines creative claims with measurement. A click-through rate is observed clicks divided by impressions; it does not establish sales lift or causality. Use consented assets and fictional performance data until a legitimate real test exists. Separate clicks, sales, profit and causal lift. Change one assumption at a time and predict the result first. Retain the failure, the revision and the rerun evidence. A failure is useful information: hiding a bad output or editing a test target after seeing the answer destroys the value of the experiment. Policy for this project: Calculate CTR and cost per click from the supplied fixture. No protected-characteristic targeting, unauthorised tracking, fabricated testimonials or guaranteed returns.

Worked example

CHANGE TESTS — predict before running:
1. Zero clicks: CPC is undefined, not zero.
2. More clicks do not establish more profit without sales, costs and attribution evidence.
3. An AI-written testimonial is not a customer review.
Keep the original expected.json unchanged.

Your practical task

1. Separate clicks, sales, profit and causal lift.
2. Open failure-tests.md from the practice pack; keep an unmodified original.
3. Record expected and observed values separately; explain every mismatch.
4. Perform Zero clicks: CPC is undefined, not zero.
5. Keep the result and your reasoning in the lesson notes; do not mark a simulated run as live.

Evidence to keep

• Challenge a flattering narrative — 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

• Zero clicks: CPC is undefined, not zero.
• 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.

Package approval and disclosure

Advertising work combines creative claims with measurement. A click-through rate is observed clicks divided by impressions; it does not establish sales lift or causality. Use consented assets and fictional performance data until a legitimate real test exists. State asset rights, revisions and client approval before publication. 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: Calculate CTR and cost per click from the supplied fixture. No protected-characteristic targeting, unauthorised tracking, fabricated testimonials or guaranteed returns. 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:
Calculate CTR and cost per click from the supplied fixture. No protected-characteristic targeting, unauthorised tracking, fabricated testimonials or guaranteed returns.

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

Your practical task

1. State asset rights, revisions and client approval before publication.
2. Open README.md and your evidence log from the practice pack; keep an unmodified original.
3. Record the human decision owner, limitations and any untested service access.
4. Perform one small change and predict its effect before rerunning.
5. Keep the result and your reasoning in the lesson notes; do not mark a simulated run as live.

Evidence to keep

• Package approval and disclosure — 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

• More clicks do not establish more profit without sales, costs and attribution evidence.
• 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.

Deliver a campaign evidence pack

Advertising work combines creative claims with measurement. A click-through rate is observed clicks divided by impressions; it does not establish sales lift or causality. Use consented assets and fictional performance data until a legitimate real test exists. Provide creative variants, checked metrics and no unsupported success claim. Deliver a reproducible bundle rather than a screenshot alone. Include inputs, rules, output, failure tests, a short README and residual limitations. Ask another person to follow the instructions if possible; self-review and actual external review must be labelled separately. Policy for this project: Calculate CTR and cost per click from the supplied fixture. No protected-characteristic targeting, unauthorised tracking, fabricated testimonials or guaranteed returns.

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

1. Provide creative variants, checked metrics and no unsupported success claim.
2. Open README.md and your evidence log from the practice pack; keep an unmodified original.
3. Record the human decision owner, limitations and any untested service access.
4. Perform one small change and predict its effect before rerunning.
5. Keep the result and your reasoning in the lesson notes; do not mark a simulated run as live.

Evidence to keep

• Deliver a campaign evidence pack — 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

• An AI-written testimonial is not a customer review.
• 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.

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: Calculate CTR and cost per click from the supplied fixture. No protected-characteristic targeting, unauthorised tracking, fabricated testimonials or guaranteed returns. Regional access route is legitimate; credentials and private data are absent; manual/constructed work is clearly labelled.

Review questions

Practice files

• README.md
• evidence-log.csv
• expected.json
• failure-tests.md
• hosted-lab.ipynb
• input.json
• lab_engine.py
• reference.py
• requirements.txt

References and editorial limits

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

• ICC advertising and marketing code

Browse all build paths → · Curriculum overview