Agency-specific FDTA rules need to make sure the data they collect is AI-ready. AI shines when given access to richly contextualized, standardized, structured data and identifiers. While Large Language Models (LLMs) can source any kind of data, structured or unstructured, for financial analysis and research that demands a high degree of accuracy, structure and standardization […more]
XBRL US Members and others using our Public Filings Database and the XBRL API know extracting data from machine-readable reports yields a wealth of granularity for unambiguous analysis. Extraction involves an XBRL processor – software that reads tagged facts and interprets them according to the taxonomies defined for the report. Altova’s MapForce and XMLSpy feature […more]
Review an AI summary of key findings from the XBRL US’ Global Climate Reporting Roundtable, held during NY Climate Week on September 22, 2025. The roundtable featured keynote talks from New York State Assemblymember Deborah Glick and California State Senator Scott Weiner. Roundtable speakers participated from the AICPA, BNY, the Data Foundation, the IFRS Foundation, KPMG, and XBRL US.
By Mark Ward, Applications Manager, XBRL US
This analysis continues our work leveraging the desktop version of Anthropic’s Claude LLM, we decided to test out how it works with energy-related data reported by public utilities to the Federal Energy Regulatory Commission (FERC). Our key takeaways? XBRL sourced AI results are more reliable, accurate, authoritative, and complete than AI responses generated using unstructured data.
By Michelle Savage, Vice President, Communication, XBRL US On its own, AI is a powerful analytical tool. XBRL can supercharge its responses. Last month we published a blog, AI is smarter with structured standardized data, about an academic study that analyzed thousands of SEC filings to learn what could boost the accuracy of information returned […more]
The national consortium for
the business reporting standard
