Adnan KhanAdnanProduct & AI
San Francisco Bay Area
Get in touch

Source note3 min read

The Context Access Divide: Interaction-Level Architecture as a Complementary Dimension of Agentic Inequality

Source

arXiv

arxiv.org/abs/2607.08495v1

Read the source

Source

Plain-Language Brief

The text discusses a new concept called the 'Context Access Divide' in AI agents, which is a divide between users who can autonomously access their own knowledge corpus (Dynamic Context Retrieval) and those who need to manually attach relevant documents (Manual Attachment). This divide is significant for knowledge-intensive workers whose intellectual capital spans thousands of files as it reproduces inefficiencies that AI is meant to eliminate. The text also introduces the concept of 'contextuality' as a new dimension of AI-mediated inequality.

What the Document Says

  • Sharp et al. (2025) introduced 'agentic inequality' framework for analyzing disparities in access to AI agents.
  • The framework has three dimensions: availability, quality, and quantity at person- and organization-level.
  • A new concept called the 'Context Access Divide' (CAD) is discussed. It operates at an individual interaction level.
  • Two types of user interactions are identified: Dynamic Context Retrieval and Manual Attachment.
  • For knowledge-intensive workers, CAD constitutes a qualitative threshold in AI usefulness.
  • Contextuality is introduced as a new dimension of AI-mediated inequality.
  • The text proposes a probabilistic model to formalize the CAD based on the fan effect literature in cognitive psychology.
  • Manual context attachment leads to a combinatorial collapse in task-success probability with growing corpus size and task conjunctivity, while dynamic retrieval architectures are insulated from this collapse.

Key Concepts Mentioned

  • agentic inequality
  • Context Access Divide (CAD)
  • contextuality
  • Dynamic Context Retrieval
  • Manual Attachment
  • knowledge-intensive workers

Claims Made by the Document

  • The Sharp et al. framework does not address a divide operating at an individual interaction level.
  • Dynamic context retrieval is more beneficial for knowledge-intensive workers.
  • Manual context attachment leads to a combinatorial collapse in task-success probability as corpus size and task conjunctivity grow.

Evidence Used

  • The text discusses the issues with Sharp et al. framework not addressing individual interaction level.
  • The text describes the benefits of dynamic context retrieval for knowledge-intensive workers.
  • The text presents a probabilistic model showing the negative impact of manual context attachment.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

Sharp et al. (2025) introduce 'agentic inequality' as a framework for analyzing disparities in access to AI agents across three dimensions: availability, quality, and quantity. These person- and organization-level dimensions characterize who can access agents and at what capability, but do not address a structurally important divide operating at a finer level: the individual interaction. Two users with nominally equivalent agent access may experience qualitatively different AI utility depending on whether the system can autonomously retrieve context from the user's knowledge corpus (Dynamic Context Retrieval) or requires the user to manually identify and attach relevant documents at each query (Manual Attachment). We term this the Context Access Divide (CAD). For knowledge-intensive workers whose intellectual capital spans tens of thousands of files, the CAD constitutes a qualitative threshold in AI usefulness: below it, the cognitive burden of context curation falls on the human, reproducing the inefficiencies AI is meant to eliminate. We propose contextuality -- the degree to which an AI system autonomously accesses a user's accumulated knowledge capital -- as a dimension of AI-mediated inequality that complements, but is not reducible to, the Sharp et al. framework. We formalize the CAD with a probabilistic model grounded in the fan effect literature in cognitive psychology, demonstrating that manual context attachment leads to a combinatorial collapse in task-success probability as corpus size and task conjunctivity grow, while dynamic retrieval architectures are structurally insulated from this collapse. We analyze the technical basis of this divide in the Model Context Protocol (MCP) and retrieval-augmented generation (RAG) architectures, and examine its implications for knowledge-work stratification and AI platform governance.