Prompt Less, Smile More: MTP with Semantic Engineering in Lieu of Prompt Engineering

TL;DR

This paper introduces Semantic Engineering with SemTexts to enrich program semantics, enabling LLMs to better understand developer intent without manual prompt engineering, thus improving prompt fidelity efficiently.

Contribution

It presents Semantic Context Annotations (SemTexts) integrated into Jac, extending MTP to incorporate enriched semantics and introduces a benchmark for realistic AI-Integrated applications.

Findings

Semantic Engineering improves prompt fidelity significantly.

Performance comparable to prompt engineering with less effort.

Benchmark results demonstrate practical effectiveness.

Abstract

AI-Integrated programming is emerging as a foundational paradigm for building intelligent systems with large language models (LLMs). Recent approaches such as Meaning Typed Programming (MTP) automate prompt generation by leveraging the semantics already present in code. However, many real-world applications depend on contextual cues, developer intent, and domain-specific reasoning that extend beyond what static code semantics alone can express. To address this limitation, we introduce Semantic Engineering, a lightweight method for enriching program semantics so that LLM-based systems can more accurately reflect developer intent without requiring full manual prompt design. We present Semantic Context Annotations (SemTexts), a language-level mechanism that allows developers to embed natural-language context directly into program constructs. Integrated into the Jac programming language, Semantic Engineering extends MTP to incorporate these enriched semantics during prompt generation. We further introduce a benchmark suite designed to reflect realistic AI-Integrated application scenarios. Our evaluation shows that Semantic Engineering substantially improves prompt fidelity, achieving performance comparable to Prompt Engineering while requiring significantly less developer effort.