Let anyone ship internal AI apps at WorkOS

AI Engineer17m 13s
0 comments · 0 votesOpen discussionClose discussion
Sign in to join the discussion

    Video summary

    Garrett Galow argues that building an AI-assisted prototype is easier than shipping an application that colleagues can reliably use. WorkOS pairs non-engineers with engineering mentors at hackathons and provides a shared CLI, templates and skillsAn AI agent skill is a reusable package of instructions, resources, and tool guidance for performing a bounded kind of work. so teams do not have to solve deployment from scratch.

    Garrett Galow describes the Wow CLI and Atlas platform: Git-based projects, Cloudflare Workers, D1 and KV storage, company app registration, Okta authenticationApplication authentication verifies the identity of a user or service before granting access to protected application capabilities., centrally managed secrets and request auditing. Examples include newsletter formatting and draft changelog tools. Granular role and group permissions are future work, not an already completed capability.

    Garrett Galow reports 278 registered applications, about 60 maintained applications and roughly 3.3 million weekly requests at WorkOS. These are company-reported figures. He describes plans for more data integrationsApplication integration connects software systems so data and actions can move through one useful workflow. and simpler Slack application setup.

    Original YouTube thumbnailWatch on YouTube

    Share this page

    Garrett Galow in a plain blue T-shirt on black beside the blue and white headline “Internal AI Apps”. Framed in blue with WWW.ARTIFICIAL-INTELLIGENCE.VIDEO, 8 October 2026 and duration 17m 13s.

    Garrett Galow explains how WorkOS pairs coding agents with a self-service deployment platform so non-engineers can ship usable internal applications.