All writings tagged with "Architecture"
Traditional software left a clear audit trail of hardcoded logic. Stochastic AI agents change this; they dynamically interpret context, choose tools, and execute high-consequence actions. Because prompts alone don't prove intent, engineering teams must shift from tracking execution to auditing runtime judgment—building "decision provenance" to prove exactly *why* an agent acted.
Software engineering has never purely been about syntax extraction. Code is simply the visible artifact: the part people can screenshot, benchmark, demo, and debate on forums.
For the last two decades, many software careers began with CRUD (Create, Read, Update, Delete) applications. A junior developer would receive a ticket to build a user form, add database persistence, create an API endpoint, add validation, and render a table view. They would then repeat this cycle
What actually happened is that the AI showed up on Monday asking where the repository lives, spent Tuesday reading the entire codebase, and by Wednesday was submitting pull requests while openly questioning architectural decisions made by senior engineers. The latest models don't just "write a function."
I spent a week running Gemma locally, comparing it against Llama, Qwen and GPT-4o, trying to answer one question: Is Google's open model strategy finally good enough for real production workloads?
Over time, you learn that clean code is an internal concern, but stable interfaces are external. Users do not care how your system is structured. They care that it behaves the same way today as it did yesterday.