Featured Leanpub Book
Beyond Context Graphs: Agentic Memory, Cognitive Processes, and Promise Graphs
Enterprise level agent in user pocket
AI engines are booming, and the more we work with agentic systems, the more we see that we need something to make them work at the enterprise level. We're quite active in exploring ideas around context graphs, decision traces, and supporting explainability—giving agents the ability to make more aware and company-aligned decisions.
But this makes sense not only for enterprises, but for users and individuals building personal agents as well. Unfortunately, we have zero-to-none inclination on how to actually build a context graph.
I'll try to explain how to build something like a context graph—but go beyond it. I deeply believe that to make this work, we need specific agentic memory and a set of cognitive processes that truly help agents use this memory and learn from experience and data.
That's why this is the Book: Beyond Context Graphs—with a focus on real-life enterprise tasks and how to make agents make better decisions and, let's say, hallucinate less.





















