Evaluation & Safety
Safety
Practices that reduce harmful, unethical, or dangerous model outputs.
Published 2026-06-12
Related terms
Explore the glossary
Find definitions for AI, LLM, MCP, RAG, agent, and prompt engineering terms.
Browse all termsRelated Resources
Evaluation
GlossaryThe process of measuring a model's performance on tasks or benchmarks.
Multimodal Fitness Form Checker
PromptUpload a video of an exercise. Gemini 3 analyzes your form and provides safety tips.
Trauma-Informed Practitioner
SkillApply trauma-informed principles to coaching, teaching, and caregiving relationships.
Firecrawl
MCP ServerOfficial Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.
Benchmark
GlossaryA standardized dataset and task used to compare models.