Architectures for Building Agentic AI

TL;DR

This paper discusses how the reliability of agentic AI systems depends on architecture, emphasizing componentization, disciplined interfaces, and control loops, and offers design guidance for building reliable agentic AI.

Contribution

It introduces a comprehensive architectural framework for agentic AI, detailing components, patterns, and safety mechanisms to enhance reliability and safety.

Findings

Reliability emerges from modular architecture and disciplined interfaces.

Different agent patterns reshape failure modes and reliability.

Design principles like schemas, permissioning, and safeguards improve safety.

Abstract

This chapter argues that the reliability of agentic and generative AI is chiefly an architectural property. We define agentic systems as goal-directed, tool-using decision makers operating in closed loops, and show how reliability emerges from principled componentisation (goal manager, planner, tool-router, executor, memory, verifiers, safety monitor, telemetry), disciplined interfaces (schema-constrained, validated, least-privilege tool calls), and explicit control and assurance loops. Building on classical foundations, we propose a practical taxonomy-tool-using agents, memory-augmented agents, planning and self-improvement agents, multi-agent systems, and embodied or web agents - and analyse how each pattern reshapes the reliability envelope and failure modes. We distil design guidance on typed schemas, idempotency, permissioning, transactional semantics, memory provenance and hygiene, runtime governance (budgets, termination conditions), and simulate-before-actuate safeguards.