Hi! I am very enthusiastic about the power of Quick-Apps, since I discovered them I have created 4-6 to solve some tooling gaps for my engineering team and it is truly amazing. I have also involved my team’s PM-T and she has quickly embraced them and made good use of them for our team. Kudos to your work!
I have a question regarding the maintainability/robustness of these apps and how trustworthy they are to keep building more features on top. I had a bad experience in which I had done near 70 iterative versions of one app and it was going very well and suddenly after asking the app to build a “dark-mode” version of itself (suggested by Quick-Apps itself), the AI deleted the main code file and basically left the app in a corrupt state with Quick-versioning not being able to recover it fully. Since then I am very defensive/fearful when using these apps as it was a big trust–buster for me. I’ve been trying to get suggestions from the Quick-AI itself on how I show best build these apps. I put some of my learnings from this bumpy experience here: Quip
Could you help me understand if these kinds of issues are on your radar and if after the Quick-Apps feature is in GA state these issues will be less likely or entirely solved?
Hi @javiasen,
Thank you for those kind words! As for Apps feature, while I do not have direct visibility into the internal engineering roadmaps or specific bug-tracking systems of the Quick-Apps development team, I think I can provide some tips to avoid future issues.
My guess for the cause of why your app became corrupted was due to the sheer volume of iterations the one singular app had. My advice would be to create duplicates of the app before you ask any major changes, that way you can have backups incase corruption happens again. I would also try to steer away from large prompts and break up the requests into smaller portions, so that it a) doesn’t overwhelm the app and b) if a specific part of the prompt leads to corruption, you can then identify it easily.
I’d recommend submitting this as a bug report through AWS Support (Case management) so the team is aware of the corruption scenario.
Hope this helps!
Hi @javiasen,
Just checking back in since this thread hasn’t received a response in a while. Was Cesar’s reply helpful to you and/or were you able to find a solution yourself in the meantime? Please help the community by marking this answer as “Solution” or following up in general within the next 3 business days!
Thank you!
Hi @javiasen,
Since I haven’t received any further updates from you, I’ll treat this inquiry as complete for now. If you have any additional questions, feel free to create a new post in the community and link this discussion for context.
Thanks!