Netflix
Build an AI Agent from Scratch, v2
This Workshop's Online Chatroom is Currently Open!
This workshop has ended. Check back soon for the recording!
You can watch a replay of this workshop!
Two days building a general-purpose agent from first principles—tool calls, loops, memory, evals, and guardrails.
Key Takeaways
By participating along with us in the workshop, you'll learn:
- Understand the core primitives of an agent: models, tools, history, memory, and orchestration
- Implement a tool-calling loop with conversation-style messages instead of relying on a framework
- Plug in filesystem tools, 3rd-party tools (web search, code execution, browser handoff), and other SDKs with minimal extra code
- Manage context windows with summarization and retrieval so your agent can use local files and search results without blowing the token limit
- Design and run evals that cover both single-step decisions and full multi-step runs
- Add guardrails and human approvals around risky tools like shell commands or bulk edits
- Treat agents as composable building blocks that can be called as tools or wired into other systems
Is This Workshop for Me?
Frontend/full-stack devs who want to build tool-using agents in TS, teams exploring agents for ops/CRM workflows, or any engineers curious about ChatKit-style UIs and chat-embedded forms.
Workshop Details
You’ll build a generic agent that can orchestrate tools on your machine like reading and transforming files, calling 3rd-party tools like web search and code execution, and handing results off to a local browser. The focus is creating an agent with a loop that maintains conversation history, uses tool calling to select tools and arguments, updates messages based on tool results, and decides when to stop. Along the way, you’ll learn how to manage context with summarization and retrieval, layer in evals to catch failures, and add guardrails and human-in-the-loop checks for sensitive actions. By the end, you’ll have an agent you can keep extending with new tools, protocols, and interfaces.
Any Prerequisites?
- Comfortable with TypeScript and Node.js.
- Able to run a local server, manage env vars, and use Git branches.
- An LLM API key (OpenAI-compatible).
Attend Online Live and in Full HD
Or Join In Person from Downtown Minneapolis
Get Your Questions Answered
Code Along with the Class
Classroom Format
You're Registered to Attend Online!
You'll receive additional details and a reminder via email as the event draws near.
Build an AI Agent from Scratch, v2
Event Details
What
- 2 Full Day Workshop Sessions
- Replay Videos (available immediately)
When
- December 2 to 3, 2025 - 9:30am to 4:30pm Central Standard Time
Where
- Option 1: Attend online on our full HD live stream
- Option 2: Attend in-person at HQ in Minneapolis, MN
Daily Schedule
Day 1
- 9:40AMWhat is an Agent?
- 9:55AMHello World LLMs
- 10:30AMEval Baseline
- 12:00PMLunch Break
- 1:00PMConversational LLMs
- 2:00PMTool-Calling Loop
- 3:00PMEvals
- 4:00PMTools and Actions
- 4:30PMEnd of Day 1
Day 2
- 9:40AMContext and Memory
- 10:00AM3rd-Party Tools
- 12:00PMLunch Break
- 1:00PMTracing and Debugging
- 2:30PMAdvanced Evals and Metrics
- 3:30PMGuardrails, HITL, and Composition
- 4:30PMEnd of Day 2
Your (Awesome) Instructor
Scott Moss
Scott is a senior software engineer at Netflix. Formerly the CEO and Co-founder of Superfilter AI. He’s spent years as a VC investing in AI startups, and founding and leading a devtools startup. He’s a 2-time YC founder that loves building things people obsess about. Outside of the grind, Scott loves to game and play basketball and spend time with his family out in California.
Check out all of our upcoming workshops!
Workshops happen throughout the year, and are all included with membership.