Stripe's Knowledge AI Platform

lltononro about 3 hours ago 48 commentsRead Article on stripe.dev

DE version is available. Content is displayed in original English for accuracy.

⚡ Community Insights

Discussion Sentiment

78% Positive

Analyzed from 1112 words in the discussion.

Discussion (48 Comments)Read Original on HackerNews

quadrifoliate•44 minutes ago

Stripe is the company I usually hold up as the exemplar of polished internal tools. Hopefully this is taken the right way and I don't want to be negative towards the teams working on this, but I see a distinct lack of polish in these tools and presentations. Some examples:

- Unnecessary AI copy throughout the interfaces like "Browse, discover, and manage skils for your agents", "No favorites yet — hover a card and click the star to pin it here", "One execution environment, shared across agents". These instantly read as AI copy and decrease my enthusiasm.

- Inconsistent, AI-sloppy look-and-feel with different typefaces spattered across the interface

- The session metrics slide looks busy and AI-generated. It repeats 360,014 sessions in one of the cells at the top, but also has a "360K sessions" in the heading

I don't know if I'm the only one that notices this stuff, or whether others see it too.

anthonypasq•41 minutes ago

> Stripe is the company I usually hold up as the exemplar of polished internal tools.

unless you work there how would you know this?

quadrifoliate•40 minutes ago

They have published a bunch of stuff about their internal tools in the past. Look up https://stripe.com/blog/stripe-home and compare it to this, as an example.

It's always possible that in reality they were always a bit less polished behind the scenes though.

lukebuehler•about 2 hours ago

Very cool demonstration of managed agents built for the needs of their own business.

I think this is where a lot of companies are going to go: on-prem platforms that give various teams access to agents that are as powerful as coding agents, but much more managed and governed.

I'm betting on this with my open source project, Lightspeed: https://github.com/smartcomputer-ai/lightspeed

hmokiguess•about 2 hours ago

Your project seems way better than the stuff they built, nice work.

neilellis•about 2 hours ago

I like it, very smart for agents at scale.

rubenfiszel•about 1 hour ago

It's very close to the direction we're taking for windmill.dev, we call it "operator builders" rather than focus on "knowledge graph" which the article is very light on details of.

What I'm mostly reading is a developer platform and runtime where users can build agents that can run tools and for that you need a secure code runtime, ACL/permissions, easy way to build apps or what cloudflare OS call gadgets. We're betting on this too at https://github.com/windmill-labs/windmill, very curious to see if that's the future for most enterprise and if a model where everyone vibe-code/fork cloudflare OS to their enterprise need is the future, or a more exhaustive/enterprise platform like ours does.

hek2sch•about 2 hours ago

I read a buzz word "Knowledge AI Platform" but I did not see any specific feature helpful for knowledge management like verification or transparency. It is more like any generic Agent builder. Maybe it meant to justify building something internally.

ofjcihen•about 1 hour ago

None of these have been especially impressive.

I think that’s because none of them go past “I’ve set up agents to be orchestrated this way” and that’s about as impressive as “look at my cloudformation template”.

docheinestages•37 minutes ago

> Within two weeks of our April launch, most of Stripe was using Stripe's Knowledge AI Platform, also known as Kai.

By force or by choice?

vaughnegut•12 minutes ago

By choice. I currently work at Stripe (opinions my own, I'm just some guy) and was here when it released. It's a genuinely useful tool, which explains the widespread adoption.

olliebrkr•about 2 hours ago

Dang it, I just named my newborn son Kai. At least I didn’t go with Alexa..

reticulates•about 1 hour ago

Don't worry, thanks to nominative determinism, you've secured your kids employment years in advance

graypegg•about 1 hour ago

It’s a cool name! Don’t let Stripe make you doubt that haha

atonse•about 2 hours ago

Ahhh I built an internal set of agents to run our company (finances, all info in the karpathy-style LLMWiki and a database of clients, contracts, billing, time tracking, all managed by MCPs, etc) and it's also called Kai (company name is Kaizen)

Happy to be in such good company!

infecto•about 2 hours ago

All hand written or did you have any underlying libraries that you used?

Bluestein•about 2 hours ago

Somebody probably mentioned this already or maybe its just me but: The "endless scroll" this page does is neat, to say the least.-

a_crowbar•about 1 hour ago

There's quite a bit of cool stuff in the console too! The one in the top right corner

wiether•about 2 hours ago

I just hear Steve Ballmer yelling

postexitus•about 1 hour ago

Oldies let's gather here.

