🤖 AI Summary
This work addresses the lack of a systematic methodology for constructing customized AI agents, a process currently fragmented across informal resources. The authors propose a framework-agnostic, end-to-end construction methodology grounded in two foundational prerequisites—base design and building blocks—and iteratively refined through three core practices: prototyping, CLI encapsulation, and agent-driven testing. Key innovations include the introduction of the “Turtle mode,” the conceptual insight that multi-agent orchestration fundamentally amounts to CLI composition, and the novel practice of “agent-testing-agent.” To validate the approach, a single developer leveraged AI pair programming to implement AAC, a production-grade open-source agent, within ten days, demonstrating both the feasibility and transferability of the proposed methodology.
📝 Abstract
Custom AI agents areagents that live inside their own
application, talk to their own data and tools, enforce their own security boundaries,
and carry their own brand and audit trail. What separates them from the general-purpose
tier is fit, not capability: each is built for one job, by the
engineer who will maintain it. No published practice sets out how to build one end to
end. The pieces are everywhere (function-calling APIs, the Model Context Protocol, code
agents to pair with), but the practice that chains them lives in podcasts, blogs, and
leaked system prompts. This paper writes that practice down as a methodology, Agents All
the Way Down: two preconditions crossed once and kept, then three practices repeated
for the agent's life. The preconditions are (P1) Substrate, the LLM as a software
component, framed as tools, then system, then messages under prompt-caching; and (P2)
Building blocks: function calling, MCP, CLI orchestration, the liteshell pattern, the
agent loop, skills, characters, hooks, and scaffolding. The practices are (P3) prototype
with a general-purpose agent; (P4) harvest, fold, and ship the result as a CLI, the
Turtle pattern; and (P5) agent-tests-agent, in which a general-purpose agent drives it
through behavioural scenarios, a complement to classical testing, not a replacement. The
working loop is P3 to P4 to P5 and back, and one corollary falls out for free:
multi-agent orchestration is just CLI composition. The methodology is framework-free by
construction. It was distilled from the AAC, a custom agent for the open-source LAMB
platform, built in about ten days by one developer with an AI pair-programmer and in
production . We present it as a transferable practice, independent of any language or framework.