Staging environment

Getting Started with Claude Code SDK

Hosted by Ty Avnit

Tue, Feb 24, 2026

5:00 PM UTC (45 minutes)

Virtual (Zoom)

Free to join

Invite your network

What you'll learn

What is the Claude Code SDK

What can it do, it's capabilities and it's components

How to set-up a controlled workflow

Plan, extract data, route, review and execute reliably and with confidence

Example via code walkthrough

Walk through of a UI that shows this workflow tangibly

Why this topic matters

Do you know the difference between the Claude Code SDK and the standard SDK?

The Claude Code SDK provides programmatic control over Claude’s execution flow—letting you structure reasoning, enforce intermediate steps, and constrain outputs to schemas. This enables deterministic workflows and reliable system integration.

I’ll cover the framework and show how you can get started.

You'll learn from

Ty Avnit

AI Engineer @ Civic

Ty Avnit is an AI engineer at Civic with over 15 years of experience building production software, including the last several years focused on AI systems. He’s helped lead Civic’s shift to an AI-first approach, building developer tools and infrastructure around the Model Context Protocol.

He teaches workshops on building production-grade AI agents, speaks at events including ProductCamp and AI Camp Austin, and writes regularly about agent architecture, context management, and designing AI that feels collaborative.

His work centers on making AI fast, transparent, and genuinely useful for developers.

Sign up to join this lesson

By continuing, you agree to Maven's Terms and Privacy Policy.