06How would you chunk contracts, Slack threads, and PDFs full of tables: same pipeline or different?▼mediumHarveyGleanScale1 repliesunlockedA reported FDE design question that punishes one-size-fits-all answers. Each corpus has a different 'semantic unit': get the three designs, the parsing tools to name, and the eval that proves the split was worth it.Open full answer →
18Ingest 40 enterprise sources (SharePoint, Confluence, Jira, drives) with incremental sync and deletion handling▼mediumGleanDatabricksMicrosoft1 replies○ sign inA Glean-signature design question where deletions, not ingestion, are the trap. Covers the connector framework, change detection per source class, tombstones, and the freshness SLO customers actually sign.Open full answer →
26You must ingest from a customer source that ships nulls, duplicates, and surprise schema changes. Design defensive ingestion.▼mediumPalantirDatabricksRetool1 replies◆ premiumPure FDE territory: the customer's data is always dirtier than scoped. The layered defense, contracts, quarantine, drift handling, and the alert-severity matrix that keeps you from crying wolf.Open full answer →