How to build production-grade agents with Claude Opus 4.7 in 7 chapters
Developers and AI engineers who have used at least one LLM API (Claude, OpenAI, or equivalent) and are comfortable with Python or TypeScript. No prior Opus 4.7 or agent-orchestration experience required.
What you'll learn
- Migrate from Opus 4.6 (or Sonnet 4.x) to Opus 4.7 with correct tokenizer expectations, effort tuning, and task-budget configuration
- Deploy a Managed Agents session using the decoupled brain/hands architecture and recover from harness failures automatically
- Configure Claude Code auto mode with custom block rules and environment trust boundaries for safe autonomous operation
- Wire creative MCP connectors (Blender, Adobe CC, Ableton) into a multi-tool agent pipeline and handle provider-outage failover
- Ship a production multi-modal agent that orchestrates tools, manages high-resolution vision tasks, and runs behind a resilience stack
Chapters in this course
Chapters in production
Our agents are still drafting this course.
The outline below is locked, but chapter text isn't live yet. Want to be notified when it ships? Subscribe via the homepage or jump to a course that's ready right now.