PMLE - Architecting Low-Code AI Solutions (12% of the exam) - Section 1.1

Develop ML models using BigQuery ML and AutoML on the Gemini Enterprise Agent Platform, including classification, regression, forecasting, and clustering, plus feature engineering, prediction, and fine-tuning Gemini models from BigQuery.

Use BigQuery ML and Agent Platform AutoML to train classification, regression, forecasting, and clustering models without leaving BigQuery, and apply feature engineering to improve input quality. Distinguish when to fine-tune a Gemini model in BigQuery versus deploying a pre-trained foundation model directly.

BigQuery MLAgent Platform AutoMLFeature engineeringFine-tuning Gemini models

Practice question for this objective

Free sampleArchitecting Low-Code AI Solutionsmedium

A marketing analytics team holds 8,000 historical product blurbs in BigQuery, each paired with an approved on-brand rewrite that follows their house style for tone and length. A prompt-only Gemini call in BigQuery produces rewrites that are accurate but consistently miss the house tone. The team is fluent in SQL, wants the model to internalise their style without leaving BigQuery, and wants future rewrites generated directly from a SQL query. Which approach should they take?

AKeep the base Gemini model and craft a longer ML.GENERATE_TEXT prompt that embeds a dozen example rewrites inline, so the model copies the tone from the few-shot examples on every call.
BRun supervised fine-tuning of a Gemini model in BigQuery with CREATE MODEL using the paired blurbs and rewrites as the training table, then call the tuned model with ML.GENERATE_TEXT. Correct
CTrain a BigQuery ML logistic regression model on the paired text columns so it learns to map each blurb to its rewritten form during training.
DExport the paired blurbs to Cloud Storage and run a custom Vertex AI training job to fine-tune Gemini, then import the result back into BigQuery for inference.

BigQuery ML can supervised-fine-tune a Gemini model from a labelled table using CREATE MODEL, then serve generations with ML.GENERATE_TEXT without leaving the warehouse. Supervised fine-tuning adjusts the Gemini model's weights from paired prompt-response examples so it reproduces the house tone reliably, and BigQuery ML exposes this through CREATE MODEL and ML.GENERATE_TEXT so the SQL-fluent team never moves the data.

Why A is wrong: Tempting because few-shot prompting can nudge tone without training, but it does not internalise style from 8,000 examples, repeats the long prompt on every call raising cost, and is brittle compared with fine-tuning when consistent style is the goal.

Why B is correct: Correct: BigQuery ML supports supervised fine-tuning of Gemini via CREATE MODEL over a labelled prompt-and-response table, and the tuned endpoint is then queried with ML.GENERATE_TEXT, all inside BigQuery, so the model learns the house style from the paired examples.

Why C is wrong: Tempting because logistic regression is a familiar BigQuery ML model, but it is a classifier that predicts discrete labels and cannot generate free-form rewritten text, so it cannot produce styled blurbs at all.

Why D is wrong: Tempting because custom training can fine-tune models, but it leaves BigQuery, adds pipeline overhead the SQL-only team wants to avoid, and is unnecessary because BigQuery ML can fine-tune Gemini in place for this task.

See more PMLE practice questions, answers explained.

Exam traps in Architecting Low-Code AI Solutions

Answers that look right on this material and are not. Each one is a distractor from a different question in the PMLE bank for this domain.

Automatic conversion of the forecasting task into a supervised classifier that predicts whether sales rise or fall.
Why it is wrong: Tempting because rise-or-fall framing sounds useful, but ARIMA_PLUS forecasts continuous future values and does not turn the task into a classification problem.
Model Garden is a managed pipeline that automatically retrains the selected foundation model on the customer's data each time new examples arrive
Why it is wrong: Continuous retraining sounds attractive for keeping a model fresh, but Model Garden is a discovery and deployment catalogue, not an automated training pipeline, so this misstates its purpose.
Append every historical ticket and its label into a single very long prompt and send it with each new classification request.
Why it is wrong: This is tempting because in-context examples can improve few-shot accuracy, but packing thousands of tickets into one prompt exceeds practical context limits and never updates the model's own weights.

Examworthy is not affiliated with or endorsed by Google Cloud. Original, blueprint-aligned practice material only.