Article · · 6 min read
Loop and Harness Engineering: The Work Around the Model
Why the code around a model now matters more than the prompt: harnesses, loops, stopping rules, verification and the token bill.
Ayhan Gurbangeldiyev
Notes on how agentic systems are built, run and kept honest: loops, harnesses, graphs and what agents change in security.
Article · · 6 min read
Why the code around a model now matters more than the prompt: harnesses, loops, stopping rules, verification and the token bill.
Article · · 6 min read
When one agent loop is not enough: nodes, edges, state and checkpoints that give an agentic system a shape you can test.
Article · · 6 min read
AI agents now drive disassemblers and decompilers. What that changes for reverse engineering and security and where it still fails.
Article · · 4 min read
Five principles for scoping, tooling, orchestrating, governing and observing systems that do more than answer.