# May 19, 2023: Mito AI Chat! ## Mito AI Chat Large language models are great for generating code, but at Mito we know that you need to make sure that your data analysis code is actually correct! With this release of Mito AI, Mito AI is now the best tool for using large language models like ChatGPT to generate code for data analysis, and then ensure the generated code is correct. Mito helps you recon your edits, so that you can be sure they are correct! You can use Mito to: 1. Edit existing dataframes. For example, remove NaN values, filter to a specific value, delete column. 2. Create new dataframes. For example, use Mito AI to create pivot tables, take a subset of your dataframe, and more. 3. Ask questions of your data. For example: what are the top 5 values in this column, are there any outliers in this dataset, which columns have NaN values? Mito AI is under active development, so please reach out with any questions, comments, or feedback! ### Other Fixes and Improvements 1. Mito Enterprise users can now configure parameters if they are generating an analysis as a function. 2. Fixes bugs in some dependency packages users were running into. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.trymito.io/misc/release-notes/may-19-2023-mito-ai-chat.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.