← All popular talks

Popular talk #24

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

Synced transcript

Follow the talk

Community discussion

Add context, evidence, or a useful disagreement

Build on the talk with an example, caveat, connection, or elaboration. Draft here, add the moment you’re discussing, then choose the direct-post pilot or the YouTube handoff.

Make it useful: add one concrete point, then support it with context, evidence, an example, or a caveat. Your words stay exactly as written.

Automated overview

What this talk covers

Thariq Shihipar of Anthropic presents the Claude Agent SDK, arguing that Bash and file-system-based agents outperform traditional tool-only approaches for autonomous tasks. He defines agents as systems that build their own context and trajectory, contrasting with structured workflows. The SDK, built on Claude Code, emphasizes the Bash tool as the most powerful primitive for composability and code generation, enabling non-coding tasks like data analysis. He demonstrates live-coding a Pokémon team advisor that dynamically fetches API data via scripts, and explains security through a 'Swiss cheese defense' of model alignment, AST parsing, and sandboxing. Shihipar also covers skills for progressive context disclosure, sub-agents for parallel work, and hooks for deterministic verification, stressing that agent building is an art of reading transcripts and iterating on context engineering.

This overview is derived from the transcript and has not been independently fact-checked by AI Engineer.

Generated highlights

Key moments

  1. 2:14insightIntro

    Shihipar argues AI capabilities evolved from single LLM features to structured workflows to autonomous agents.

  2. 8:36insightStrong Opinions

    Shihipar outlines the Anthropic way: Unix primitives, Bash and file system over custom tools, agents building their own context.

  3. 15:33insightBash Tool

    Bash is all you need: Shihipar claims the Bash tool’s composability, reuse of existing software, and programmatic nature separates Claude Code from other frameworks.

  4. 23:35insightAgent Loop

    Verification is key to agent reliability; Shihipar prioritizes deterministic rules (linting, null checks) over open-ended checks.

  5. 25:45insightTool Selection

    Shihipar breaks down the three tool types: structured Tools, composable Bash, and dynamic Code Generation, each with distinct performance and context trade-offs.

  6. 50:54storySpreadsheet Design

    Shihipar walks through designing a spreadsheet agent, prompting the audience to brainstorm search, action, and verification strategies.

These moment labels are generated from the unreviewed transcript and may contain errors.

Generated classification

Detected Q&A

  1. 10:15qaStrong Opinions

    Q: What does code generation for non-coding tasks mean? Shihipar explains composing APIs via Bash and scripts.

  2. 12:41qaStrong Opinions

    Q: How does Anthropic handle security and permissions for the Bash tool? Shihipar details Swiss cheese defense: model alignment, harness rules, sandboxing.

  3. 29:18qaTool Selection

    Q: How to handle long tool call outputs that blow up context? Shihipar advises saving results to files and returning file paths.

  4. 34:08qaTool Selection

    Q: Are skills just a bridge until models improve? Shihipar says models get better, but skills handle out-of-distribution tasks; rewrite agent code every six months.

  5. 36:40qaTool Selection

    Q: Skill versus API for agent tools? Shihipar says both are forms of progressive disclosure; let the agent’s transcript guide what it prefers.

  6. 1:07:21qaSpreadsheet Design

    Q: How to enforce a specific order of operations in an agent? Shihipar says you just tell it in the system prompt; let the agent be intelligent.

Podhood’s automated analysis classified these moments as Q&A. AI Engineer has not independently reviewed them.