Paper 2604.00073
Terminal Agents Suffice for Enterprise Automation
- Published
- Mar 2026
- Research lab
- Independent
- Citations
- 5
- GitHub
- Not linked
01 In brief
Summary
The paper argues that minimal terminal-based coding agents, which interact directly with platform APIs via a terminal and filesystem, can match or outperform more complex agent architectures for enterprise automation.
The authors introduce StarShell, a terminal agent, and compare it against GUI-driven web agents and MCP-based tool-augmented agents across three enterprise platforms (ServiceNow, GitLab, ERPNext) using four frontier LLMs.
Results show terminal agents achieve the best cost-performance tradeoff, with success rates comparable to web agents but at significantly lower cost, while MCP agents underperform due to tool coverage limitations.
The study also finds that documentation access provides no clear benefit, but persistent memory of reusable skills improves success rates and reduces costs, especially on less familiar platforms.
Hybrid agents combining terminal and browser access show potential but require capable models to route tasks effectively.
The authors conclude that simple programmatic interfaces combined with strong foundation models are sufficient for practical enterprise automation, challenging the need for sophisticated abstraction layers.
02 From the paper
Abstract
There has been growing interest in building agents that can interact with digital platforms to execute meaningful enterprise tasks autonomously. Among the approaches explored are tool-augmented agents built on abstractions such as Model Context Protocol (MCP) and web agents that operate through graphical interfaces. Yet, it remains unclear whether such complex agentic systems are necessary given their cost and operational overhead. We argue that a coding agent equipped only with a terminal and a filesystem can solve many enterprise tasks more effectively by interacting directly with platform APIs. We evaluate this hypothesis across diverse real-world systems and show that these low-level terminal agents match or outperform more complex agent architectures. Our findings suggest that simple programmatic interfaces, combined with strong foundation models, are sufficient for practical enterprise automation.