English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

Anthropic's Guide to Building Effective Agents: First Principles and Engineering Practice

Forum topic · 小凯 · 2026-02-28

Summary

A Chinese forum post summarizes Anthropic's influential guide 'Building Effective Agents' by Erik Schluntz and Barry Zhang. The core insight: the most successful LLM agent implementations rely on simple, composable patterns rather than complex frameworks. The post distinguishes workflows (predefined code paths) from agents (models dynamically directing their own processes) and outlines five workflow patterns: prompt chaining, routing, parallelization, orchestrator-workers, and evaluator-optimizer. Agents suit open-ended problems where steps cannot be predicted, at the cost of higher latency, expenses, and error accumulation. Key engineering advice includes keeping designs simple and transparent, investing heavily in the Agent-Computer Interface (ACI), writing tool descriptions like good docstrings, and preferring direct LLM API calls over abstraction-heavy frameworks. Practical applications covered include AI customer support and coding agents (SWE-bench), with a success formula: start simple, optimize with evaluations, and add agentic complexity only when demonstrably needed.

Overview

This forum post is a detailed Chinese-language walkthrough of Anthropic's guide "Building Effective Agents" (by Erik Schluntz and Barry Zhang, published December 19, 2024). After working with dozens of teams across industries, Anthropic found a counterintuitive truth: the most successful implementations use simple, composable patterns—not complex frameworks or specialized libraries.

Core Distinction: Workflow vs Agent

Anthropic classifies all LLM-enhanced systems as *agentic systems*, with a key architectural split:

| Type | Definition | Control | |------|------------|---------| | Workflow | LLMs and tools orchestrated through predefined code paths | Developer-controlled flow | | Agent | LLM dynamically decides its own process and tool usage | Model-autonomous control |

Core principle: don't build agents/workflows unless necessary. Agentic systems trade latency and cost for task performance. Find the simplest solution first; optimizing a single LLM call (RAG, in-context examples) is often enough.

When to Use Workflows: Five Patterns

1. Prompt Chaining — Decompose a task into sequential subtasks with checkpoints. Example: generate marketing copy, then translate it; write an outline, check it, then write the document. Trade latency for accuracy.

2. Routing — Classify input and dispatch to specialized follow-up tasks. Examples: customer support triage (general questions / refunds / tech support); routing easy queries to Haiku and hard ones to Sonnet.

3. Parallelization — *Sectioning* (MapReduce-style independent subtasks, e.g., one model handles queries while another filters inappropriate content) and *Voting* (run the same task multiple times, e.g., several prompts reviewing code for vulnerabilities).

4. Orchestrator-Workers — A central LLM dynamically decomposes tasks and delegates to worker LLMs. Unlike parallelization, subtasks are not predefined. Examples: editing an uncertain number of files; multi-source research.

5. Evaluator-Optimizer — One LLM generates, another evaluates and gives feedback in a loop. Works when feedback clearly improves responses (e.g., literary translation nuance, deciding whether further search is needed).

When to Use Agents

Agents fit open-ended problems where steps can't be predicted or hardcoded. Requirements: some trust in model decisions, a trusted execution environment, sandbox testing, and safeguards—since costs and error-accumulation risks are higher.

> An agent is just "an LLM in a loop, using tools based on environmental feedback to accomplish its task."

Examples: a coding agent solving SWE-bench tasks; the "computer use" reference implementation.

Three Design Principles

1. Keep it simple — avoid over-engineering. 2. Keep it transparent — explicitly show the agent's planning and steps. 3. Design the ACI (Agent-Computer Interface) carefully — this emerged as crucial. Best practices:

  • Give the model room to "think" so it doesn't paint itself into a corner
  • Use formats close to text models naturally see on the internet
  • Avoid format overhead (no counting thousands of lines, no string escaping)
  • Write parameter names/descriptions like good docstrings
  • Test extensively how the model uses tools and iterate
  • Apply poka-yoke: make errors structurally harder
  • Notably, while building their SWE-bench agent, Anthropic spent more time optimizing tools than the overall prompt. One fix: requiring absolute paths (models erred with relative paths after the agent left the root directory)—after which the model performed flawlessly.

    On Frameworks

    Frameworks mentioned: Claude Agent SDK, Strands Agents SDK (AWS), Rivet, Vellum. Recommendations:

    1. Prefer direct LLM API calls—many patterns need only a few lines of code 2. If using a framework, understand the underlying code (false assumptions cause bugs) 3. Don't hesitate to strip abstraction layers in production

    Extra abstraction can hide prompts/responses, complicate debugging, and tempt you into unnecessary complexity.

    Summary of First Principles

    | Principle | Meaning | |-----------|---------| | Start simple | Don't build giant control flows; provide robust atomic tools | | Build for deletion | Modular architecture; newer models will replace your logic | | Performance drives complexity | Add complexity only when performance clearly improves | | Tools are the interface | ACI matters as much as HCI |

    Success = the right system, not the most complex system. Start with simple prompts, optimize with thorough evaluations, and only introduce multi-step agentic systems when simple solutions genuinely fall short.

    Application Cases

  • AI customer support: natural conversational flow, tool integration for customer/order data, programmable actions (refunds, ticket updates), measurable success. Some companies use pay-on-success pricing, signaling confidence in outcomes.
  • Coding agents: verifiable via automated tests, well-defined problem space, objective quality metrics. Anthropic's agent solves real GitHub issues (SWE-bench Verified), though human review remains essential.
  • Reference

  • Original: Building Effective Agents
  • Authors: Erik Schluntz, Barry Zhang (Anthropic), December 19, 2024

Tags

#anthropic#llm-agents#ai-engineering#prompt-engineering#workflows#agent-design#swe-bench#developer-tools

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/177168628