Loop Engineering from First Principles
Continuing the topic of Loop Engineering, I'd like to share the talk: Loop Engineering from First Principles.
The author criticizes the current trend of using "blind" agentic loops everywhere. They can lead to a huge volume of generated code that nobody really understands. Quality decreases, the number of bugs grows.
No, he doesn't reject the approach itself. Instead, he suggests looking at it from a more engineering perspective and applying a Control Theory Framework.
Control theory is a branch of engineering and applied mathematics that regulates the behavior of dynamical systems to achieve a desired output.
Sounds promising, right?
To apply it to agentic loops, the following elements should be defined:
🔸 Sensor (Measurement). Define the desired state and use deterministic tools like tests and linters to detect violations.
🔸 Controller (Prioritization). Use deterministic rules to prioritize tasks, for example, starting with the smallest unit of work.
🔸 Actuator (Change Application). Use hand-written "golden patterns" to guide the agent and keep changes aligned with your team's standards.
🔸 Feedback Loop. Verify the result after each change and feed it back into the next iteration:
- Run the loop in CI to detect regressions.
- Keep a human in the loop for the final review. They should understand the changes and own the code.
So the main point is not to let an agent generate a huge pile of code that a human can no longer understand. The point is to get controlled and verifiable results incrementally, in small pieces, keeping "human-in-the-loop".
I liked the talk. It's really great when we start moving from hype toward something more manageable and controllable.
#ai #engineering
Continuing the topic of Loop Engineering, I'd like to share the talk: Loop Engineering from First Principles.
The author criticizes the current trend of using "blind" agentic loops everywhere. They can lead to a huge volume of generated code that nobody really understands. Quality decreases, the number of bugs grows.
No, he doesn't reject the approach itself. Instead, he suggests looking at it from a more engineering perspective and applying a Control Theory Framework.
Control theory is a branch of engineering and applied mathematics that regulates the behavior of dynamical systems to achieve a desired output.
Sounds promising, right?
To apply it to agentic loops, the following elements should be defined:
🔸 Sensor (Measurement). Define the desired state and use deterministic tools like tests and linters to detect violations.
🔸 Controller (Prioritization). Use deterministic rules to prioritize tasks, for example, starting with the smallest unit of work.
🔸 Actuator (Change Application). Use hand-written "golden patterns" to guide the agent and keep changes aligned with your team's standards.
🔸 Feedback Loop. Verify the result after each change and feed it back into the next iteration:
- Run the loop in CI to detect regressions.
- Keep a human in the loop for the final review. They should understand the changes and own the code.
So the main point is not to let an agent generate a huge pile of code that a human can no longer understand. The point is to get controlled and verifiable results incrementally, in small pieces, keeping "human-in-the-loop".
I liked the talk. It's really great when we start moving from hype toward something more manageable and controllable.
#ai #engineering