Hey HN!<p>We're building Embra, an always-one-second away GPT assistant that integrates into your OS, apps, and workflows.<p>Everyone is talking about the "context problem" as it relates to GPT, in that the answers you get out are only as good as the information you put in. And, well, a lot of users don't want to type in a bunch of text.<p>With Embra, you can pick and choose which context to feed the AI within the interface itself. And that context can be anywhere on your computer -- text in a PDF document, any tabs within Chrome, etc.<p>One of the primary use cases is improved coding, debugging, and software workflows. We especially want to gather feedback in this direction, as engineers engage in Q&A workflows and code creation 15+ times a day. Really awesome. :)<p>Just launching our closed beta signup page today, and rolling out first invites to broader community.<p>https://embra.app/<p>And the twitter launch thread: https://twitter.com/zachtratar/status/1623015294569713665<p>We're also looking for the following feedback:<p>1) What do you think about OS-level integration vs VSCode extension? Both have filesystem access, but do you perceive them differently security or capability wise?
2) What do you use ChatGPT for today primarily, and would desktop access improve those workflows meaningfully?
3) What context would you like to pull into the AI, as an engineer?<p>Thanks! And feel free to poke at the idea. We've been around the block and welcome the classic, ruthless HN constructive criticism.