News for hackers. Stuff that matters.

marcospassos

Show HN: CMS-Powered UI Components

https://croct.com

We just launched Croct Templates, a way to drop CMS-powered components into your app with a single command.It's like Shadcn, but for CMS, AB testing and personalization:* Built-in support for A/B testing, content editing, and dynamic logic * Works with existing projects (Next.js, React, etc.) * Supports community libraries via `npm://`, `shadcn-ui://`, etc.Example:```bash npx croct@latest use...

( Read More... | no comments | 2 points | on HN )
Yep, that's something I'd have to figure out.
The value is building the context itself.

Using MCP, this could be a method that would get the context to take decisions.

For example, here's an example of how I use it currently:

```

const context = await getContext();

const response = await generateText({ system: `Here's the user context: ${context}`, messages: [...] });

console.log(context);

// "First-time visitor using Google Chrome on a MacBook, browsing from San Francisco.

// Landed on the pricing page from a Google ad, clicked to compare plans,

// then visited the enterprise section before initiating a support chat."

```

It's like a session recorder for LLMs that captures rich user behavior and traits (like device, browser, location, and journey) and turns them into LLM context. Your agent or app instantly becomes more helpful, relevant, and aware without wiring up your own tracking and enrichment pipeline.

Exactly! Something like a tag you install and then query prompt-ready contexts.
Super interesting! However, it focuses on external sources rather than the user journey.
That's a good approach. But what I'm looking for is a bit different, more like Segment, but for LLMs. Something that when a user lands on your website, clicks around, and interacts with your app, you get a full behavioral context out of the box, including click path, location, language, currency, etc. You can then inject that context directly into your prompt so the LLM understands what the user is doing and responds without guessing or asking.
It might help with context generation. But honestly, most of the work is still in tracking, processing, enriching (different services, like IP location, etc), and all the plumbing around it.
Yeah, exactly. My whole point is to avoid doing all that. It adds up fast. What I really want is something that handles the heavy lifting end-to-end: tracking, interpreting, and outputting a prompt-ready summary like:

"The user landed on the pricing page from a Google ad, clicked to compare plans, then visited the enterprise section before initiating a support chat."

Ask HN: Building LLM apps? How are you handling user context?

I've been building stuff with LLMs, and every time I need user context, I end up manually wiring up a context pipeline.Sure, the model can reason and answer questions well, but it has zero idea who the user is, where they came from, or what they've been doing in the app. Without that, I either have to make the model ask awkward initial questions to figure it out or let it guess, which is...

( Read More... | 18 comments | 9 points | on HN )

Show HN: Dynamic headless CMS with built-in CDP, AB testing and personalization

https://docs.croct.com/introduction/getting-started

Hey HN,I'm a developer and long-time OSS contributor. Over the years, I've implemented tons of headless CMSs to give product and marketing teams more autonomy. But there's always been a gap with CMSs when it comes to user interfaces.I kept running into the same issues: poor developer experience, bad performance, no support for dynamic content, and needing vendors for AB testing or...

( Read More... | no comments | 19 points | on HN )