AI guides grounded on research

Rooted Layers Guides

Technology EN ↓ 6 episodes

This is the Guides section of Rooted Layers, where you get in depth multi part walkthroughs and how-tos, architecture blueprints and full courses on AI topics. lambpetros.substack.com

Author

AI guides grounded on research

Episodes

Operating Agents Bonus: Workflow Optimization and Evaluation 27.03.2026 44:48

Read with: Optimization Companion and Optimization Blueprint . Optimization stays last because the workflow becomes the object only after it is stable enough to deserve improvement. Before that point, prompt tuning is usually just movement on the easiest visible surface rather than progress on the system that actually carries the work. Thanks for reading Rooted Layers! Subscribe for free to receiv...

Operating Agents V: Trust Boundaries and Agent Safety 27.03.2026 40:43

Read with: Safety Companion and Safety Blueprint . These essays share one claim. Reliable agents do not come from stacking more visible capability on top of a strong model. They come from explicit operating layers a reviewer can still inspect when something breaks: action surfaces, memory policy, reasoning scaffolds, role boundaries, trust boundaries, and evaluation loops. Once a workflow can touc...

Operating Agents IV: Multi-Agent Boundaries and Handoffs 27.03.2026 39:34

Read with: Multi-Agent Companion and Multi-Agent Blueprint . These essays share one claim. Reliable agents do not come from stacking more visible capability on top of a strong model. They come from explicit operating layers a reviewer can still inspect when something breaks: action surfaces, memory policy, reasoning scaffolds, role boundaries, trust boundaries, and evaluation loops. Once a workflo...

Operating Agents III: Reasoning Scaffolds and Planning 27.03.2026 34:03

Read with: Reasoning Companion and Reasoning Blueprint . These essays share one claim. Reliable agents do not come from stacking more visible capability on top of a strong model. They come from explicit operating layers a reviewer can still inspect when something breaks: action surfaces, memory policy, reasoning scaffolds, role boundaries, trust boundaries, and evaluation loops. Once a workflow ca...

Operating Agents II: Memory Systems and Authority 27.03.2026 53:10

Read with: Memory Companion and Memory Blueprint . These essays share one claim. Reliable agents do not come from stacking more visible capability on top of a strong model. They come from explicit operating layers a reviewer can still inspect when something breaks: action surfaces, memory policy, reasoning scaffolds, role boundaries, trust boundaries, and evaluation loops. Once a workflow can touc...

Operating Agents I: Action Systems and Tool Use 27.03.2026 49:30

Part 1 of the Operating Agents series, a builder-first run on how modern agent systems actually work once language leaves the prompt and starts acting inside software. This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit lambpetros.substack.com