• Comparing zero-shot and few-shot prompting across GPT-based and DeepSeek models, the study found architecture differences were driven mainly by prompting strategy, not which model provider was used.
• Few-shot prompting consistently produced finer-grained service decomposition, lower inter-service communication density, and more detailed responsibility descriptions than zero-shot.
• Zero-shot prompting instead favored coarser, more tightly coupled microservice designs.
• The study measured structural properties only, not architectural correctness or quality -- it's offered as a baseline for future work on LLM-driven architecture generation.

• LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.

Gives engineers using LLMs for architecture design concrete metrics on where generated microservice decompositions become inconsistent, useful before trusting a model's design output.

• articleModular Cognitive Architecture Emerges in Large Language ModelsPengrui Han, Jacob Andreas, Evelina Fedorenko, Andrea Gregor de Varda
• articleArchitecture as Capability Equalizer for Coding AgentsArquimedes Canedo
• articleAn Empirical Evaluation of Cost-Efficient Large Language Models on Algorithmic Programming TasksChandimal Adikari, Nandika Herath

Checking sign-in…

Loading comments…