by eddy-sekorti
0 subcomment
- Hmm great, All these on the fly generated apps also needs some adult supervision to ensure secuirty and compliance. So you need to consider including some builtin security guardrails. But overall this is a nice idea.
by ManuelKiessling
0 subcomment
- What if software shipped with a software engineer?
https://manuel.kiessling.net/2025/11/04/what-if-software-shi...
- I agree that is part of the future of AI, you describe what kind of UI you need and the app generates a combination of UI components to match your needs.
I expect this to be a simple NLP mapping via local/cloud AI model to a JSON/DSL that describes the interface. Naturally, this won't work well for complex UI that are context aware but will do well for most simple apps/dashboards.
My question is: How do you plan to make this a business?
- This is such an important step forward as we start to understand the 2nd order implications of AI and how it will change UIs in the future.
We used to have to allow + review 3rd party plugins for software so that people could customize it, but when the cost of development is near-0, we can simply hand over the development reigns to customers.
- I guess I don't really understand how this works although I admit to not reading everything. Most SaaS companies are very vigilant about not having per-customer code changes - many people have lived through the hell of ending up with divergent code bases as a result of customer demands.
But I did want to mention something that I think would work well for SaaS companies which is related, and that is empowering customers to make their own changes to the core product.
We tried at one stage having a council of customers, but it's simply wasn't practical to implement all of the ideas that they came up with. That's changed now.
I think an interesting product would bundle the communications, voting (if necessary), updates, screen captures / video demos, feedback loops and so on that are involved in a decent sized group of customers consolidating their requirements/ideas.
A true mark of success might be when the product becomes self-stewarding, with customers driving a lot of the requirements.
by rachidsahde
0 subcomment
- This is a very interesting idea, but I think the hardest part is not generating the workflows/apps — it’s making them safe. If the AI can read customer data and generate apps on top of APIs, prompt injection, cross-tenant data leaks, over-permissioned API calls, and generated-code bugs become serious risks.
by ruben81ad
1 subcomments
- How do you know that the values of the automatically generated dashboards are correct?
- 2,000 daily users is 2,000 separate paying businesses that use your app or you count one business with 2,000 employees as 2,000 users?
How many paying clients (companies, not people) do you have?
- i love this because it seems like you've turned vibecoding up to 11 unleashing the non-technicals in your org to ship vibecode slop straight to prod. it's an idea so obviously terrible to most engineers that maybe it's actually really really smart. much bolder than yet another AI-driven dashboarding tool or smart notebook.
to address the elephant in the room... how do you think about technical debt incurred by users who likely do not understand the underlying data models, consider auth, etc?
by password4321
1 subcomments
- Palantir Foundry as a plug-in.
- [flagged]
by Jinyibruceli
0 subcomment
- [flagged]
Hacker News