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.
reticulates 19 minutes ago [-]
I think there’s been somewhat of a mask-off moment post-AI in which we’ve realized that a lot of the careful and considered output we’ve come to expect of some companies wasn’t out of a respect for the craft or desire to produce “good work”.
Pre-AI the attitude was: if we are going to do something, it is going to use up our precious resources, so we should do it well, because our staff are capable and the marginal cost of doing it well vs. doing it at all is negligible.
Post-AI: we can churn out things quickly, we don’t have to worry about resource allocation, churn churn churn!
Ultimately, it is pragmatic for businesses to behave this way, but it is a shame for those who love the craft. I think we took for granted the beautiful ornate hand carved furniture era of software engineering. We are now in the ikea era.
ilaksh 18 minutes ago [-]
Maybe they have jobs to do so they offloaded a lot of the presentation work to AI, assuming reasonable people would not judge based on surface level copy style.
anthonypasq 1 hours 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?
edlebert 20 minutes ago [-]
I worked there. All the internal tools are amazingly polished. I’ve never seen anything like it.
quadrifoliate 1 hours 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.
jstummbillig 21 minutes ago [-]
It's possibly a cost benefit thing. Moving quickly with AI leaves blood splatter, but if you get enough in return you decide it's worth it anyway.
away0g 23 minutes ago [-]
Its always more likely the company pushing the PR is less polished than they present themselves.
lukebuehler 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.
You wrote your readme yourself. It shows. So refreshing and i was able to finish it too.
lukebuehler 36 minutes ago [-]
Thank you. Yes, I did. There might be some AI-isms in there, because agents just can’t help themselves to dump their arcanae in there.
hmokiguess 2 hours ago [-]
Your project seems way better than the stuff they built, nice work.
sebmellen 54 minutes ago [-]
Wow, where do you work? Can we talk? Looking for smart people!
neilellis 2 hours ago [-]
I like it, very smart for agents at scale.
bob1029 28 minutes ago [-]
> Building a standalone agent product wouldn't work. Instead, it would force users out of their natural workflows and into a new app.
I am finding the opposite to be true with one of my clients. They explicitly want a new channel. The chat-style UI/UX is vastly preferred over their poorly maintained internal tooling.
I suppose if you are Stripe actual, most things would be well designed and more difficult to abandon. Most places aren't like Stripe.
The hard part is bringing everything that matters to the new channel, but it's certainly feasible to do this. I am doing it right now. We will soon be able to delete hundreds of wildly inconsistent cshtml views and related controllers in favor of a single agent tool that applies json patches. This will easily cover 99.9% of use cases. A manual json editor is retained for the rare case where we need some multi-megabyte merge operation.
godzillafarts 45 minutes ago [-]
I want to read this, but the ever-changing linear gradient of the background is too visually distracting. I tried to get around it by highlighting text I want to read, but since the background is changing underneath it, so is the highlight. My eyes hurt.
ck45 27 minutes ago [-]
Does your browser have a reader mode? Looks quite decent in Safari and Brave
hek2sch 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 2 hours 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”.
rubenfiszel 1 hours 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.
olliebrkr 2 hours ago [-]
Dang it, I just named my newborn son Kai. At least I didn’t go with Alexa..
reticulates 1 hours ago [-]
Don't worry, thanks to nominative determinism, you've secured your kids employment years in advance
graypegg 1 hours ago [-]
It’s a cool name! Don’t let Stripe make you doubt that haha
atonse 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 2 hours ago [-]
All hand written or did you have any underlying libraries that you used?
atonse 50 minutes ago [-]
Mostly custom. Full data model and full web and mobile app to help run day to day operations.
The agent has switched a few times, initially NanoClaw, then Hermes, and now Vercel's Eve (maximum customizability).
NextJS/Shadcn web app, postgres db, eve agent layer, MCP tools (over 100 so every single thing can be done by an agent), SwiftUI mobile app, etc.
Integrations with gmail, gcal, gdrive, quickbooks, using mdx for the wiki displays (so we have rich diagrams, 3d models, etc).
> 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 35 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.
Bluestein 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 1 hours ago [-]
There's quite a bit of cool stuff in the console too! The one in the top right corner
wiether 2 hours ago [-]
I just hear Steve Ballmer yelling
postexitus 1 hours ago [-]
Oldies let's gather here.
