The challenge offers three approaches. You must use at least one approach, but you may use two or all three. Submissions are only eligible for one prize. Inspiration is provided for each approach, but should be considered as the type of project that would be considered a great application. 

### **Approach 1: The AI Architect 🧠**

**Your Mission:** Use [BigQuery's built-in generative AI](https://cloud.google.com/bigquery/docs/generative-ai-overview) to architect intelligent business applications and workflows. Build solutions that can generate creative content, summarize complex information, or even forecast future trends directly within your data warehouse.

**Your Toolbox (Must use at least one):**

* **Generative AI in SQL:**  
  * [`ML.GENERATE_TEXT`](https://cloud.google.com/bigquery/docs/reference/standard-sql/bigqueryml-syntax-generate-text): The classic function for large-scale text generation.  
  * [`AI.GENERATE`](https://cloud.google.com/bigquery/docs/reference/standard-sql/bigqueryml-syntax-ai-generate): Generate free-form text or structured data based on a schema from a prompt.  
  * [`AI.GENERATE_BOOL`](https://cloud.google.com/bigquery/docs/reference/standard-sql/bigqueryml-syntax-ai-generate-bool): Get a simple True/False answer about your data.  
  * [`AI.GENERATE_DOUBLE`](https://cloud.google.com/bigquery/docs/reference/standard-sql/bigqueryml-syntax-ai-generate-double): Extract a specific decimal number from text.  
  * [`AI.GENERATE_INT`](https://cloud.google.com/bigquery/docs/reference/standard-sql/bigqueryml-syntax-ai-generate-int): Extract a specific whole number from text.  
  * [`AI.GENERATE_TABLE`](https://cloud.google.com/bigquery/docs/reference/standard-sql/bigqueryml-syntax-generate-table): Create a structured table of data from a single prompt.  
  * [`AI.FORECAST`](https://cloud.google.com/bigquery/docs/reference/standard-sql/bigqueryml-syntax-ai-forecast): Predict future values for time-series data with a single function.  
* **Generative AI in BigFrames (Python):**  
  * [`bigframes.ml.llm.GeminiTextGenerator`](https://cloud.google.com/python/docs/reference/bigframes/latest/bigframes.ml.llm.GeminiTextGenerator): Leverage the power of Gemini models in your Python workflows.  
  * [`bigframes.DataFrame.ai.forecast()`](https://cloud.google.com/python/docs/reference/bigframes/latest/bigframes.operations.ai.AIAccessor#bigframes_operations_ai_AIAccessor_forecast): Run powerful forecasting models directly on your DataFrames.

**Inspiration:**

* **Build a Hyper-Personalized Marketing Engine:** Generate unique marketing emails for every customer based on their individual purchase history and preferences.  
* **Create an Executive "Insight" Dashboard:** Develop a dashboard that automatically ingests raw support call logs and transforms them into summarized, categorized, and actionable business insights.  
  ---

### **Approach 2: The Semantic Detective 🕵️‍♀️**

**Your Mission:** Go beyond keyword matching and uncover deep, semantic relationships in your data using [BigQuery's native vector search](https://cloud.google.com/bigquery/docs/vector-search-intro). Build systems that understand meaning and context to find similar items, concepts, or issues with incredible accuracy.

**Your Spy Kit (Must use at least one):**

* **Vector Search in SQL:**  
  * [`ML.GENERATE_EMBEDDING`](https://cloud.google.com/bigquery/docs/reference/standard-sql/bigqueryml-syntax-generate-embedding): Transform your data (text, images) into meaningful vector representations.  
  * [`VECTOR_SEARCH`](https://cloud.google.com/bigquery/docs/reference/standard-sql/search_functions#vector_search): The core function to find items based on meaning, not just keywords. Can be used with or without a vector index.  
  * [`CREATE VECTOR INDEX`](https://cloud.google.com/bigquery/docs/reference/standard-sql/data-definition-language#create_vector_index_statement): Build an index for speeding up similarity search on larger tables (1 million rows or above)  
     
* **Vector Search in BigFrames (Python):**  
  * [`bigframes.ml.llm.TextEmbeddingGenerator()`](https://cloud.google.com/python/docs/reference/bigframes/latest/bigframes.ml.llm.TextEmbeddingGenerator): Create embeddings seamlessly in your Python environment.  
  * [`bigframes.bigquery.create_vector_index()`](https://cloud.google.com/python/docs/reference/bigframes/latest/bigframes.bigquery#bigframes_bigquery_create_vector_index): Build a vector index programmatically using Python.  
  * [`bigframes.bigquery.vector_search()`](https://cloud.google.com/python/docs/reference/bigframes/latest/bigframes.bigquery#bigframes_bigquery_vector_search): Query your vector index using the BigFrames API.

**Inspiration:**

* **Develop an Intelligent Triage Bot:** Instantly find historical support tickets that are semantically similar to a new, incoming ticket to speed up resolution time. The bot may also recommend a solution based on past ticket resolutions.  
* **Design a "Smart Substitute" Recommender:** Suggest ideal product substitutes based on a deep understanding of product attributes, not just shared tags or categories.  
  ---

### **Approach 3: The Multimodal Pioneer 🖼️**

**Your Mission:** Break the barriers between structured and unstructured data using [BigQuery's multimodal capabilities](https://cloud.google.com/bigquery/docs/analyze-multimodal-data). Combine numerical and categorical data with images, documents, and other rich media to unlock insights that are impossible to find in siloed datasets.

**Your Palette (Must use at least one):**

* **Multimodal Features in SQL:**  
  * [`Object Tables`](https://cloud.google.com/bigquery/docs/object-tables): Create a structured SQL interface over your unstructured files in Cloud Storage.  
  * [`ObjectRef`](https://cloud.google.com/bigquery/docs/reference/standard-sql/objectref_functions): A data type that lets you reference and pass unstructured data to AI models.  
* **Multimodal Features in BigFrames (Python):**  
  * [`BigFrames Multimodal Dataframe`](https://cloud.google.com/bigquery/docs/multimodal-data-dataframes-tutorial): Natively load, transform, and analyze mixed data types (text, images, tables) together.

**Inspiration:**

* **Revolutionize Real Estate Valuation:** Improve property price predictions by fusing structured data (e.g., sqft, \# of bedrooms) with unstructured data from street-level and satellite imagery.  
* **Build an Automated Quality Control Agent:** Detect discrepancies between a product's listed specifications, its marketing description, and its actual product image.