Build your own company brain: the enterprise AI playbook from Stripe’s engineering team | Sharadh Krishnamurthy

September 7, 2026

AI Summary

5 min read

"Agents are very creative at bringing your infra down," says Sharadh Krishnamurthy, an engineering manager at Stripe. "It turns out that agents just dial up all your failure modes. It just multiplies the amplitude of problems you can get." Krishnamurthy and his colleague Anna Pomper built Kai, Stripe’s internal "company brain" and company-wide agent, from scratch. They did it not because off-the-shelf AI tools were lacking, but because the real bottleneck was governance: how to let 10,000 people use AI safely, effectively, and with the right context, without creating chaos. The episode walks through the architecture, the psychology of user friction, and the infrastructure investments that make enterprise AI actually work at scale.

Why Build Your Own? The Governance Problem

Continue reading the full summary in the app — free to try.

Read Full Summary →

Free • No credit card required

Listen to Audio Summary Open in App

Never miss an episode of How I AI

Get every new episode summarized in your inbox — free, ~5 minutes to read.

No spam. Unsubscribe anytime.

What you'll learn

1 (03:15) **Why Stripe Built Kai Instead of Buying** - The core problem: getting AI to everyone at a complex enterprise, which requires more than just a tool—it requires governance and context.
2 (05:30) **Kai's Bounded Context Engine** - How Kai knows who you are and what you're doing.
3 (07:42) **Projects as a Governance Mechanism** - The key differentiator: using projects to set AI policy and intent.
4 (10:58) **Live Demo: Building a Dashboard with Kai** - A step-by-step walkthrough of a common task: creating a data dashboard.
5 (14:43) **Making Your Data Warehouse "Agent-Ready"** - Key infrastructure investments that make data agents effective.
6 (20:42) **The Result: An Iterative Dashboard** - The outcome of the demo: a usable, interactive dashboard.
7 (25:04) **Rollout and Team Size** - How a tiny team built and scaled an enterprise-wide AI tool.

+ Full timestamped outline available in the app

Show Notes

Sharadh Krishnamurthy is an engineering manager at Stripe, where he helped build Kai, the company’s internal AI agent used by more than 10,000 employees every week. He’s worked across several of Stripe’s core infrastructure teams, including data and developer experience, which gives him a grounded, systems-level perspective on what it actually takes to make AI work at enterprise scale. He’s currently focused on the governance, skills, and infrastructure layers that let every Stripe employee use AI safely and effectively, regardless of their technical background.

What you’ll learn:

Why Stripe built Kai from scratch instead of buying, and what tipped the decision
What Kai knows about you by default and what you actually control
Why “projects” at Stripe are a governance mechanism, not just a folder
How Stripe structured its data layer so agents can query safely at scale
Why the infrastructure Stripe built for human developers turned out to be exactly what agents needed
How Kai’s skills platform lets any employee package a workflow, and what happens when you have 2,000 of them
What Sharadh learned the hard way when agents nearly took down production systems

—

Brought to you by:

DX—Engineering intelligence for the AI era

Hyperagent—Deploy fleets of agents that handle real work

—

In this episode, we cover:

(00:00) Introducing Sharadh

(02:46) Why Stripe built an AI agent (Kai) instead of buying tools

(05:18) What Kai knows about you (and what you can turn off)

(06:51) Projects as a governance layer

(10:04) Live demo: Kai builds a dashboard

(12:18) Tools, skills, and the secure sandbox

(17:22) Why Stripe has benefited so much from AI

(19:20) Agentic identity, load shedding, and rogue agents

(20:41) Iterating on the dashboard

(25:01) How they rolled out Kai across the team

(29:07) How projects work

(34:18) Bespoke agents for bespoke use cases

(35:58) The skill builder workflow

(40:40) Skill quality, evals, and telemetry

(43:01) Recap

(45:13) Lightning round

—

Tools referenced:

• Trino: https://trino.io/

• Anthropic: https://www.anthropic.com/

• Gemini: https://gemini.google.com/

• Cursor: https://www.cursor.com/

—

Where to find Sharadh Krishnamurthy:

LinkedIn: https://www.linkedin.com/in/sharadhk

—

Where to find Claire Vo:

ChatPRD: