Skip to content
Resources

Learning path · 4 steps · 21h of lectures

Building with AI agents

From using AI tools well to engineering agents and building software with them.

Good for
Developers who use coding assistants and want to build agentic systems of their own. If Transformers are new to you, start with the LLM path.

The route, in order

  1. Step 1

    CourseStanfordAutumn 20267 lectures · 7h 41m

    CS193T: Thinking with AI

    No prerequisites. Prompting, context and when to push back on a model, before building anything on top of one.

    A hands-on course with no prerequisites on working with AI tools, covering prompting, agents, evaluating models and knowing when to push back.

  2. Step 2

    CourseStanfordAutumn 202610 lectures · 13h

    CS329Z: Engineering AI Agents

    The engineering core, from simple LLM pipelines to autonomous agents, with RAG, tool use, DSPy and evaluation.

    Building agentic systems, from simple LLM pipelines to compound systems and autonomous agents, with RAG, tool use, DSPy, evaluation and a quarter-long project.

  3. Step 3
  4. Step 4

    TalkStanford CS146S

    How always-on agents work (opens in a new tab)

    A guest lecture from CS146S on agents that keep running in the background, short enough to finish on.

    A guest lecture in CS146S on how agents that keep running in the background are built.

Hours count only the lectures posted on YouTube so far; 2 steps have no recordings to count. Tick lectures on a course page and its step fills in here. That progress stays in your browser.