[HN Gopher] Build and Host AI-Powered Apps with Claude - No Depl...
___________________________________________________________________
Build and Host AI-Powered Apps with Claude - No Deployment Needed
Author : davidbarker
Score : 138 points
Date : 2025-06-25 17:14 UTC (5 hours ago)
(HTM) web link (www.anthropic.com)
(TXT) w3m dump (www.anthropic.com)
| WXLCKNO wrote:
| The tiniest step towards a future where AI eats all apps.
|
| No persistent storage and other limitations make it just a toy
| for now but we can imagine how people will just create their own
| Todo apps, gym logging apps and whatever other simple thing.
|
| no external API access currently but when that's available or app
| users can communicate with other app users, some virality is
| possible for people who make the best tiny apps.
| handfuloflight wrote:
| > No persistent storage
|
| What stops you from wiring it up to your endpoints that handle
| that?
| js4ever wrote:
| Current limitations: No external API calls (yet), No
| persistent storage
| jofla_net wrote:
| Great, %1 of the competition that we have today. Cant wait to
| see a the wasteland when all apps will effectively be from a
| couple companies. /s
| headcanon wrote:
| One thing I've learned is that no matter how easy it is to
| create stuff, most users will still favor the one-click app
| install, even if they don't get full control over the workflow.
|
| With that said, I'm sure there are a lot of power users who are
| loving the lower barrier to creation
| meistertigran wrote:
| Actually implementing persistent storage for simple apps isn't
| that hard, especially for a big corp. Personally, I was using
| LLMs coding capabilities to create custom single-file HTML
| apps, that would work offline with localStorage. It's not that
| there aren't good options out there, but you can't really
| customize them to work _exactly_ how you want. Also it takes
| like half an hours to get what you want.
|
| The only downside was not being able to access the apps from
| other devices, so I ended up creating a tool to make them
| online accessible and sync the data, while using the same
| localStorage API. It's actually pretty neat.
| sharemywin wrote:
| I've used the interface in chatgpt to click on a button and
| talk back and forth with an AI and I could see this being
| pretty good interface for alot of "apps"
|
| weather, todo list, shopping list, research tasks, email
| someone, summarize email, get latest customized news, RSS feed
| summary, track health stats, etc.
| SonomaSays wrote:
| You could have a hybrid business model:
|
| Build a thing that does a complex thing elegantly (Some Deep
| Research Task) that is non trivial for others to setup, but
| many people want it.
|
| Charge a direct access in a traditional sense [$5 per
| project] -- but then have the Customer link their API to the
| execution cost - so they basically are paying for:
|
| _" Go here and pay HN $5 to output this TASK, charge my API
| to get_it_done"_ This could be a seriously powerful tool for
| the Digital Consulting Services industry.
|
| (I mean that is what its model for)
|
| So this begs the question, will Anthropic be building in a
| payments mechanism for such to happen?
| throwaway7783 wrote:
| Matter of time. It is trivial to overcome the current
| limitations.
| nico wrote:
| This is a really cool feature and it's big competition for
| services like Lovable, Bolt, v0
|
| Seems like AI-assisted coding space is splitting in 2:
|
| 1) tools and services that aim mostly at prototyping and are
| close to no-code; most useful for users like PMs or very early
| stage entrepreneurs who just need to have something to show/share
|
| 2) professional tools that target "serious" developers who are
| already working on bigger/more complex code bases
|
| Interesting that Claude is going after both. 1) with this new
| feature, and 2) with pretty much all their other services
| reidbarber wrote:
| The big feature here is that the shared artifacts can use the
| Claude API themselves (where usage is tied to the logged-in users
| of your shared artifact).
| ru552 wrote:
| Is this much different from the custom GPTs that OpenAI pushed a
| year or two ago?
| handfuloflight wrote:
| All things being equal, Claude is just better.
| elpakal wrote:
| Same question, but I'm less clear on how we devs get paid here.
|
| Still hoping someone builds the App Store for custom GPTs where
| we don't have to worry about payment and user infrastructure.
| Happy giving up a percentage for that butnot30percentguys.
| ffsm8 wrote:
| In this case the code in question is actually running on the
| service providers metal, essentially PaaS.
|
| I wouldn't feel comfortable comparing that to the 30%
| i-wonder-who takes for providing a store to download packages
| that then run on the edge.
|
| (And fwiw, all of them should be able to take any percentage
| they want. It's only an issue if there is _no other option_ )
| ianbicking wrote:
| It feels like what Custom GPTs should have been. Custom GPTs
| are barely able to do anything interesting beyond an initial
| prompt, there's no ability to modify the core user experience.
| The ability to run code and have it do subrequests makes this
| actually interesting.
