Enable javascript in your browser for better experience. Need to know to enable it? Go here.

Curated shared instructions for software teams

Last updated : Apr 15, 2026
Apr 2026
Adopt ?

As teams mature in their use of AI, relying on individual developers to write prompts from scratch is emerging as an anti-pattern. We advocate for curated shared instructions for software teams, treating AI guidance as a collaborative engineering asset rather than a personal workflow.

Initially, this practice focused on maintaining general-purpose prompt libraries for common tasks. We’re now seeing a more effective evolution specifically for coding environments: anchoring these instructions directly into service templates. By placing instruction files such as CLAUDE.md, AGENTS.md or .cursorrules into the baseline repository used to scaffold new services, the template becomes a powerful distribution mechanism for AI guidance.

During our Radar discussions, we also explored a related practice: anchoring coding agents to a reference application. Here, a live, compilable codebase serves as the source of truth. As architecture and coding standards evolve, both the reference application and embedded instructions can be updated. New repositories then inherit the latest agent workflows and rules by default. This approach ensures consistent, high-quality AI assistance is built into every project from day one, while separating general prompt libraries from repository-specific AI configuration.

Nov 2025
Adopt ?

Para los equipos que utilizan activamente la IA en la entrega de software, el siguiente paso es ir más allá del prompting individual y avanzar hacia prompts compartidos seleccionados para equipos de software. Esta práctica ayuda a aplicar la IA de manera efectiva en todas las tareas de entrega (no solo en la codificación) mediante el uso compartido de prompts comprobados y de alta calidad. La forma más sencilla de implementarla es incorporando archivos de instrucciones, como AGENTS.md, directamente en el repositorio del proyecto. La mayoría de las herramientas de codificación con IA, incluidas Cursor, Windsurf y Claude Code, permiten compartir prompts a través de comandos personalizados barra (/) o flujos de trabajo. Para las tareas que no implican código, pueden configurarse bibliotecas de prompts a nivel organizacional listas para usar. Este enfoque sistemático permite la mejora continua: en cuanto un prompt se perfecciona, todo el equipo se beneficia, garantizando acceso constante a los mejores prompts para interactuar con la IA.

Published : Nov 05, 2025

Download the PDF

 

 

 

English | Português

Sign up for the Technology Radar newsletter

 

 

Subscribe now

Visit our archive to read the previous volumes