Things Sharadh Krishnamurthy Has Said on Podcasts

Krishnamurthy was demoing Stripe's internal agent platform and explaining why tool permissions are scoped to projects rather than set per person. Claire Vo had just raised the cost of making every employee manage their own connectors and approvals. His answer is a claim about people rather than software: put an approval prompt on every tool call and eventually everyone clicks the wrong button.

Lenny's Newsletter · 2026-09-07 Permalink → Listen →

Lenny's Newsletter

Sharadh Krishnamurthy

…really good. They're very creative. So we've got to put some restrictions on them so they don't go rogue, right? And projects help us decide. I'd also don't want this to be happening for every person at Stripe. That would be kind of frictionful. So projects are again drawing the boundary around it.

Claire Vo

…this connector, connect to this data? And so I do think one of the benefits right now of teams building their own thing is. They can really think about bespoke agents for bespoke use cases, but kind of hide all that complexity from the end employee, the end teammate, and just let them get to work.

Sharadh Krishnamurthy

…were speaking about bespoke agents, and I showed a little bit of this earlier, Kai looks like a single product. It really isn't. It's like the icing on top of a multi-layer cake, and each of those layers can be like customized to work at the enterprise, right? So, 100% agree that the notion of both customization, but lowering the cost of management, the cost of ownership, and just the friction. If you put too much friction in front of people, they're just going to do unsafe things because that's how humans are, right? We don't, if I showed you this every single session for every single tool, eventually you're going to press the wrong button, right? So, really thinking through that is a big part of what we're trying to do here. So, that's projects and why I love projects as a unit of governance. Let's hop back really quickly to the skill builder flow that I spoke about. Again, we made that dashboard. We want…

Claire Vo

again.

Sharadh Krishnamurthy

This is what happens if you prepare too well for demos. This

Claire Vo

is when you do it live. I mean, we believe you. I think what you're showing here, great. You have kind of a skill creator skill or tool. You have a specific spec that you're using to ensure that it's both written well generally for agents, but also written well very specifically for the Kai…

Speaker names come from our own diarization. The position is estimated from where the line sits in the episode.

“It turns out that agents just like dial up all your failure modes. It just multiplies the amplitude of problems you can get…” — Sharadh Krishnamurthy, How I AI

Krishnamurthy is describing what happened when Stripe pointed internal agents at its own data and infrastructure. He is not warning about a hypothetical: in the same answer he says agents went rogue and nearly took down core systems before the team caught it. His point to Claire Vo is that agents do not introduce new categories of weakness, they find the ones already there faster.

How I AI · 2026-09-07 Permalink → Listen →

How I AI Around 15:30 into the episode

Sharadh Krishnamurthy

…were made for humans, but have held up really well for agents because terms are the reasoning through it, agents have the same problem. They can answer the question, but they have no idea if it was the right query or the right table. And these investments have paid off in helping guard that.

Claire Vo

…hardening investment, performance investment, not sexy, not what people are thinking about when you're building these data agents, but actually allow agents to do a really effective job because you don't worry about like, you know, turning over your data warehouse because an agent is hammering it.

Sharadh Krishnamurthy

…yet, right? But thinking about how do we say that, you know, this is an agent and this is what it's trying to do. Like what is the use case it's trying to use as it goes around doing its thing in our infrastructure and using this. That as a way to think about priorities and load shedding and all of that good stuff. Again, not super sexy, very like deep infra stuff, but the same principles apply. It turns out that agents just like dial up all your failure modes. It just multiplies the amplitude of problems you can get, right? And the investments, I wouldn't claim that we did not have any issues. We definitely had a bunch of issues where when we started doing this, like there were agents that went rogue. There were agents that may have almost taken down core systems, but we caught it in time. And now we've hardened those systems as well.

Claire Vo

I love it. Okay, so we've yapped while Kai ran. Let's show what Kai actually generated using these skills and tools in Sandbox.

Sharadh Krishnamurthy

Yeah, of course. So here's what you see. You see that, you know, Kai adoption is looking good. And this is something I'm personally super happy about. Like pretty much everyone at Strike uses Kai, like 86 plus percent of the company now. So really AI for everyone, which is how we started out this…

Claire Vo

it, right? I don't know a single marketing person that doesn't either want some sort of app built or some sort of dashboard. You have product market fit. That leads me to my next question, which is: how do you roll out? I'm just curious, kind of, you know, inside inside the doors of Stripe, how do…

Speaker names come from our own diarization. The position is estimated from where the line sits in the episode.

Things Sharadh Says on Podcasts

Where to Find Them

What They Said

Collections They Appear In