Human-Centered, AI-powered CMS for News

AI-powered automation offers a range of possibilities for productivity, as well as the potential to change the types of products we can provide to news audiences. This project will explore how authoring tools can help journalists gather information, prioritize what is found, and utilize large language models to complement human-generated stories. The project will begin by studying reporters and editors, documenting their current work processes and studying existing research on the needs and desires of news audiences. The project will prototype a user experience for a new and improved content management system and experiment with large language model (LLM) generation.

Faculty and Staff Leads

Jeremy Gilbert

Knight Professor in Digital Media Strategy

Jeremy Gilbert is the Knight Professor of Digital Media Strategy. Both his work and teaching focus on the content and revenue strategies of existing and emerging media companies. He explores the intersection of technology and media, examining how new tools and techniques will affect the creation, consumption and distribution of media.

Project Details

2025 Fall

Important Questions
  • What are the needs of news consumers?
  • What are the needs of news creators?
  • What are the atomic units of storytelling?
  • How can an LLM-powered CMS create multiple, meaningful narratives from a collection of facts?
  • How can an LLM-powered CMS change the research and reporting process?
Sample Milestones
  • Weeks 1-2: Study existing research about audience news needs, canvas existing CMSes and interview journalists
  • Week 3: Diagram workflows
  • Weeks 4-5: Prototype user experiences for a new CMS
  • Week 6: Midterm presentation and user testing
  • Weeks 7-8: Revise user experience and begin building functional prototype
  • Week 9: User testing of functional prototype and begin reflection
  • Week 10: Public demo and finalize reflection
Outcome

Outline for the industry what journalism needs from a future-facing content management system for reporters and editors. This will include an information-mapped workflow and a tested user experience.