Context Graphs for Proactive Enterprise Agents

2026-07-04

AI Summary

This work addresses the limitation of enterprise agents, which typically respond passively to queries and struggle to proactively deliver high-value information, thereby constraining productivity gains. The paper proposes the first proactive agent architecture tailored for enterprise settings, integrating a dynamic context graph to model entity relationships and state evolution, a change detection engine, a unified proactivity scoring function, and an LLM-based information delivery layer to automatically identify and precisely disseminate valuable insights. Built on NetworkX for graph representation and leveraging the Claude API for natural language explanations, the system incorporates real-time monitoring and personalized ranking algorithms. Evaluated across three representative enterprise scenarios, it achieves a Precision@5 of 0.83 with a false positive rate of only 0.11, reducing information delivery latency from 47 minutes to under 30 seconds.

Abstract

Retrieval-Augmented Generation (RAG) and agentic frameworks have advanced enterprise AI considerably, yet agents remain fundamentally reactive: they wait for a human query before acting. This paper argues that genuine enterprise productivity gains require proactive agents: systems that surface relevant, actionable information to workers before they ask. We propose the Context Graph, a live relational data structure that models enterprise entities, their relationships, and state transitions over time. Built on this graph, we define a Delta Detection Engine that continuously monitors state changes, a Proactivity Scorer that ranks candidate insights by urgency, relevance, and persona-fit, and a Surfacing Layer powered by an LLM that delivers ranked notifications with grounded explanations. We formalize each component, derive a unified Proactivity Score function, and provide a complete end-to-end Python implementation using NetworkX and the Anthropic Claude API. Evaluation across three generic enterprise case studies (contract lifecycle management, engineering incident response, and sales pipeline hygiene) demonstrates that context-graph-driven proactivity achieves Precision@5 of 0.83, a false positive rate of 0.11, and reduces mean time to surface from 47 minutes (reactive baseline) to under 30 second.

Problem

• proactive agents
• enterprise AI
• context graphs
• information surfacing
• reactive systems

Innovation

• Context Graph
• Proactive Agents
• Delta Detection
• Proactivity Scoring
• Retrieval-Augmented Generation