Search papers, labs, and topics across Lattice.
This paper investigates the necessity of complex agentic systems for enterprise automation, arguing that coding agents with terminal and filesystem access can effectively interact with platform APIs. They evaluate this "terminal agent" approach against more complex architectures like tool-augmented and web agents across diverse real-world systems. Results show that terminal agents match or outperform these complex systems, suggesting that simple programmatic interfaces combined with strong foundation models are sufficient for practical enterprise automation.
Forget the fancy tool-augmented agents: a simple coding agent with terminal access can often beat them at real-world enterprise automation tasks.
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.
