# Agentic Engineering Operating Level: WHERE to FOCUS your AGENTS?

## Executive summary

The video introduces the 'Agentic Operating Level,' a framework that maps where an engineer and their agents should focus attention when building software. The core principle is that higher leverage does not guarantee success; engineers must dynamically choose between maximizing speed/leverage (moving up) or gaining control/understanding (moving down). Moving up requires deep domain expertise, while moving down is necessary when the system is unfamiliar, high-risk, or performance details matter.

## Key takeaways

- Higher Is NOT Better: Gaining leverage without understanding (moving too high on the stack) leads to limited capability and poor debugging ability. The goal is finding a dynamic *range* of operation, not just moving up.
- Leverage vs. Control Trade-off: The choice must be dictated by the problem: Choose control when the system is unfamiliar or high-risk; choose leverage when the domain is understood and work is repetitive.
- Importance of Domain Expertise: Domain expertise allows an engineer to know when automation (leverage) is appropriate. If the work is familiar and repeated, it's a strong signal to automate.

## Technical details

- Agentic Operating Level Framework: The framework defines five levels of operation: Code Primitives (lines, blocks, functions, types, classes), Code Structure (files, modules, directories), Data and Execution (database tables, scripts, CLIs), Delivery and Intent (application/repository level), and Agentic Systems (planning, documentation).
- High-Level Automation Concepts: The highest levels include the AI Developer Workflow (ADW) and the Software Factory. The ADW is defined as a repeatable workflow that allows scaling developer processes, which is distinct from simple 'loop engineering.'
- Low-Level Control Artifacts: The video emphasizes that understanding these low-level components (e.g., types) is necessary before attempting to build complex systems at the top.

## Practical implications

- When starting a new project or dealing with an unfamiliar codebase, prioritize operating at lower levels (Code Primitives, Code Structure) to establish control and understanding before attempting high-level automation.
- To scale development, focus on mastering the AI Developer Workflow (ADW) and building repeatable processes that move beyond simple agent calls. This is a key skill for advanced engineering.
- When designing systems or debugging complex issues, always ask: Is this high-risk/high-impact? If yes, you must go down to gain control over the details.

## Topics

Agentic Engineering, Software Architecture, AI Developer Workflow (ADW), System Design, Code Primitives, Build Automation, Understand The SOFTWARE FACTORY, Forget Loop Engineering

Source: https://www.youtube.com/watch?v=rPWCYB62wvI