Sign InOpen Brain
AI EngineerVideoSource Linked

The Half Life of Agent Infrastructure — Ben Kus, Box

Agent architectures are expiring quickly. Keep model, search, and orchestration choices replaceable, and evaluate platforms by how well they handle repeated change.

AI Engineer · Aug 29, 2026
Open Source Open MarkdownOpen JSON
Source Summary

Box operates at **over an exabyte of data**, tens of millions of users, and roughly **a trillion tokens**. Its CTO says last year’s graph-based agent pattern was overtaken by looping agents, while adaptive model selection and agentic search are now preferred approaches.

Practical Implication

Treat agent infrastructure as replaceable. Separate components, make migrations routine, prepare teams for repeated rewrites, and choose vendors partly by how they handled transitions over the previous six to twelve months.

Agent-Ready Context
Box operates at **over an exabyte of data**, tens of millions of users, and roughly **a trillion tokens**. Its CTO says last year’s graph-based agent pattern was overtaken by looping agents, while adaptive model selection and agentic search are now preferred approaches.

Treat agent infrastructure as replaceable. Separate components, make migrations routine, prepare teams for repeated rewrites, and choose vendors partly by how they handled transitions over the previous six to twelve months.

This advice comes from enterprise-scale experience, and today’s preferred stack is not presented as durable. Frequent rebuilding also creates breakage, skepticism, and morale costs that modular architecture alone cannot remove.
Connected Context · Feed7 Judgment

This elevates replaceability from a model-level concern to the governing principle for the entire agent stack. It confirms that routing and harness policies are temporary, workload-dependent choices, while adding an organizational cost the technical candidates largely omit: recurring migrations can damage stability, trust, and morale even when components are modular.

Evolution of agentic surfaces — Gagan Bhat & Isabella Kai He, AnthropicDirectly reinforces replaceable scaffolding with a concrete case where a harness fix became harmful after a model upgrade.How Cursor Router chooses the right model for the taskSupplies a production mechanism for the adaptive model selection Box now prefers, while showing that routing itself depends on changing behavior and economics.Asymmetric Capacity Allocation in Self-Refinement PipelinesNarrows adaptive selection further by showing that model capacity can be allocated differently by pipeline stage rather than uniformly across a workflow.How to Get Your Org to Adopt Coding Agents (Without Shipping Garbage) — Eyal Blum, FigmaAdds the human consequence of repeated infrastructure change: skepticism can reveal real verification and review burdens that modularity does not remove.
Context Map
agentcoding#harness-engineering#model-selection#agent-reliability
Uncertainty
This advice comes from enterprise-scale experience, and today’s preferred stack is not presented as durable. Frequent rebuilding also creates breakage, skepticism, and morale costs that modular architecture alone cannot remove.