I built an AI Hiring Assistant that performs an initial screening, collects candidate information, answers questions about the role, and also asks a several behavioral interview questions: https://hiring.gracekelly.dev/
Built entirely on Vercel & OpenAI. Took about a day, hardest part was configuring Sign In With Google. Had several dozen candidates use it, saved a lot of time and helped prioritize conversations.
Small dataset for those that emailed, n=~3, but none of them were standout resumes. Best few candidates actually went through chat and also followed up via email with additional information a few days later.
The Vercel templates are really awesome. I used the AI Chatbot starter (https://vercel.com/templates/next.js/nextjs-ai-chatbot), and it just took me a few hours to build a GPT-4 powered initial screening chatbot tool for a job posting. It asks candidates a few behavioral questions and answers their questions about the role. I had to swap out the auth provider to Google, add a Postgres database for permanent storage, and write an initial prompt, but other than that - the fastest I ever built and deployed something useful.
Pro tip: I use a mix of Mac and Windows with Apple's magic keyboard. The way I fixed the key layout issue was to swap the mapping of the CMD and CTRL keys on the Windows machine. (used a utility called SharpKeys, but Windows may now have a built in way to do this) It feels pretty much seamless. I'm also using the magic trackpad on Windows - the ability to pinch zoom, pan and scroll is just as functional and awesome as it is on the Mac.
PS, I have never been able to understand the Windows control key placement. You have to use it all the time but it's off to the far side. It has to be pressed with the tiniest, weakest finger.
I'm mostly a Mac guy but have spent lots of time using Windows and I still have to pause to place my finger on the control key. For the same thing, I press the command key on my Mac with my thumb. I can't miss it, my fingers naturally spread out over the keyboard for the second keypress and my thumb is strong.
Speaking as a guitarist, this is an excellent tool for exploring and learning different scales. I especially like the piano view - helps you see patterns on a piano side by side.
On bass, you can play a scale anywhere on the instrument using the same pattern. (Different patterns for major and minor scales, obviously, and the less common ones.) E.g. ascending major is 2 4 -> 1 2 4 -> 1 3 4; ascending minor is 1 3 4 -> 1 3 4 -> 1 3. You just have to find the root of the scale. On guitar, outside of the high B/e strings, which are weird because there are a different number of semitones between G and B, you can do the same thing.
Who are the people behind this project? There’s no information about the company building this, no privacy policy/tos on the website. Looks like a scam the way it is right now.
If you want to build trust with your early supporters, I’d recommend putting your team on display. It looks like you’ve invested into a good looking marketing site, but what I’d show off instead are videos and photos of prototypes in the lab and progress that you’re making on the product, with actual team members talking about the problem you’re solving and their inspiration.
I found this very helpful! As a self-taught musician, it filled some gaps in my music theory knowledge - especially being able to visualize computing scales, modes, and intervals as algorithms. I can now better evaluate these in my head when I encounter a key/scale that I haven't seen before! Thank you!
