From Prompt-Response to Goal-Directed Systems: The Evolution of Agentic AI Software Architecture

TL;DR

This paper explores the evolution of agentic AI from prompt-based models to goal-directed systems, proposing a reference architecture, taxonomy, and enterprise checklist to enhance scalability, governance, and safety.

Contribution

It introduces a comprehensive architecture, taxonomy, and governance checklist for developing scalable, safe, and interoperable goal-directed AI systems based on LLMs.

Findings

Emerging industry platforms show convergence on standardized agent loops.

Shared protocols and governance structures are key for scalable autonomy.

Challenges in verifiability and safety remain significant for deployment.

Abstract

Agentic AI denotes an architectural transition from stateless, prompt-driven generative models toward goal-directed systems capable of autonomous perception, planning, action, and adaptation through iterative control loops. This paper examines this transition by connecting foundational intelligent agent theories, including reactive, deliberative, and Belief-Desire-Intention models, with contemporary LLM-centric approaches such as tool invocation, memory-augmented reasoning, and multi-agent coordination. The paper presents three primary contributions: (i) a reference architecture for production-grade LLM agents that separates cognitive reasoning from execution using typed tool interfaces; (ii) a taxonomy of multi-agent topologies, together with their associated failure modes and mitigation approaches; and (iii) an enterprise hardening checklist that incorporates governance, observability, and reproducibility considerations. Through an analysis of emerging industry platforms, including Kore.ai, Salesforce Agentforce, TrueFoundry, ZenML, and LangChain, the study identifies a convergence toward standardized agent loops, registries, and auditable control mechanisms. It is argued that the subsequent phase of agentic AI development will parallel the maturation of web services, relying on shared protocols, typed contracts, and layered governance structures to support scalable and composable autonomy. The persistent challenges related to verifiability, interoperability, and safe autonomy remain key areas for future research and practical deployment.