Claude Agent SDK [Full Workshop] — Thariq Shihipar, Anthropic

Q: Who is Claude Agent SDK [Full Workshop] — Thariq Shihipar, Anthropic for?

This course is designed for learners with some foundational knowledge.

Q: Is Claude Agent SDK [Full Workshop] — Thariq Shihipar, Anthropic free?

Yes, Claude Agent SDK [Full Workshop] — Thariq Shihipar, Anthropic is completely free to watch on YouTube.

1.7K

About this course

Learn to use Anthropic's Claude Agent SDK (formerly Claude Code SDK) for AI-powered development workflows! https://platform.claude.com/docs/en/agent-sdk/overview https://x.com/trq212 **AI Summary** This workshop by Thariq Shihipar (Anthropic) details the architecture and implementation of the **Claude Agent SDK**. The session moves from high-level theory—defining "agents" as autonomous systems that manage their own context and trajectory—to a live-coding demonstration. Shihipar builds an agent "Harness" from scratch, implementing the core **Agent Loop** (Context Thought Action Observation), integrating the **Bash tool** for general computer use, and demonstrating **Context Engineering** via the file system to maintain state across long tasks. **Timestamps** 00:00 Introduction: Agenda and the "Agent" definition 05:15 The "Harness" concept: Tools, Prompts, and Skills 10:10 Live Coding Setup: Initializing the Agent class and environment 15:45 implementing the "Think" step: Getting the model to reason before acting 25:20 The Agent Loop: connecting `act`, `observe`, and `loop` 33:10 Tool Execution: Handling XML parsing and tool inputs 42:00 The "Bash" Tool: Giving the agent command line access 49:30 Safety & Permissions: "ReadOnly" vs "ReadWrite" file access 58:15 Context Engineering: Using `ls` and `cat` to build dynamic context 01:05:00 The "Monitor": Viewing the agent's thought process in real-time 01:12:45 Handling "Stuck" States: Feedback loops and error correction 01:21:20 Multi-turn Complex Tasks: Building a "Research Agent" demo 01:35:10 Refactoring patterns: "Hooks" and deterministic overrides 01:48:39 Q&A: Reproducibility, helper scripts, and non-determinism 01:50:31 Q&A: Strategies for massive codebases (50M+ lines) 01:52:00 Closing remarks and future SDK roadmap * **Evolution of AI Capabilities:** Shihipar argues we are shifting from **LLM Features** (categorization, single turn) to **Workflows** (structured, multi-step chains like RAG) to **Agents**. He defines agents as systems that *"build their own context, decide their own trajectories, and work very autonomously"* rather than following a rigid pipeline. * **The Claude Agent SDK Architecture:** The SDK is built directly on top of **Claude Code** because Anthropic found they were *"rebuilding the same parts over and over again"* for internal tools. * **The Harness:** A robust agent requires more than just a model; it needs a "Harness" containing Tools, Prompts, a **File System**, Skills, Sub-agents, and Memory. * **Opinionated Design:** The SDK bakes in lessons from deploying Claude Code, specifically the "opinion" that general computer use (Bash) is often superior to bespoke tools. * **The Agent Loop & Intuition:** Building a successful agent loop is described as *"kind of an art or intuition"*. The loop generally follows a **Gather Context Take Action Verify Work** cycle. Shihipar emphasizes that this loop allows the agent to self-correct, a capability missing from rigid workflows. * **Strategies for Determinism (Hooks):** During the Q&A, a technique for controlling agent behavior is discussed: **Hooks**. * If an agent hallucinates or skips a step (e.g., guessing a Pokemon stat instead of checking a script), a hook can intercept the response and inject feedback: *"Please make sure you write a script, please make sure you read this data."* * This enforces rules like "read before you write" without retraining the model. * **Scaling to Large Codebases:** For massive codebases (50M+ lines), standard tools like `grep` or basic context window stuffing fail. * **Semantic Search Limitations:** Shihipar notes that while semantic search is a common solution, it is *"brittle"* because the model isn't trained on the specific semantic index. * **Solution:** He recommends good **"Claude MD"** files (context files) and starting the agent in a specific subdirectory to limit scope, rather than trying to index the entire 50M lines at once. --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/TqC1qOfiVcQ-claude-agent-sdk-workshop Join our upcoming AI Engineer conferences (see https://ai.engineer landing page): - AIE New York, October 12–14 — the first AI Engineer Finance mainstage summit - AIEi Shanghai, November 5–6 — the first for meeting top Chinese labs and engineers - AIE CODE in SF, November 10–12 — the top AI Coding conference returns - AIEi Sydney, December 7–8 — the first AIEi run alongside NeurIPS 2026 in Sydney ---

What learners say

AI summary

Learners find the workshop useful for getting started and clearing up confusion about the Claude Agent SDK, especially through its examples. However, several criticize it as more of a Q&A session for those already familiar with the SDK rather than a thorough, structured tutorial, noting it is overly long and lacks fundamental explanations.

What learners praise

Clears up confusion for beginners
Helpful examples
Reveals SDK's power and cool factor
Good for understanding Claude Code alongside the SDK

Common caveats

Lacks deep SDK explanation
Feels like Q&A for experienced users rather than a structured workshop
Overly long; could be compressed to 20 minutes
Example choices caused confusion about when to use skills, CLI, tools, or agents

AI-generated from 67 viewer comments on YouTube — it summarizes outside comments and is not a CourseShelf review.