Home / Companies / WorkOS / Blog / Post Details
Content Deep Dive

What 21 five-minute demos looked like at WorkOS Demo Night

Blog post from WorkOS

Post Details
Company
Date Published
Author
Noelle Festa
Word Count
3,374
Company Posts That Month
89
Language
English
Hacker News Points
-
Post removed?
No
Summary

WorkOS’s second San Francisco Demo Night featured 21 live, slide-free, non-promotional five-minute demonstrations focused largely on the infrastructure needed to make AI agents useful, secure, and deployable. Projects included Carbon Code, an AI coding agent that edits its own source on emulated Mac OS 9; hosted and collaborative agent control planes such as Omnara and Open-Inspect; remote interfaces through mobile apps, terminals, voice, and Apple Watch controls; and security systems including Sesame and Super Self that keep credentials outside agents’ reach and enforce network or policy boundaries. Other presenters examined custom benchmarks and open vendor comparisons, MCP-based integrations for agents operating across ChatGPT, Claude, Slack, Teams, and LinkedIn, and local-first model and embedding systems that run without cloud APIs. Demos also highlighted supporting tools such as deterministic lint rules for agent-generated code, task-specific context compilers, and unified data-query layers, while Sangria showed a consumer-facing purchasing agent embedded in iMessage. Across the presentations, the recurring conclusion was that agents themselves are becoming less central than the surrounding scaffolding for execution, context, evaluation, access control, reliability, and human oversight.

Trends Found in this Post
Trend Post Mentions Total Month Mentions Posts Companies MoM
MCP 6 8,107 809 199 -26%
LLM 2 4,718 960 222 -38%
Vector Search 2 2,312 357 123 +3%
AI Coding Assistant 1 1,400 436 132 -25%
Developer Experience 1 413 218 82 -30%
Secrets Management 1 1,985 445 125 -23%
Voice AI 1 2,814 261 53 -37%
Use This Data

Use this post, company, and trend context to find content marketing opportunities, perform competitive analysis, or address product feature gaps via the Plushcap MCP server or the Plushcap API.