Databricks and Stripe Projects: Infrastructure Built for Agents

AI coding agents can create, scaffold, and deploy a full-stack app in minutes. But provisioning application infrastructure still requires human effort and can slow you down significantly.

Humans are still required to provision services, navigate UIs, configure accounts, enter credit card info, etc. Every manual step is one where autonomous app development fails - manual provisioning is no longer just a friction point, but a clear gap in AI app development.

Databricks has partnered with Stripe Projects to close that gap. 

Introducing agentic provisioning of Neon databases using Stripe Projects. 

Today Stripe is launching Stripe Projects - a new agent-first CLI tool that allows AI agents to discover, provision, and pay for Neon databases. It’s the first fully-agentic provisioning tool of its kind.

Databricks is a proud launch partner, bringing Neon databases seamlessly to every AI development environment. Agents can now get a production-ready Neon Postgres database in under 350ms, without any human interaction.

Lakebase and Neon: a foundation for autonomous infrastructure

To allow AI agents to manage infrastructure independently, the underlying database must be as flexible and programmable as the agent itself. Lakebase architecture, developed by Neon, is the first serverless Postgres database designed for the AI era. By decoupling compute from storage, agents can create, build, and tear down OLTP databases in seconds.

This agent-first architecture is built on three core technical pillars:

• Serverless Scaling and Scale-to-Zero: Traditional databases require manual provisioning and "always-on" costs. Lakebase compute resources dynamically adjust to match traffic spikes in real-time and automatically scale to zero when idle. For agents, this means they can spin up production-ready environments without worrying about capacity planning or wasted spend.
• Instant Database Branching: Using zero-copy cloning, agents can create isolated branches of production data in seconds. This allows autonomous systems to safely test code, run migrations, or experiment with new prompts against live data states without risking the primary production environment or incurring massive storage overhead.
• It’s Postgres: Agents understand Postgres better than any other OLTP database, meaning that software development using the Lakebase architecture is quick and easily automated.

By treating the database as a programmable, on-demand service rather than a static piece of hardware, lakebase architecture allows agents to bridge the gap between scaffolding an idea app and running a production application.

Getting started with Neon and Stripe Projects

Learn more about using a coding agent with your Stripe Projects account.

More collaborations with Databricks and Stripe

In addition to Stripe Projects, Databricks is also announcing the Stripe Data Pipeline, now available on the Databricks Marketplace. Learn more about how Stripe customers can analyze payment and business data directly in their Databricks account - no ETL required.