Hex Magic is a powerful set of AI-driven features to help you do more with data. As of this writing, Magic features are in private beta, and not yet generally available. You can join the waitlist at hex.tech/magic.
These features are experimental. You should not rely on AI-generated code to be accurate, complete, or free from bias. Hex Magic is meant as a way to augment - not replace - human insight and judgement.
Hex Magic features still require you, the human, to click a run button. Hex will not automatically run AI-generated code, and it’s on you to determine whether what was written is correct.
If you have been added to the private beta, you'll receive an email with specific instructions on accessing Hex Magic.
To activate Hex Magic as a beta user, the only thing you need to do is head to your Hex user preferences (Settings → Preferences) and toggle on the Magic option.
Refresh your open Hex pages, and you'll have access to Magic features in any Python or SQL cell.
How to use Hex Magic
In any Python or SQL cell, you can invoke Hex completions by hitting
Cmd/ctl+shift+m. The inferred completion will fill in and you can accept or reject it using
Activate the Edit pane with the keyboard shortcut
Cmd/ctl+shift+e. You can ask Magic Edit to do anything to your code.
This feature can automatically detect and fix errors in your code. Access it with
Use Magic Explain to automatically document code – whether it’s something you wrote, or something unfamiliar you’re seeing for the first time. Try it out with
Hex is not using user content or data to train models, and will not do so without your expressed permission.
Hex does not send the actual contents of dataframes to a model, so your actual data never leaves Hex. We do, however, use metadata about the project context, including upstream code, database schemas, and your prompt text. If any of these contain sensitive information, or you’re not comfortable with that, you should not use Hex’s Magic features.
Like all AI-driven features, accuracy can be highly variable based on the model, prompt, and other factors. Hex Magic can and will create some errors, and it’s on you, dear user, to evaluate, understand, and execute the code in your projects.
Of course improving the accuracy of completions is a key focus for us, and we welcome your feedback on where they are or aren’t working well.
Support & Feedback
Your feedback and bug reports are the best way for us to make this feature better. Please email [email protected] with any questions, product feedback, or bugs.
During this private beta, we ask that you not email [email protected] directly with questions and feedback related to Hex Magic. We're iterating rapidly, and will be providing very limited support outside of acknowledging bugs and feedback.
PS: If you hit a bug, it's very helpful to include the debug info, which is easily copied from the bottom left hand support menu.