nickca

Yea! We gotta make some prompt changes to the spicy option. I also like the normal better. But that's super awesome! Glad you like it.

Congrats and thanks for being so open in the write up!

Very cool!

Would love to see Gemini there too!

I like how they have a way to test between different dialogue models. Very interesting! Will read the paper.

Oh interesting, I like that. Reminded me of Gartic for some reason. Could be interesting if the AI draws for you or you draw for the AI to guess.

Hi, Nick here from SideGuide. Thanks for your questions and suggestions. 1. As of right now it seems like 90% of the responses can infer the language pretty well from the issue context. Although we are working hard to improve this. 2. We use the issue's labels to identify the issue type and choose an appropriate prompt depending on what type it is. Thanks for the suggestion, will add more screenshots about that asap. 3. We're currently only using GPT-3 (davinci-003) on production. But we are currently testing ChatGPT too, but we don't think it is ready yet due to it is down time/rate limiting and lack of fine-tuning capabilities. Because this is still an early MVP, we haven't gotten around to filtering abusive responses just yet.

That's awesome! We're big fans of CodeSandbox and we love what y'll are doing with Sandpack. Would love to get in touch!

Hi HN! I'm Nick, CTO of SideGuide, happy to answer your questions as well :)

Hey there! So, kinda of, we definitely took inspiration from RunKit and in the future we want to support different languages. Our main goal right now is to focus on the core developer experience, illustrating how one can use a company's API with a real use case, instead of trying out a single independent API endpoint. Once, we nail that, we would like to move to new languages.

I took a quick look at your podcast API product. First, this seems awesome! Would love to try it. Second, would love to see a web example consuming your API (if you don't have one). Maybe that's something that you could use SideGuide for and would be more aligned with our current state. Although I totally see why it would be awesome to execute all the api endpoints in different languages. Will keep that in mind and maybe explore that in the future.

Thank you! Totally. When a developer is playing around with the demo we safely track and identify errors that occur in their environment and we let API companies reproduce that in their end. Aside from that, we provide customer journey visualization so API companies can see what steps the customer took and what made them do X rather than Y. The user also has the ability to provide immediate feedback if they are stuck.

We also track aggregate metrics, like engagement time, conversion rate, etc.