practical-gcp-examples

Analyze data (e.g. an uploaded CSV/Excel) with pandas and produce a chart or report file, returned to the user as an attachment.

Solve the user's task by writing Python; the harness runs it in an isolated sandbox and returns stdout.

Use when the user asks about using Gemini in an enterprise environment or explicitly mentions Vertex AI, Google Cloud, or Agent Platform. Guides the usage of the Gemini API on Agent Platform with the Google Gen AI SDK. Covers SDK usage (Python, JS/TS, Go, Java, C#), capabilities like multimodal inputs, tools, media generation, caching, batch prediction, and Live API.

Manages datasets, tables, and jobs in BigQuery, and integrates with BigQuery ML and Gemini for advanced data analytics and AI-driven insights. Use when you need to interact with BigQuery, run SQL queries, manage BigQuery resources, or leverage BigQuery's built-in ML capabilities. Also use when performing data analysis, ingesting data into BigQuery, or developing AI applications on BigQuery.

Echo the user input back verbatim

Compute the prime factorization of an integer by executing Python in the sandbox

Reverse the user input string

Use when answering a business/analytics question over already-aggregated data and the deliverable is a visual. Produces ONE annotated chart plus a compact exact-numbers table, with the headline finding as the title. Defaults to a single secure PNG image (no live code in the artifact). Trigger on requests like "show me the trend", "chart this", "visualize X by segment", "build a report on the numbers". Do NOT use for multi-panel dashboards or for fetching/validating raw SQL (the harness owns data access and validation).