Launch HN: Kenobi (YC W22) – Personalize your website for every visitor

Adding to what Rory said:

We don't know for sure. This is built on the intuition that websites are still a one-size-fits-all approach that makes no sense in an age where we have intelligence at our finger tips, able to process and reformulate information that speaks directly to people.

You could see this idea as being on the opposite side of the same spectrum as agentic browsing (which hasn't really taken off yet).

And thanks for the feedback! There are limitations in the quality of the personalizations in onboarding experience due to latency constraints. These get lifted the moment you create an account, and can start doing some more in-depth context gathering of your website and the types of visitors you're likely to get.

In general the case that we’re building for here is the one where we are able to do two things effectively: “streamlining” content, so that instead of 7 different use-cases on a maze of a brochure site, as a visitor you see the top one or two use case you actually care about, in way more detail.

Second, we want to show B2B visitors’ brands in context. I.e. showing you what it would look like if your company was using the service in question with social proof from your industry peers. We don’t have our image tech in the on-demand demo right now, but companies that we have helped pre-render copies of their site with dynamic images (especially e-commerce brands), found higher engagement on their outreach as a result.

I have no affiliation or horse in the AI Slop race but wouldn’t mind taking a shot at this. From my ignorant perspective, there are obvious common arguments against optimizing for generally inconsistent UI and UX, particularly how problematic and fruitless it can be.

However, I’d argue that there are some good arguments for this sort of optimization with what we know about potential consumer insights and how insignificant (but unique) aspects of an appeal can make or break someone’s interest. Or just given other evidence of how unique appeals can be effective (see things like Project Narwhal from Obamas first campaign.)

It’s also more tangential than argument above, but what we know about regular users of larger platforms indicates that a one size fits all approach doesn’t really fit all. Also consider that we really do have the tools/data now more than ever to offer a unique experience to users, and how that very concept of a unique user experience is what led to the proliferation of the platforms we use in the first place. There is a reason we preferred Google to Yellow pages and Google ad revenue took off — or atleast it wasn’t just about the profit motive of easy to access, updatable information. It was about using your insights and insights from others to craft unique results that appealed to you in a way that mass produced impersonal solutions did not do.

> You could show some images of what you mean by the product personalization

This is a great point, we've heard this elsewhere so I will be adding a section to our site for this. Thanks!

Damn, that’s unfortunate. We found the logs and looks like apollo returned empty for your domain. I just pushed an update that uses the same enrichment workflow as the rest of the app and looks like it correctly IDed your co. we're using gemini 2.5 flash-lite under the hood, and if it's not grounded it can come up with some whacky results! we'll shortly be shelving it for flash-3-lite as soon as we can

Glad to hear you enjoyed the UI/UX and experience! The ‘how’ is a key question - right now the visitor inputs what company they’re from, and with that info we send out a research agent that compiles a) context on that company, and b) combines that with the deeper research its already done on your domain — essentially it marries up what it knows about you, with what it quickly learns about the visitor, to the customise whatever sections of the website you’ve given Kenobi permission to transform

Obviously a lot of companies have vastly different personas, and this is a harder problem to solve which we are working on.

What they do is ask the visitor from which company they come from. Behind the scenes, this is what I imagine happens: - Kenobi scrapes that website and understands what it does - Has some prompts to transform the text in your website through the lens of your user: eg "Transform this text [your website text here] to appeal to a visitor from this company that does the following [scraped content here]"

Of course internally it might be much more complex than this but this is how I would do this if I had to build it.

really? My very first interaction was it prompted me for my company name, and the basic html text <input/> didn't behave correctly.

It had no highlight styling so if you wanted to highlight a portion of your input it would be impossible to tell what the current selection was.

Looks cool, not trying to hate, I just have a pet peeve around native elements having basic function/accessibility features removed during heavy styling.

Thank you yes, we perhaps should have made that a little clearer in the post body :')

We get asked this a fair amount and the way we’re strategising on it is to build more opportunities for the site owners to define context as part of the broad site research that goes into creating the interpolations.

If you would be willing to give us another chance please email product@kenobi.ai with the site you used and we can get the research context that it generated fixed! (This has been a bit of an issue for some users, when the research gathering agent goes down the wrong track)

We went through YC with Verdn, a donation software for ecom stores to give a small proportion of revenue to e.g. plant a tree with each sale: verdn.com

Felix handles our personalisation pipeline so will let him chime-in. We do some fast-scraping (cached where possible) to understand the host site, and pull in as much extra page data as possible. We also use other (firmographic) sources like Apollo.io.

