
DS Agent: Snap's AI Data Scientist
Part 1 of a series on DS Agent, the data-science agent platform built inside Snap. This post stands on its own; later posts cover the hosted web app and how we evaluate quality.
Specs

Building SPECS Experiences Faster
We built a working spatial Lens (app) on SPECS in about a day, then did it six more times. The speed didn't come from a new engine. It came from pairing two mature toolkits with an AI that can drive Lens Studio directly. Here's how that loop works.

Casper: Snap’s fleet of friendly AI teammates
This is Part 3 of a three-part series on how Snap is building AI-assisted software development workflows. This post is about Casper, our autonomous remote AI agents that take a task and hand back a reviewable pull request.
Specs

World-scale Outdoor AR Tracking with GNSS
Augmented reality (AR) has the power to transform the world around us, and its true potential is unlocked when digital content can be reliably anchored to specific, real-world locations.
Snap Inc.

Code Search: How Agents search across Snap’s codebase
This post is about Code Search, the retrieval layer that lets both agents and engineers explore and understand all of Snap's code

Measuring Spatial Intelligence in LLMs
Today we’re open-sourcing Spatial Benchmark, a benchmark for measuring how well language models reason about 3D space.