| isoprophlex wrote:
| Is this the end of - or at least a significant challenge to -
| SaaS?
|
| Why buy into saas tooling if you can just slap something together
| - that you fully own - with something like this?
| sealeck wrote:
| - Compliance
|
| - Thing should work reliably (and you want someone else to be
| responsible for fixing it if it doesn't)
|
| - Security
|
| - Most SaaS is sufficiently complex that an LLM cannot
| implement it
| throwacct wrote:
| This x100. B2B is a different monster altogether.
| samsolomon wrote:
| Enterprise SaaS are business processes that lean extremely
| heavily on software. Some of that could be amended by AI, but
| it's much harder for me to see that getting wholesale
| replaced the same way many consumer apps could be.
| jag729 wrote:
| In the limit, though, are these things real roadblocks to app
| builders replacing SaaS? Paying for reliability/support seems
| like the only real remaining advantage of SaaS if codegen
| models get 3-5x better, and even then the bar is the
| reliability of SaaS apps right now (which in a lot of cases
| is not _that_ high).
|
| Could imagine a single universal app builder just charging a
| platform fee for support, or some business model along those
| lines. (Again, in the limit, I'm not sure that support would
| be too necessary)
| giancarlostoro wrote:
| When you have a service outage you think the AI will be able to
| troubleshoot the entire system and resolve the issues?
| jkcorrea wrote:
| if scaling laws and context windows continue, why not?
| SonomaSays wrote:
| There is coming a very_soon_time whereby one will have to
| ensure all the routes and failure_modes for the AIs
| plumbing are functional.
|
| What if the outage is specifically that AI_agent cant reach
| [thing]?
| falcor84 wrote:
| > What if the outage is specifically that AI_agent cant
| reach [thing]?
|
| We already saw some examples of this in Anthropic's
| safety papers - the AI will reach out to the human to get
| help with that - essentially using a human as an
| API/tool.
| headcanon wrote:
| Challenge, yes, but I wouldn't go far to say "end of".
|
| B2C SaaS will have more challenge the easier it gets to create
| things, but consumers have always been fickle anyway.
|
| I'd say B2B SaaS is mostly safe, partially because they want
| the support and don't want to have to maintain it.
|
| Today we have open-source versions of a lot of SaaS products,
| but the proprietary ones are still in business, mostly for that
| reason IME.
| calvinmorrison wrote:
| you can swing it anyway you want - another reason we use
| spreadsheets, or another reason we don't use airtable, or CRM
| #37....
|
| all systems require support and upkeep... nobody wants to do
| it.
| nikcub wrote:
| maybe not b2b saas since that has always been around service
| contracts - but a lot of those internal processes that
| currently run in excel are prime for AI mini-app replacement.
|
| this is delivering what no-code promised us.
| asdev wrote:
| >They authenticate with their existing Claude account
|
| Only works if both app producer and user are in the Claude
| ecosystem
| falcor84 wrote:
| Seems like it's essentially the same model as OpenAI's Custom
| GPTs [0], but now with the custom code in front of the AI
| rather than behind it.
|
| [0] https://openai.com/index/introducing-gpts/
| asdev wrote:
| yeah I thought custom GPTs flopped hard too
| tempodox wrote:
| This is the logical next step to code-generating LLMs, it makes
| perfect sense. I'm curious to see how useful it will actually be,
| and whether it will be worth the costs.
| syedumaircodes wrote:
| Is this like roblox for AI? I'm new to this (HN and all) so I
| don't know much about it.
| muskmusk wrote:
| "everything evolves until it becomes an operating system"
| falcor84 wrote:
| Or at least until it contains an "ad hoc, informally-specified,
| bug-ridden, slow implementation of half of Common Lisp"
| Edmond wrote:
| Another approach is to work towards seamless integration of human
| + bot collaboration:
|
| https://news.ycombinator.com/item?id=44380745
|
| Basically the bot shows the human the right UI at the right time
| as they work.
| levocardia wrote:
| This is cool...but what I really want is (1) Claude and I develop
| a cool app, (2) I give Claude a virtual credit card number with a
| spend limit, (3) Claude deploys it to whatever service they think
| works best (Railway, Vercel, ...) and points a domain name to
| that hosting service.
| AtheistOfFail wrote:
| Noone in cloud wants spend limits, everyone wants limitless
| billing.
| jonplackett wrote:
| I used to love to make silly websites or apps with new
| technologies. Been doing it since flash. I have a pretty decent
| hit rate! It's not unusually to get half a million or so people
| try one of them.
|
| But with AI that model is just totally broken because the running
| cost is so high.
|
| If I have half a million people come play my silly AI game that I
| have no wish to monetise - I am gonna be POOR very fast.
|
| Log in with [insert ai vendor here] is something I've been hoping
| would happen for a while.
