In-Context Prompting Obsoletes Agent Orchestration for Procedural Tasks

TL;DR

This paper demonstrates that for procedural tasks, embedding the entire procedure in the system prompt and allowing the model to self-orchestrate outperforms traditional external agent orchestration frameworks across multiple domains.

Contribution

It provides a controlled comparison showing that in-context prompting surpasses agent orchestration frameworks for procedural multi-turn tasks with recent models.

Findings

In-context prompting scores higher on quality criteria than orchestration.

External orchestration systems fail more often than in-context prompting.

Advances in frontier models make external orchestration unnecessary for procedural tasks.

Abstract

Agent orchestration frameworks -- LangGraph, CrewAI, Google ADK, OpenAI Agents SDK, and others -- place an external orchestrator above the LLM, tracking state and injecting routing instructions at every turn. We present a controlled comparison showing that for procedural tasks, this architecture is dominated by a simpler alternative: putting the entire procedure in the system prompt and letting the model self-orchestrate. Across three domains -- travel booking (14 nodes), Zoom technical support (14 nodes), and insurance claims processing (55 nodes) -- we evaluate 200 conversations per condition using LLM-as-judge scoring on five quality criteria. The in-context approach scores 4.53--5.00 on a 5-point scale while a LangGraph orchestrator using the same model scores 4.17--4.84. The orchestrated system fails on 24% of travel, 9% of Zoom, and 17% of insurance conversations, compared to 11.5%, 0.5%, and 5% for the in-context baseline. While external orchestration may have been necessary for earlier models, advances in frontier model capabilities have made it unnecessary for multi-turn conversations following a defined procedure.