📄️ What are AI multi agents for evaluations?
AI multi-agents are a system of AI agents that work collaboratively to conduct evaluations of LLM outputs, as close to human evaluations as possible.
📄️ Setting up the AI multi-agents for evaluations
Lighthouz is the first platform to create your own bespoke AI multi-agents to do AI evaluations, in just 1 minute!
📄️ Using the AI agents in the evaluation playground
Once the agents are set up, you can test them in the playground (on the same page where you set up the agents). You can provide a query, expected response, and a response to evaluate to the agents for evaluations. You will see the label and reasons from the agents per round as well as the final label and reason from the meta agent.
📄️ Using the AI agents to conduct scalable evaluations
You can use the AI agents to evaluate your AI application on a dataset by heading to the Evaluation Studio.
📄️ FAQs about evaluation AI agents
- Which LLMs to use in setting up the agents?