Trust layer for AI on enterprise data: a live context layer compiled from your code
Typedef builds a live context layer, compiled from a company's code, that maps data-model dependencies, lineage and impact across the data platform so AI answers and changes can be checked before they ship. Its product combines a knowledge graph with agents for cross-system tracing, a semantic catalog and impact analysis, and the team also maintains fenic, an open-source semantic DataFrame engine. Typedef launched in June 2025 with a $5.5 million seed round led by Pear VC. It was co-founded by Yoni Michael and Kostas Pardalis, and on October 30, 2026 Factory announced it had acquired Typedef to bring data context to its Droid coding agents.