# AI tooling for requirements engineering AI tooling for requirements engineering splits in two: **gathering** produces requirements from informal input, and **detection** audits the ones that exist. This is the **AI as the oracle** branch of the [section spine](https://quality.stereobooster.com/ai.md): no sound oracle exists yet, so AI judges intent rather than writing or consuming a check. ## The shape of the field This tooling has two distinguishing findings: 1. **Gathering has usable tools; detection is mostly research.** Most detection tools score *individual* requirements and skip *cross-requirement* contradiction. 2. **Spec-driven AI development is now a workflow category.** A spec-first scaffold orders the AI's work; it does not check the spec against a quality rule set. ## The two activities **Gathering — LLM produces requirements.** Informal input (a Slack thread, an interview transcript, a regulation, a brief) becomes structured output (user stories, acceptance criteria, PRDs). The LLM produces *requirement-shaped text*; whether it describes what the team or user actually wants is a separate question AI doesn't answer. **Detection — LLM audits requirements.** A set of existing requirements becomes a list of problems, the same audit a human reviewer does by hand ([Requirements quality checking](https://quality.stereobooster.com/requirements-quality-checking.md)). It decomposes into sub-tasks of decreasing maturity: per-requirement quality scoring, ambiguity detection, and cross-requirement contradiction. ## Tools for gathering [GitHub Spec Kit](https://github.com/github/spec-kit) (still experimental and pre-1.0) imposes spec-first discipline on AI-assisted development and works across agent hosts; SpecStory captures AI design conversations into `decisions.md` artifacts, close to an [architecture decision record](https://quality.stereobooster.com/adrs.md). [ChatPRD](https://www.chatprd.ai) is a hosted PRD-drafting tool. RM platforms (Jama, IBM DOORS Next + watsonx, Polarion, Codebeamer) add AI authoring that scores against INCOSE/EARS; product-management suites (Productboard, Atlassian Rovo, Linear) draft tickets and cluster feedback upstream of a PRD. Generating acceptance criteria as Gherkin from user stories has been measured at one company (Ferreira et al. 2025)[^ferreira2025]: over 166 uses, 95% of the 65 responses collected called the criteria helpful, and the executable test scripts derived from them were accurate and complete 60% of the time, or 92% after minor fixes or extra context. ## Tools for inconsistency / quality detection - [QuARS](https://www.sei.cmu.edu/library/quars-a-tool-for-analyzing-requirement/) (ISTI-CNR) — lexical and syntactic rule matching over requirement text, pre-2010 and still cited as a baseline. - **ALICE** (Gärtner and Göhlich 2024)[^gartner2024] — formal logic plus an LLM, classifying contradictions in requirements written in controlled natural language; it reached 60% recall on the paper's contradiction dataset where the LLM-only method reached none. - **LMAdetect** (Gao et al. 2026)[^gao2026] — heuristic rules + LLM for ambiguity, improving on both rules-only and LLM-only. - **Lubos et al.** (Lubos et al. 2024)[^lubos2024] — an LLM scored requirements against ISO/IEC/IEEE 29148; expert–LLM agreement was weak in independent assessment but improved in the bound-assessment phase. - **SpecFix** (Jia et al. 2025)[^jia2025] — repairs an ambiguous NL problem description by aligning it with the input/output examples and reducing the model's code-generation uncertainty, measured on programming-benchmark descriptions rather than on requirements documents. - [Knowledgebase Guardian](https://github.com/datarootsio/knowledgebase_guardian) (dataroots) — a small open-source reference implementation of RAG + LLM contradiction detection across a corpus, and a starting point for a custom checker. **Polarion's Consistency Checker** is the one tool that visibly attempts cross-requirement contradiction detection rather than per-requirement scoring; its evidence is vendor-reported. ## Where existing tooling stops - **Cross-requirement contradiction detection at scale.** The logical-form + LLM hybrids are research prototypes, and no shipping tool reproduces them. - **Conflicting NFR triangulation.** Conflicts among latency, throughput, security, and cost are under-supported; pre-LLM matrix-map approaches haven't been folded in. - **Spec ↔ regulation tracing.** Bidirectional drift detection between requirements and a regulatory clause (GDPR, ISO 26262, DO-178C) is largely manual. - **Transcript → structured requirement with provenance.** Enterprise assistants do the recap; none emit a structured, traceable artifact. - **Open-source agent skill for requirements quality.** No established `SKILL.md` package targets ISO/IEC/IEEE 29148 or INCOSE checking. ## Tools vs research A 2025 systematic review of 74 studies published in 2023–2024 (Zadenoori et al. 2025)[^zadenoori2025] found elicitation and validation the most-studied RE tasks, GPT models in 90% of the studies and zero-shot or few-shot prompting in most of them, and 75% of the evaluations run as laboratory experiments rather than in industry. ## Referenced by - [AI tooling for process methods](https://quality.stereobooster.com/ai-process.md) · AI ## References [^ferreira2025]: Ferreira, Margarida, Luis Viegas, Joao Pascoal Faria, and Bruno Lima. 2025. "[Acceptance Test Generation with Large Language Models: An Industrial Case Study](https://arxiv.org/pdf/2504.07244)." *2025 IEEE/ACM International Conference on Automation of Software Test (AST)*, 1–11. . [^gartner2024]: Gärtner, Alexander Elenga, and Dietmar Göhlich. 2024. "[Automated Requirement Contradiction Detection through Formal Logic and LLMs](https://link.springer.com/content/pdf/10.1007/s10515-024-00452-x.pdf)." *Automated Software Engineering* 31. . [^gao2026]: Gao, Juntao, Fang Liu, and Yilong Yang. 2026. "[Requirement Ambiguity Detection Method Based on Large Language Model](https://crad.ict.ac.cn/en/article/pdf/preview/10.7544/issn1000-1239.202550700.pdf)." *Journal of Computer Research and Development* 63 (4): 827–53. . [^lubos2024]: Lubos, Sebastian, Alexander Felfernig, Thi Ngoc Trang Tran, et al. 2024. "[Leveraging LLMs for the Quality Assurance of Software Requirements](https://arxiv.org/pdf/2408.10886)." *Proceedings of the 32nd IEEE International Requirements Engineering Conference (RE '24)*, 389–97. . [^jia2025]: Jia, Haoxiang, Robbie Morris, He Ye, Federica Sarro, and Sergey Mechtaev. 2025. "[Automated Repair of Ambiguous Problem Descriptions for LLM-Based Code Generation](https://arxiv.org/pdf/2505.07270)." *Proceedings of the 40th IEEE/ACM International Conference on Automated Software Engineering (ASE '25)*, 367–79. . [^zadenoori2025]: Zadenoori, Mohammad Amin, Jacek Dąbrowski, Waad Alhoshan, Liping Zhao, and Alessio Ferrari. 2025. *[Large Language Models (LLMs) for Requirements Engineering (RE): A Systematic Literature Review](https://arxiv.org/pdf/2509.11446)*. . ## Acronyms - AST — abstract syntax tree - NFR — non-functional requirement - NL — natural language - PRD — product requirements document - RAG — retrieval-augmented generation - RE — requirements engineering - RM — requirements management