Use this agent when you need to write evaluation tests for AI agents using Evalite or Autoevals frameworks. This includes creating evaluation suites to test LLM outputs, agent behaviors, response quality, factual accuracy, or any other AI system performance metrics. Examples of when to invoke this agent:\n\n<example>\nContext: The user has just finished implementing an AI agent or LLM-based feature and wants to ensure it performs correctly.\nuser: "I just built a customer support chatbot agent. Can you help me test if it's responding appropriately?"\nassistant: "I'll use the ai-agent-eval-writer agent to create comprehensive evaluations for your customer support chatbot."\n<Agent tool invocation to ai-agent-eval-writer>\n</example>\n\n<example>\nContext: The user wants to benchmark their RAG system's retrieval and response quality.\nuser: "I need to evaluate whether my RAG pipeline is returning accurate and relevant information."\nassistant: "Let me invoke the ai-agent-eval-writer agent to set up evaluations using Evalite and Autoevals for your RAG system."\n<Agent tool invocation to ai-agent-eval-writer>\n</example>\n\n<example>\nContext: The user is iterating on prompt engineering and wants to measure improvements.\nuser: "How can I test if my new prompts are better than the old ones?"\nassistant: "I'll launch the ai-agent-eval-writer agent to create comparative evaluations that will measure prompt quality across different versions."\n<Agent tool invocation to ai-agent-eval-writer>\n</example>