Spec-Graph Meta-framework for AI-Assisted Software Development: An Industry Case
1 — Tres Astronautas, Bogotá, Colombia
2 — Universidad de los Andes, Bogotá, Colombia
3 — Blend 360, Bogotá, Colombia
This is the published version of record. It appears in the ACM Digital Library as part of the ASE 2026 workshop proceedings, and is open access under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 licence, with copyright retained by the authors. 10.1145/3843282.3844432 ↗
AI-assisted software development increasingly relies on large language models to transform natural-language specifications into code. However, in most current workflows, specifications are treated as inline prompt content, limiting their structure, reuse, and traceability across development tasks. This paper introduces a meta-framework for spec-driven AI-assisted development in which specifications are represented as a typed, queryable graph consumed at runtime by software agents. The framework is organized around three principles: legibility, achieved through a typed hierarchy that distinguishes buildable artifacts from contextual constraints; addressability, enabled by a minimal set of edge types, substrate-agnostic graph materialization, and a cost-function-driven sequencing mechanism; and longevity, maintained through continuous curation of the specification substrate. We instantiate the framework in an industrial setting involving a multi-project software development organization with over fifty employees, using thirteen specification types, a multi-substrate architecture, and four cooperating AI agents. To explore the proposed framework’s behavior in practice we surveyed 19 practitioners in the organization after using the framework from one to five months.
- Spec-driven development
- AI-assisted software engineering
- knowledge graphs
- code-generation agents
- industrial study
Daniel Soto, Daniel Alejandro González-Rueda, Mario Linares-Vásquez, and Andrés Hurtado. 2026. Spec-Graph Meta-framework for AI-Assisted Software Development: An Industry Case. In Proceedings of the 1st International Workshop on Agentic AI for Next-Generation Software Development (AgenticDev '26), October 12–16, 2026, Munich, Germany. ACM, New York, NY, USA, 11 pages. https://doi.org/10.1145/3843282.3844432
BibTeX
@inproceedings{soto2026specgraph,
author = {Soto, Daniel and
Gonz\'{a}lez-Rueda, Daniel Alejandro and
Linares-V\'{a}squez, Mario and
Hurtado, Andr\'{e}s},
title = {Spec-Graph Meta-framework for {AI}-Assisted Software
Development: An Industry Case},
booktitle = {Proceedings of the 1st International Workshop on Agentic AI
for Next-Generation Software Development},
series = {AgenticDev '26},
location = {Munich, Germany},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
year = {2026},
pages = {21--31},
numpages = {11},
isbn = {979-8-4007-2985-0},
doi = {10.1145/3843282.3844432},
url = {https://doi.org/10.1145/3843282.3844432}
}