Bluestein•about 2 hours ago

[Bad mental image ... can't unsee ...] :)

anonzzzies•about 2 hours ago

TIL people still fall for eh I mean use Langchain. Sorry, low value comment; I don’t know how to do that differently; it is such bad garbage since day one and strangely it did not improve. Sorry anyway for the comment, at least it was not LLM generated?

bogdanoff_2•about 2 hours ago

To make your comment more high value, could you explain why you think langchain is bad?

ramraj07•about 2 hours ago

It (and most other systems) abstract the wrong concepts when you want to create an agent. They promote what was likely never a great strategy but even parsimoniously what are strategies that were good ideas months or a year back.

For example how langchain or whatever else handles subagents and deep research is laughable even today.

So whats the recommendation? Just use pydantic and code everything up yourself. Maybe strands I dont know.

mdrxy•about 1 hour ago

Which specific strategies do you think are outdated, and what would you recommend instead? This sounds more like a criticism of older versions of LangChain than its current APIs. The post also uses deepagents, a separate package in the same ecosystem. Is there something in the current implementation of either that you’re referring to?

mawadev•about 2 hours ago

I have a hard time keeping up with the space. Is langchain old news? Is there a page that kind of shows what the status quo for tooling is?

infecto•about 2 hours ago

+1 would love to know as well. I have generally found the open source space to be lacking in this area and hoping it catches up!

simlevesque•about 2 hours ago

There's like 1000 langchain alternatives and none are good, they're all vibe-coded unstable projects.

I use Apache Burr but it's not as good as LangChain. I just don't want to use software whose website has a pricing page if it's not a SAAS.

realsarm•about 2 hours ago

Yes, I also thought it's crap the moment I saw they need langchain to develop a harness.

weego•about 1 hour ago

The fact that Stripe are touting a production product that (at face value) benefits their business seems to suggest that maybe crap is subjective and as ever, being overly opinionated in an emerging space might actually be a blocking mindset rather than a positive one.

owebmaster•about 1 hour ago

It might also suggest they went with the first LLM recommendation, like Anthropic choosing React for Claude Code.

infecto•about 2 hours ago

Instead of spending half the comment reflecting on your post why not point out what you don’t like about it or some better alternatives?

hmokiguess•about 2 hours ago

Totally, I find LangChain is the Vercel of ML

mdrxy•about 1 hour ago

For what reasons?

hmokiguess•about 1 hour ago

It's a lot of sugar and high level abstractions on top of existing things, I find using the existing things not that complicated or difficult and I struggle to see the value on using the framework as it doesn't sit well with my way of abstracting the stack.

wenbin•about 2 hours ago

so is it like CloudflareOS ? https://github.com/cloudflare/cloudflare-os

seems every company that has spare engineering resource all builds such thing internally

nozzlegear•44 minutes ago

Somewhat interesting how the design of Stripe's developer-focused landing pages used to be the "cream of the crop," so to speak, but now they just look like Claude run amok. I wonder if the web design "skills" for Claude, and other LLMs, were overly trained on Stripe.

ianpurton•about 2 hours ago

They don't really say why they built their own rather than using one of the open source solutions like https://github.com/bionic-gpt/bionic-gpt

sceptic123•about 2 hours ago

In the first paragraph:

> No existing tool could handle the data security requirements and specific workflows Stripe needed

NichoPaolucci•about 2 hours ago

Size and scale, I would think. An out of the box solution probably doesn't quite have the same capabilities as something they can (and now have to) manage in it's entirety.

Stripe probably WANTS to be opinionated about how their company works with the tools.

adithyassekhar•about 2 hours ago

This site could use a bit more line height, more paragraphs, or less text overall.

doctorpangloss•about 1 hour ago

haha stripe's example prompt is "Create an event"

olliebrkr•about 2 hours ago

Dammit, I just named my newborn son Kai.

quijoteuniv•about 2 hours ago

But no darkmode support? … :D

ckrapu•about 2 hours ago

The article reads like slop, to be honest.

dominotw•about 2 hours ago

oh not these guys again. These are just so idiotic.

Spotify built some nonsense like this too and made ridiculous claims that it saves 90 percent of tokens. I guess anything goes these days.