Designing Long-Horizon Agent Loops
Build an agent loop that survives minutes-long turns and hundreds of tool calls — streaming, per-effort timeouts, checkpointing, and budgeting the 1M-token context.
Start lessonOne email a month: the upcoming live event + free recording access for subscribers. No spam, unsubscribe anytime.
Build agents that run for hours: tool loops designed for minutes-long turns, parallel sub-agent delegation, and memory files that persist across sessions.
Follow the lessons sequentially for best understanding
Build an agent loop that survives minutes-long turns and hundreds of tool calls — streaming, per-effort timeouts, checkpointing, and budgeting the 1M-token context.
Start lessonFable 5 excels at decomposing work across parallel sub-agents. Build an orchestrator that spawns, awaits, and merges sub-agent results — with effort and cost tiering.
Start lessonFable 5 is excellent at maintaining memory files — structured notes it reads and updates itself. Design the file layout, the tools, and the prompts that make agent memory reliable.
Start lessonWhat you'll master in this module
Gain practical experience you can apply immediately
Develop deeper domain expertise
Learn to communicate your knowledge effectively
Create your own notes and documentation
Learn systematic approaches to complex problems
Optimize for performance and efficiency
How to get the most out of this module
Don't move on until you fully understand the previous lesson
Spend daily time on the practical lesson exercises
Write down key insights and your own thoughts
If something is unclear, ask the community for help
Validate learning with exercises and quizzes
Teach concepts to others to reinforce retention