Enterprise Agents Have a Structure Problem - Ishita Daga, Tesla
Enterprise AI agents fail due to ambiguity, staleness, and preference problems, not model size.
“while all of these are fair solutions, they're not the answer to actually improving the data agent itself”
Tesla ML engineer Ishita Daga argues that enterprise agents fail not because of insufficient model size or context length, but due to three structural problems: ambiguity in knowledge source selection, staleness of context as business definitions and KPIs change, and team-specific preferences for metrics and query filters. She proposes treating knowledge sources as a hierarchy from cleanest to most dynamic, rather than weighting all sources equally. This reframes a common enterprise AI debugging instinct — reach for a bigger model — as a misdiagnosis.