Bluestein 2 hours ago [-]
[Bad mental image ... can't unsee ...] :)
anonzzzies 3 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 2 hours ago [-]
To make your comment more high value, could you explain why you think langchain is bad?
ramraj07 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 1 hours 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 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 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 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 2 hours ago [-]
Yes, I also thought it's crap the moment I saw they need langchain to develop a harness.
weego 2 hours 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 2 hours ago [-]
It might also suggest they went with the first LLM recommendation, like Anthropic choosing React for Claude Code.
infecto 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 2 hours ago [-]
Totally, I find LangChain is the Vercel of ML
mdrxy 1 hours ago [-]
For what reasons?
hmokiguess 1 hours 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.
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.
sceptic123 2 hours ago [-]
In the first paragraph:
> No existing tool could handle the data security requirements and specific workflows Stripe needed
nozzlegear 1 hours 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.
olliebrkr 2 hours ago [-]
Dammit, I just named my newborn son Kai.
doctorpangloss 1 hours ago [-]
haha stripe's example prompt is "Create an event"
quijoteuniv 2 hours ago [-]
But no darkmode support? … :D
ckrapu 2 hours ago [-]
The article reads like slop, to be honest.
eis 47 minutes ago [-]
Hope this comes over as constructive criticism:
1. The whole interface feels way too vibe coded with tons of unneeded stuff. Why does it have a console and snake game built in? Why does it have annoying sounds? Why is it full of AI slop writing? The latter is especially confusing because the first person listed under authors is a "Technical Writer". I guess the interface is the general stripe.dev page not exactly related to Kai but the post definitely is pure AI slop writing.
2. It seems to claim things that might not be substantiated like the following: "When Account Executives use Kai, they produce 2x the sales activity, create 17% more opportunities, generate 26% more revenue opportunities, and close 39% more deals when compared to the same sellers in weeks they don't use it." Correlation is not causation. More engaged, better sales people might just also use more tools like this one, it doesn't mean all the increase in sales is because of the tool.
3. the post talks a lot about how great this tool is but it describes nearly nothing of value to the outsider who can't access it. What were the valuable lessons learned? What's neat about it? There is not much meat imho.
It doesn't live up to my usual expectations from Stripe.
TimVasil 1 hours ago [-]
[dead]
pushpendraw 2 hours ago [-]
[dead]
dominotw 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.
Rendered at 17:15:34 GMT+0000 (Coordinated Universal Time) with Vercel.
- 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.
Pre-AI the attitude was: if we are going to do something, it is going to use up our precious resources, so we should do it well, because our staff are capable and the marginal cost of doing it well vs. doing it at all is negligible.
Post-AI: we can churn out things quickly, we don’t have to worry about resource allocation, churn churn churn!
Ultimately, it is pragmatic for businesses to behave this way, but it is a shame for those who love the craft. I think we took for granted the beautiful ornate hand carved furniture era of software engineering. We are now in the ikea era.
unless you work there how would you know this?
It's always possible that in reality they were always a bit less polished behind the scenes though.
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
I am finding the opposite to be true with one of my clients. They explicitly want a new channel. The chat-style UI/UX is vastly preferred over their poorly maintained internal tooling.
I suppose if you are Stripe actual, most things would be well designed and more difficult to abandon. Most places aren't like Stripe.
The hard part is bringing everything that matters to the new channel, but it's certainly feasible to do this. I am doing it right now. We will soon be able to delete hundreds of wildly inconsistent cshtml views and related controllers in favor of a single agent tool that applies json patches. This will easily cover 99.9% of use cases. A manual json editor is retained for the rare case where we need some multi-megabyte merge operation.
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”.
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.
Happy to be in such good company!
The agent has switched a few times, initially NanoClaw, then Hermes, and now Vercel's Eve (maximum customizability).
NextJS/Shadcn web app, postgres db, eve agent layer, MCP tools (over 100 so every single thing can be done by an agent), SwiftUI mobile app, etc.
Integrations with gmail, gcal, gdrive, quickbooks, using mdx for the wiki displays (so we have rich diagrams, 3d models, etc).
We write about it here: https://kznconsulting.com/work/how-we-run-kaizen
By force or by choice?
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.
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.
seems every company that has spare engineering resource all builds such thing internally
Stripe probably WANTS to be opinionated about how their company works with the tools.
> No existing tool could handle the data security requirements and specific workflows Stripe needed
Spotify built some nonsense like this too and made ridiculous claims that it saves 90 percent of tokens. I guess anything goes these days.