Neat idea to track the technologies they've bought _recently_ though! I think capturing buying signals (and inferring intent that way) would be a neat addition to the pipeline!

We use apollo and gemini 2.5 flash lite with web search in a quick pass to ground and enrich data on the visitor. Right now, the queries are generic, as opposed to constructing more "tailored" queries based on what the host might be pitching to that visitor.

We're definitely going to be looking into finding more relevant signals on a case-by-case basis, and this kind of idea fits really neatly into that paradigm!

Also re: ‘deceptive advertising’ - if what you mean is that the output of the model will misrepresent what the host site actually sells/provides, that does happen on occasion, and it’s a top priority for us. We’re constantly working to reliably improve what Kenobi outputs in any given situation. It’s partially a research problem (i.e. deeply understanding the host website, and the nuances of their offerings, as well as research on the visitor, where the time window is seriously constrained), and it’s a model + prompting problem.

One of the ways we want to enhance Kenobi is to allow the host site to plug in more data sources (e.g. an FAQ, KB, etc). This helps solve the research problem, and it also increases the utility of the tool because more the very generic website can be be customized in more nuanced, specific, and esoteric ways, depending on the visitor.

Fair criticism! We actually got funded for a different idea (this was a pivot) so perhaps you're onto something.... Jokes aside -- and to address your points.... Privacy: Visitors currently opt-in and provide only the company they are from (no other PII). Security: Our current version handles only text (we have images + dynamic content in the works), but we do our best to build a sanitisation pipeline around this, it's the same kind of problem that any arbitrary-code widget builder needs to account for. Accessibility: I'm keen to hear what concerns or ideas you have here since we are interpolating content and copying existing structure (so that a11y is kept as intact as possible). Advertising: Companies choose to integrate this themselves on their own website, so if anything we see it as forming part of their marketing strategy.

Thank you for flagging! Are you able to share the input you tried so we can diagnose it for you?

Failed requests that are coming in (people are trying some wild inputs!!) we are keeping an eye on and adding to our edge cases pile to fix asap!

Thank you. Accessibility came up in another comment and to be honest we've only thought in terms of _preserving_ accessibility so far, not _improving_ it (as you're suggesting) -- would love to see if we could explore something along these lines soon even though right now we're focussed on B2B...

> if the buyer enters their company and the copy just changes into what we think they want, are they going to lose trust that the copy is a true representation of our focus?

Great point. That's pertinent to how we've been configuring the research → computing "intent" pipelines. Our focus right now is mainly just to streamline content and show brands "in context" as much as possible without having too much of an "opinion".

Your idea about showing how specifically the company could be helped + a use-case is lovely way of putting some of the more complex layout generation ideas we've been working on!

We think that in commercial buying there will still be a place for “discovery”, where B2B visitors gain from being able to independently digest public facing materials themselves. And that this will mean the adoption of agentic browsing is slower than people think.

However, we did already start experimenting with the agentic browsers like Atlas and Strawberry — I built a PoC for the former. But this is still very much experimental!

Edit:

Just wanted to add that your question is a prescient one and it is something we get asked a lot by investors, VCs etc, but hardly ever by people who run businesses with websites, or the people who visit them / do commercial buying.

Appreciate the candid feedback!

The number one request we have is to integrate deanonymisation, so you’re right on the money there. That’s coming in the next couple of weeks or so…

Wrt the changes being text-based for now, we do actually have image and complex element and layout generation working, but have kept it as an experiment for pre-rendered pages until we are confident we can get it right in most cases. (Some early beta users used Kenobi to send out in some cases thousands of customised landing pages with imagery)

We‘re also starting our on demand product with text only precisely because we want to hear what people think we should be working on next as we are a super small team of three!

Aah! Thanks for reporting! We’ve seen that in a couple of cases. Feel free to reach out to product@kenobi.ai with the site you’re using and we’ll look into it for you.

So right now (what we’re demoing), we do “on demand” personalisation, so there isn’t an SEO angle there really. However, we started with pre-rendering changes onto hardcoded URLs and while that did affect content, we didn’t see any SEO issues come up since these URLs were being used in campaigns only.

You shouldn't be(!) We have a very high bar set up to be met to be considered bot traffic. Sometimes we are at the behest of the model providers and there's way more latency + even timeouts under higher load.