Referencias

Anthropic (25 de noviembre de 2024). Introducing the Model Context Protocol. Anuncio oficial. Creado por David Soria Parra y Justin Spahr-Summers. Especificación en modelcontextprotocol.io.

Anthropic, Cline / Task tool documentation (2024). Cline / Task tool documentation, as cited in the manuscript.

Aspuru-Guzik lab (2024). As cited in the manuscript.

Beyer, Betsy; Jones, Chris; Petoff, Jennifer; Murphy, Niall Richard (2016). Site Reliability Engineering: How Google Runs Production Systems. O’Reilly Media.

Bloomberg (2025). News report, as cited in the manuscript, January.

Boehm, Barry W. (1981). Software Engineering Economics. Prentice Hall.

Bonér, Jonas; Farley, Dave; Kuhn, Roland; Thompson, Martin (2014). The Reactive Manifesto.

Breck, Eric; Cai, Shanqing; Nielsen, Eric; Salib, Michael; Sculley, D. (2017). The ML Test Score: A Rubric for ML Production Readiness, 2017. IEEE Big Data.

Brewer, Eric A. (2000). Towards Robust Distributed Systems (CAP Theorem). ACM PODC, 2000.

Brooks, Frederick P., The Mythical Man-Month: Essays on Software Engineering (1975). The Mythical Man-Month: Essays on Software Engineering. Addison-Wesley, 1975.

CNCF (2026). OpenTelemetry Specification, versión 1.61.0. Proyecto incubation de la Cloud Native Computing Foundation. Especificación en opentelemetry.io/docs/specs/otel/.

Evans, Eric (2003). Domain-Driven Design: Tackling Complexity in the Heart of Software. Addison-Wesley.

Greshake, Kai; Abdelnabi, Sahar; Mishra, Shailesh; Endres, Christoph; Holz, Thorsten; Fritz, Mario (2023). Not What You’ve Signed Up For: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection. arXiv preprint.

Ji, Ziwei; Lee, Nayeon; Frieske, Rita; others (2023). Survey of Hallucination in Natural Language Generation. ACM Computing Surveys.

Kaplan, Jared; McCandlish, Sam; Henighan, Tom; others (2020). Scaling Laws for Neural Language Models, 2020. arXiv preprint.

Kapoor, Sayash; Stroebl, Benedikt; Siegel, Zachary S.; Nadgir, Arvind; Narayanan, Arvind (2024). AI Agents That Matter. arXiv preprint.

Kleppmann, Martin (2017). Designing Data-Intensive Applications. O’Reilly Media, 2017.

LangChain Inc. (2024). LangGraph, framework de orquestacion y runtime para agentes con estado y larga duracion. Documentacion en docs.langchain.com. Beneficios declarados: mezclar pasos deterministas y pasos agénticos en un mismo grafo, persistencia que sobrevive a fallos, inspección humana en cualquier punto y memoria a corto y largo plazo.

Learning; Intelligent Systems group, As cited in the manuscript, 2025 (2025). As cited in the manuscript, 2025.

Lewis, Patrick; Perez, Ethan; Piktus, Aleksandra; Petroni, Fabio; others (2020). Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. Advances in Neural Information Processing Systems (NeurIPS).

Liu, Nelson F.; Lin, Kevin; Hewitt, John; Paranjape, Ashwin; Bevilacqua, Michele; Petroni, Fabio; Liang, Percy (2024). Lost in the Middle: How Language Models Use Long Contexts. Transactions of the Association for Computational Linguistics (TACL).

Martin, Robert C. (2017). Clean Architecture: A Craftsman’s Guide to Software Structure and Design. Prentice Hall.

Newman, Sam, Building Microservices (2021). Building Microservices. (2nd, O’Reilly Media, 2021 ed.) O’Reilly Media, 2021.

NIST (2023). AI Risk Management Framework 1.0. National Institute of Standards and Technology.

NVIDIA, As cited in the manuscript, 2024 (2024). As cited in the manuscript, 2024.

OpenAI, GPT-6 Astra announcement, September, 2026 (2026). GPT-6 Astra announcement, September, 2026.

OWASP Foundation (2025). OWASP Top 10 for LLM and GenAI Applications 2025. Proyecto OWASP GenAI Security Project. Diez riesgos de LLM01:2025 (inyección de instrucciones) a LLM10:2025 (consumo no acotado). En genai.owasp.org/llm-top-10/.

Patterson, David; Gonzalez, Joseph; Le, Quoc; others (2021). Carbon Emissions and Large Neural Network Training, 2021.

Peng, Sida; Kalliamvakou, Eirini; Cihon, Peter; Demirer, Mert (2023). The Impact of AI on Developer Productivity: Evidence from GitHub Copilot. arXiv:2302.06590 [cs.SE]. Experimento controlado: el grupo con acceso al asistente completó la tarea un 55,8 % más rápido que el grupo de control.

Schwartz, Roy; Dodge, Jesse; Smith, Noah A.; Etzioni, Oren (2020). Green AI, 2020. Communications of the ACM.

Sculley, D.; Holt, Gary; Golovin, Daniel; others (2015). Hidden Technical Debt in Machine Learning Systems, 2015. NeurIPS.

Skelton, Matthew; Pais, Manuel (2019). Team Topologies: Organizing Business and Technology Teams for Fast Flow. IT Revolution Press.

Systems Security group, As cited in the manuscript, 2025 (2025). As cited in the manuscript, 2025.

Unión Europea, Reglamento de Inteligencia Artificial (EU AI Act), 2024 (2024). Reglamento de Inteligencia Artificial (EU AI Act), 2024.

Zheng, Lianmin; Chiang, Wei-Lin; Sheng, Ying; Zhuang, Siyuan; others (2023). Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena. Advances in Neural Information Processing Systems (NeurIPS).

Ziegler, Albert; Kalliamvakou, Eirini; Li, X. Alice; Rice, Andrew; Rifkin, Devon; Simister, Shawn; Sittampalam, Ganesh; Aftandilian, Edward (2024). Measuring GitHub Copilot’s Impact on Productivity. Communications of the ACM, 67(3), 54-63._ Estudio de campo con Metric, el equipo de análisis de GitHub.

TypeSafe AI (2026). Jev: A System One Control Layer for Autonomous Agents. Architecture and Technical Specification.

OpenAI (2026). Introducing Dots: Persistent Digital Coworkers with Isolated Cloud Environments and Governed Control Planes. OpenAI DevDay 2026.