Can AI Agents Generate Microservices? How Far are We?

TL;DR

This study evaluates the capability of AI agents, especially LLMs, to generate functional microservices with explicit dependencies and API contracts, analyzing their correctness, quality, and efficiency across different scenarios and prompting strategies.

Contribution

It provides the first comprehensive assessment of AI-generated microservices, comparing various agents, prompts, and testing methods to understand their strengths and limitations.

Findings

Incremental generation achieves 50-76% unit test pass rates.

Clean state generation achieves 81-98% integration test pass rates.

Generated code is less complex than human-written baselines.

Abstract

LLMs have advanced code generation, but their use for generating microservices with explicit dependencies and API contracts remains understudied. We examine whether AI agents can generate functional microservices and how different forms of contextual information influence their performance. We assess 144 generated microservices across 3 agents, 4 projects, 2 prompting strategies, and 2 scenarios. Incremental generation operates within existing systems and is evaluated with unit tests. Clean state generation starts from requirements alone and is evaluated with integration tests. We analyze functional correctness, code quality, and efficiency. Minimal prompts outperformed detailed ones in incremental generation, with 50-76% unit test pass rates. Clean state generation produced higher integration test pass rates (81-98%), indicating strong API contract adherence. Generated code showed lower complexity than human baselines. Generation times varied widely across agents, averaging 6-16 minutes per service. AI agents can produce microservices with maintainable code, yet inconsistent correctness and reliance on human oversight show that fully autonomous microservice generation is not yet achievable.