Be sure to checkout convex for a great backend for your applications: http://convex.dev/?utm=webdevcody

Code at https://github.com/webdevcody/convex-title-generator

Workflow:
https://www.convex.dev/components/workflow
https://stack.convex.dev/durable-workflows-and-strong-guarantees

Agent:
https://stack.convex.dev/ai-agents
https://www.convex.dev/components/agent

Timestamps
00:00:00 Demo
00:04:47 Code Setup
00:11:32 Download Transcripts
00:18:16 Generate Summary
00:22:11 Workflow Component
00:30:32 Story Telling Agent
00:36:34 Theo Agent
00:40:36 Reviewer Agent
00:54:40 Storing Titles
00:57:24 Passing Summary
01:03:09 Build out UI
01:06:27 Adding Schema
01:12:43 Adding more Agents

My Courses
⚛️ https://beginner-react-challenges.webdevcody.com

My Applications
🎥 https://thevideocrafter.com
🤖 https://projectplannerai.com
🎨 https://icongeneratorai.com
🧟 https://survivethenightgame.com/

Useful Links
💬 Discord: https://discord.gg/N2uEyp7Rfu
🔔 Newsletter: https://newsletter.webdevcody.com/
📁 GitHub: https://github.com/webdevcody
📺 Twitch: https://www.twitch.tv/webdevcody
🤖 Website: https://webdevcody.com

Web Dev Cody

The post explains how to build complex AI agent workflows using Convex. It highlights the creation of a YouTube title generator that uses multiple AI agents to generate, review, and rewrite video titles based on specific criteria. Convex's real-time database and workflow components make stitching together various AI tasks and handling asynchronous jobs straightforward. The process involves setting up a backend with Convex, integrating AI agents for different functions, and utilizing Convex's features to manage the workflows efficiently.

How to Code Complex AI Agent Workflows using Convex