Learn 90% of Building AI Agents in 30 Minutes
Not only have I built hundreds of AI agents myself, I've seen other people build thousands of AI agents for every use case under the sun. The people who are the most successful are the ones who don't overcomplicate it - and I want that to be you too. It's easy to think building AI agents is super complicated, but honestly you can learn 90% of what you need to know (and what to focus on) from this video. No matter how you're building your agents, I'll show you here what you need to think about, and more importantly what you shouldn't worry about when you're first creating your agent. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Platforms mentioned in this video (most are open source!): - Synk for automated AI-native app security: https://snyk.plug.dev/xgmYQhO - Guardrails AI for agent guardrails: https://github.com/guardrails-ai/guardrails - Pydantic AI for the AI Agent framework: https://ai.pydantic.dev/ - Mem0 for long term memory: https://mem0.ai - Langfuse for agent observability: https://langfuse.com/ - Docker for deployment: https://www.docker.com/ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - If you want to master AI coding assistants and learn how to build systems for reliable and repeatable results, check out the new Agentic Coding Course in Dynamous: https://dynamous.ai/agentic-coding-course - Here is the repo for the super simple AI Agent we built in this video: https://github.com/coleam00/ottomator-agents/tree/main/ai-agent-fundamentals - Here is the system prompt template I covered: https://docs.google.com/document/d/1-OB4ZMg20pIRVmLw50TCclzQWCATaezV_cx73Muw5wU ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Thanks to Snyk for working with me on the security portion of this video! It's been a pleasure and I really do believe Snyk is on the forefront of software/agent/AI coding security especially with their new MCP server: https://docs.snyk.io/integrations/snyk-studio-agentic-integrations#local-and-remote-mcp-server-support ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 00:00 - Master the First 90% of Building AI Agents 01:38 - The 4 Core Components of AI Agents 03:06 - The First 3 Steps of Building an Agent 04:09 - Building a Basic AI Agent Together Live 09:17 - Choosing Your LLM 10:34 - Crafting Your System Prompt 12:20 - Creating Your Tools (Agent Capabilities) 14:26 - AI Agent Security 15:32 - Guardrails AI 16:45 - Snyk MCP Server 19:45 - Managing Agent Context (Memory) 22:05 - Mem0 for Long Term Agent Memory 23:53 - Agent Observability (with Langfuse) 26:28 - Agent Deployment (with Docker) 28:41 - Final Thoughts ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Join me as I push the limits of what is possible with AI. I'll be uploading videos weekly - at least every Wednesday at 7:00 PM CDT!
