Claude Agent SDK [Full Workshop] — Thariq Shihipar, Anthropic
Understand agent/harness choices, scoped access and verification. Long SDK workshop; recommend relevant sections, not exact book folder/check.py configuration.
About this selection
T07-L03: Use the workshop's workflow-versus-agent, harness and verification discussions to understand a reusable agent's moving parts. It is a long SDK workshop, not the book's folder/check.py walkthrough. Its Bash-capable architecture does not justify widening the book's permissions. T07-L04: Focus on layered controls, scoped access and reversible actions when connecting agents to real systems. These architectural principles complement the book; the workshop does not implement its credential-free agent, fetcher/poster separation or Microsoft Graph mailbox restrictions.
Linked by topic; a curriculum association does not certify the full video. Check the source date and compare technical instructions with current official documentation.