Your AI Product Needs Evals

In this reference
A practical approach to evaluating AI applications through inspection of real outputs, error analysis and iterative development of task-specific checks.
Cite the original work
Hamel Husain (29 March 2024). Your AI Product Needs Evals. Hamel’s Blog. https://hamel.dev/blog/posts/evals/
View BibTeX
@misc{ai_product_evals,
author = {Hamel Husain},
title = {{Your AI Product Needs Evals}},
howpublished = {Hamel’s Blog},
url = {https://hamel.dev/blog/posts/evals/},
year = {2024}
}
