Agentic AI engineering
LLMs, tools, RAG, agents, MCP, evals and shipping.
- AGT.01Roles and the career pathunderstand the AI engineering roles and plan the move from frontend.2 concepts
- AGT.02LLM fundamentalsexplain how LLMs work well enough to make engineering decisions.7 concepts
- AGT.03Python for JavaScript developersbe productive in Python for AI work.4 concepts
- AGT.04Robust LLM API callscall LLM APIs reliably, cheaply and observably.3 concepts
- AGT.05Prompting and structured outputwrite prompts that work and get machine-readable outputs.3 concepts
- AGT.06Tool calling and retrieval (RAG)give models tools and knowledge.5 concepts · 1 ready
- AGT.07Agents, workflows, frameworks and MCPbuild agents only when they are the right tool, with the right framework, using MCP.4 concepts
- AGT.08Durable execution, human-in-the-loop and memorybuild long-running, reliable agents that people can supervise.3 concepts
- AGT.09Evals and LLMOpsmeasure and operate LLM systems.4 concepts
- AGT.10LLM securitybuild LLM systems that resist the OWASP LLM risks.3 concepts
- AGT.11Agent UX and multi-agent systemsdesign agent experiences and know when multiple agents help.2 concepts
- AGT.12Fine-tuning and local modelsknow when and how to fine-tune and run open models.2 concepts
- AGT.13Shipping an AI serviceput an AI feature into production responsibly.2 concepts
- AGT.14AI interviews, portfolio and the 24-week planget hired as an AI engineer.3 concepts
- AGT.15Forward deployed engineeringpass the customer-scenario rounds of forward deployed engineer (FDE) loops and work well on customer sites.3 concepts