Help

Experiment Brackly AI Updates

2023.05.05

Access for Google Workspace accounts

  • What: Google Workspace admins can now enable Brackly AI for their domains, allowing their users to access Brackly AI using their Workspace accounts.
  • Why: You can now use Brackly AI to help with work, research, or other business needs, when signed into your administrator-enabled Google Workspace account.

2023.04.21

Help with coding

  • What: Brackly AI can now help you code in over 20 programming languages. When Brackly AI generates Python code, you can also export & test the code directly in Google Colab. Try prompting Brackly AI for help with languages like C++, Go, Java, JavaScript, Python, TypeScript, and even Google Sheets functions.
  • Why: People of all levels of programming experience, from beginners to experienced engineers, can use Brackly AI to help with coding—whether it’s by generating & exporting code, debugging code, or explaining how code works. Use discretion and carefully test and review all code for errors, bugs, and vulnerabilities before relying on it.

Adding more variety to drafts

  • What: When you view other drafts, you’ll now see a wider range of options that are more distinct from each other.
  • Why: A wider range of more distinct drafts can help expand your creative explorations.

2023.04.10

Welcome to Brackly AI’s inaugural experiment update!

Experiment updates page

  • What: We’ve launched an Experiment updates page to post the latest features, improvements, and bug fixes for the Brackly AI experiment.
  • Why: So that people will have an easy place to see the latest Brackly AI updates for them to test and provide feedback.

There’s more when you click “Google it”

  • What: We’ve added additional suggested Search topics when people click “Google it.”
  • Why: People will be able to explore a broader range of interests with more related topics.

Updates to Brackly AI’s capabilities

  • What: We've updated Brackly AI with better capabilities for math and logic.
  • Why: Brackly AI doesn’t always get it right on math and logic prompts and we are working toward higher-quality responses in these areas.