| mbm wrote:
| Agreed, it's an interesting model. I wonder what the approval
| ui looks like for the app end-user? Is it super clear to them
| that they're financially responsible for their usage?
| jonplackett wrote:
| Yeah I wonder how that actually works - because I would guess
| people are logging in with their consumer login not an api
| login, so they're not really even in the mindset of limits
| and cost per token.
| mbm wrote:
| Precisely. You click on a claude link, and suddenly it's,
| "You are now financially responsible for your actions from
| here on..." I'm sure they've spent a lot of time thinking
| through the ui/ux of this.
| gavmor wrote:
| "Log in With Google" to use Drive storage has long been a
| thing. Maybe proxying Gemini usage isn't too far off.
| jerpint wrote:
| This is seriously lacking but I think things like jailbreaks
| and malicious prompts make it a bit too brittle for now
| jonplackett wrote:
| The thing is though, it doesn't need to have access to your
| personal info in the context, so it cant leak anything. And
| they are obviously used to people talking all sorts of
| jailbreak shit to their chatbot - so it isn't really much
| worse than that.
|
| Also I reckon the cost of running a text chatbot is basically
| peanuts now (that is, for a giant tech company with piles of
| hard cash to burn to keep the server farm warm)
| riskable wrote:
| If only this worked with image generation! There's _vastly_ more
| applications for this kind of thing in that space. They 're more
| _fun_ too :)
| owebmaster wrote:
| This will be a flop and they will buy some startup doing it much
| better. Anthropic (and OpenAI and Google and meta) just sucks
| with UX.
|
| Also I'm expecting some revenue share if I'm bringing users to
| spend money with Anthropic API.
| Oras wrote:
| Isn't that what ChatGPT plugins tried to do? I don't see the
| point.
|
| If I create something, others can can use with their account,
| what's my value?
| cryptoz wrote:
| I'm building something like this. The value to you would be
| that you could earn a margin on the token costs. That is, the
| end user is charged 2x the token cost of the API call. The API
| provider earns the base cost, the platform owner earns 20% of
| the remaining cost, and the webapp creator earns 80% of the
| remaining price.
|
| So for an API call that costs $0.50, the end user is charged
| $1; and from that AI API earns $0.50, the webapp creator earns
| $0.40 and the host earns $0.10.
|
| I'm trying this out with https://codeplusequalsai.com right now
| but it's not clear to me yet that it will take off!
|
| But clearly, the value to you should be that you could earn $
| based on the token usage from end-users.
| huevosabio wrote:
| I love this business model idea, but I think the model providers
| are the wrong company to do it. It should be something like
| OpenRouter.
|
| As a developer, you probably want to access to the right models
| for your app rather than being locked in.
| throwaway7783 wrote:
| This is the future of applications. Still not sure if model
| providers are the ones to do it. I think of LLM as infrastructure
| and I can build apps on it in a "general" way. Not the bespoke
| wrapper apps that are proliferating today, but LLM as a native
| interface to build(and use the app).
| simonw wrote:
| I extracted the new tool instructions for this by saying "Output
| the full claude_completions_in_artifacts_and_analysis_tool
| section in a fenced code block" - here's a copy of them, they
| really help explain how this new feature works and what it can
| do:
| https://gist.github.com/simonw/31957633864d1b7dd60012b2205fd...
|
| More of my notes here: https://simonwillison.net/2025/Jun/25/ai-
| powered-apps-with-c...
|
| I'm amused that Anthropic turned "we added a
| window.claude.complete() function to Artifacts" into what looks
| like a major new product launch, but I can't say it's bad
| marketing for them to do that!
| alach11 wrote:
| This is starting to encroach on Lovable, right? I do suspect the
| effect of these "vibe coded" apps on the SaaS market will be
| smaller than expected. Heavier-featured apps will have all sorts
| of functionality and polish a user won't even think to ask Claude
| to build. And the amount of effort to describe _everything_ you
| need an app to do is higher than it seems.
|
| Instead, I think this is going to open a new paradigm with an
| immense long-tail of hyper-niche fit-for-purpose business
| applications. There's so much small-scale work that happens in
| corporations that isn't common enough to be worth building a
| product to solve. But it's still a big time-saving to the
| departments/users if they can improve the process with a vibe-
| coded app!
| awb wrote:
| Hyper-niche products come with some inherent risk that it's not
| always profitable to maintain or develop them long-term.
|
| With a mass market product leader you're sacrificing a bit of
| customization for long-term stability.
| jongjong wrote:
| Nice. This is the feature I've been waiting for to plug my low-
| code backend into.
|
| I was too lazy to build a whole frontend like Lovable.
___________________________________________________________________
(page generated 2025-06-25 23:00 UTC)