Core vs edge agents

As our employees use Claude Code for various tasks, we keep seeing agents repeat the same work. Summarizing a customer's state across Salesforce, email, product analytics, usage data: every agent pulls together the same picture from scratch, every time.

Martin Kosk, our enterprise architect, proposed a useful frame for thinking about this: core vs. edge. Edge is the end-user agent session, where everything is computed on the fly. Core is a set of recurring workflows (probably also agent-driven) that pre-compute and cache information for every edge session to reuse.

There's an obvious parallel here to data warehousing. These agents are doing ETL on the fly: pulling from multiple sources, transforming, summarizing. The "core" starts looking like a data pipeline with better natural-language interfaces on top.

I don't know yet how far this analogy stretches, which is one reason to keep your internal data platform people close to the AI transformation people.