Test-Oriented Programming: rethinking coding for the GenAI era
2026-04-09 • Software Engineering
Software Engineering
AI summaryⓘ
The authors suggest a new way to program called Test-Oriented Programming (TOP), where developers write tests based on natural language, and large language models (LLMs) generate the actual production code. Instead of writing the full code, programmers just review the test code, making coding simpler. They built a simple tool as a test and tried creating a small command-line program using two different LLMs. The results were promising, but the authors also found some challenges that need to be solved before applying this method to bigger projects.
Large Language ModelsTest-Oriented ProgrammingSoftware DevelopmentAutomated Code GenerationNatural Language SpecificationsAuto-completeMulti-agent SystemsCommand-line Program
Authors
Jorge Melegati
Abstract
Large language models (LLMs) have shown astonishing capability of generating software code, leading to its use to support developers in programming. Proposed tools have relied either on assistants for improved auto-complete or multi-agents, in which different model instances are orchestrated to perform parts of a problem to reach a complete solution. We argue that LLMs can enable a higher-level of abstraction, a new paradigm we called Test-Oriented Programming (TOP). Within this paradigm, developers only have to check test code generated based on natural language specifications, rather than focusing on production code, which could be delegated to the LLMs. To evaluate the feasibility of this proposal, we developed a proof-of-concept tool and used it to generate a small command-line program employing two different LLMs. We obtained promising results and identified challenges for the use of this paradigm for real projects.