Tool · Standard tools and platforms

Gen AI Evaluation Service

Also called: Gen AI evaluation, Vertex AI evaluation, GenAI Evaluation Service

A part of Google Cloud's Gemini Enterprise Agent Platform, formerly Vertex AI, that scores the outputs of AI models against criteria a team sets, so they can compare models and prompts.

For example: A team runs the Gen AI Evaluation Service on 200 sample questions to see whether a new prompt gives better answers.

Official site: docs.cloud.google.com

Connects to 5

• Evals Concept
• Benchmark Concept
• Vertex AI Tool
• promptfoo Tool
• Gemini Prompt Optimizer Tool