Zep AI editorial newsletter

NEWSLETTER NEW ON THE BLOG · 9 MIN READ Metadata is the easy part of a data context layer A data agent can write correct SQL and still pick the wrong table, metric or join key. We read 15 engineering write-ups, from teams at OpenAI, Anthropic, LinkedIn, Spotify and others, to see how they address it. Read more By Patrick Kemp KEY TAKEAWAYS 01 Data agents now fail on context more than on SQL. In a 2026 benchmark study, agents on the strongest model failed more often at finding the right data than at writing the query. 02 Most business context is outside table metadata. Decisions, exceptions and account terms are usually in documents and chat threads. In 13 of the 15 write-ups, people write or approve this context by hand. 03 A recent fact isn't always a valid fact. A message from today can describe a rule for last year's data. 10 of the 15 teams check for stale data or context, but none of the write-ups describes a record of when a business fact applied. Read the full article → ALSO ON THE BLOG How Zep Context Graphs keep two timelines for every fact Each fact in a Zep Context Graph keeps two timelines: when the fact was true, and when the graph learned it. OCT 29 · 7 MIN 7 reasons context graphs are unusually effective Why a graph of entities and dated facts gives agents better context than text chunks. OCT 22 · 8 MIN You are receiving this email because you opted in to receive email from the list Newsletter from Zep AI Zep AI, 2261 Market Street STE 5686 San Francisco, CA 94114 Unsubscribe