# Agents' next frontier: agent-to-agent and network effects — Jean-Denis Greze, Town

## Executive summary

The talk reframes multi-agent systems not as 'agent-to-agent' interactions, but fundamentally as a search problem: ensuring that an LLM's context window contains the optimal information for a tool call. The primary technical barrier to achieving this ideal state—a single agent with access to all world information—is not context length, but privacy and security. Greze outlines five strategies (Shared Trust Boundaries, Custom Tools, Shared Silos, Human Conduit, Black Box) that attempt to approximate the optimal outcome while managing data leakage risks.

## Key takeaways

- Reframing Agents as Search Problems: Most LLM systems are best viewed as search problems. The goal is engineering the system so that the context window contains the precise information needed before a tool call, maximizing the LLM's ability to return the best result.
- The Privacy Constraint (Coase Theorem): The ideal state is one agent with access to all world information. However, privacy acts as a transaction cost, preventing this perfect data aggregation, which the Coase theorem highlights.
- Shared Silos and Sweeper Agents: A promising approach is creating shared silos (e.g., wikis) where a 'sweeper AI' automatically identifies and moves information from private spaces into public, company-wide knowledge bases.
- The Black Box Approach: This advanced method allows an LLM (in a 'black box' agent) to query multiple silos without pinging every human. It only asks the data owners for approval at the final moment of information sharing.
- The Future: Auto Mode: The frontier is 'auto mode,' where LLMs are trusted to automatically determine if a disclosure is low-sensitivity and can be shared without explicit human approval, scaling with model capacity.

## Technical details

- Agent Architecture Reframing: The concept of 'agent-to-agent' is discouraged. The focus should be on optimizing the context window for a single, powerful agent call.
- Coase Theorem Application: In data systems, the theorem suggests that perfect information and zero transaction cost yield optimal outcomes. Privacy represents this non-zero transaction cost.
- Strategy: Shared Trust Boundary: Giving an agent access to multiple, related systems (e.g., all HR systems) as if it were the lowest-level employee in that team. Limitation: This approach does not scale with model improvements and still requires human thought.
- Strategy: Custom Tools (Power vs. Privacy): Building tools that perform specific, limited data aggregations to trade power for privacy. Example: A tool that reads all emails but only returns a 'relationship strength score' between two parties.
- Strategy: Sweeper AI: An AI agent placed within private silos with a policy to automatically detect and surface information into shared, public spaces (e.g., company wikis). This is the most promising approach for internal data flow.
- Black Box Approach: A system where an LLM has full access to all silos but only requests human approval when it must make a specific, actionable disclosure (the 'sharing moment').

## Practical implications

- Architects should shift focus from multi-agent orchestration to optimizing the context window for single LLM calls.
- Implementing 'sweeper AI' mechanisms can automatically improve data discoverability and reduce information trapped in private silos.
- Designing systems around a defined, low-sensitivity zone allows for gradual automation ('Auto Mode') of data sharing decisions.
- For enterprise adoption, the Black Box approach offers a path to cross-silo querying while maintaining human oversight at critical disclosure points.

## Topics

Large Language Models (LLMs), Agent Systems, Data Privacy, Information Retrieval, System Architecture, Network Effects, Town, Apex / Ivy

Source: https://www.youtube.com/watch?v=REascnFlq_8