Preparing unstructured data for AI with Deasy Labs

An enterprise's first internal AI project worked brilliantly in the POC. But in production, the data became massive and messy: relevance and quality were unclear, sensitive information couldn't easily be filtered out, and there was no metadata to point AI toward the right answers. In this session from Data Citizens on the Road in San Francisco, see how adding a curation and enrichment layer before ingestion cuts unstructured data prep from months to days, lowers compliance risk, and improves AI accuracy. We cover: * The role of context in building safe, scalable, accurate AI systems, especially with unstructured data * The challenges of not having a formal unstructured data governance program * Examples of issues arising from outdated information and lack of data curation * The importance of filtering, enriching, and combining data for AI readiness * Steps to improve data quality, including filtering for relevance and sensitivity * How to enrich unstructured data with contextual metadata * The benefits of integrating unstructured data into a unified data product * The concept of knowledge decay and the need for continuous data curation Watch more Data Citizens on the Road sessions at https://www.collibra.com/resources/watch-on-demand-data-citizens-on-the-road-2026