Build safer agent workflows with Convex types and MCP
From the video description
During AI Agents + Full-Stack demo nights at Convex, Tom Ballinger shows how Convex helps developers ship applications with fewer moving parts and safer agent workflows. Tom explains why end-to-end types across database, server, and frontend give LLM agents faster feedback and more predictable behavior than piecing together a traditional stack. You will see a simple chat app wired through Convex, a Model Context Protocol (MCP) demo, and a frank look at prompt injection, token flow, and permission design.
Topics
Sources
Video by Convex, played through YouTube.
- Indie Picks
Data and selection notes
Indie Picks uses video metadata for classification. The description above is an uploader excerpt, not an independent review.
Indie Picks: Independently collected SaaS and AI product videos, organized by a founder handbook. Topics and relevance are metadata-indexed; full-video editorial review has not been completed. Descriptions are uploader excerpts where available.
Views, duration and playback status refresh separately from the published catalog. When an update fails, existing data remains visible.
Selection checks
- SaaS & AI candidates: Matches the configured criteria
- Editor-approved picks: Editorial review is required