Author

AI Step-by-Step

Sharing AI knowledge, practical implementation records, and more.

Articles

Likes

Views

Comments

Latest from AI Step-by-Step

39 recent articles

AI Step-by-Step

Apr 1, 2026 · Artificial Intelligence

When to Use Which Model in an Agent: Beyond the “Strongest Model” Myth

The article explains why routing every request to the most powerful LLM hurts cost, speed, and throughput, and presents a three‑layer task decomposition that assigns execution‑level tasks to cheap small models, intermediate tasks to mid‑size models, and high‑risk judgment tasks to large models, with concrete examples and a minimal routing strategy.

Agent DesignCost OptimizationLLM

0 likes · 8 min read

When to Use Which Model in an Agent: Beyond the “Strongest Model” Myth

AI Step-by-Step

Mar 31, 2026 · Artificial Intelligence

Designing Effective Human-in-the-Loop AI Workflows: When to Automate and When to Involve Humans

The article explains how to avoid the extremes of fully automated AI or no AI at all by defining clear Human-in-the-Loop patterns, identifying irreversible, high‑responsibility, and high‑exception steps, and applying tailored approval, edit, and escalation nodes in finance, contract, and other critical business processes.

AI assistanceAI workflowHuman-in-the-Loop

0 likes · 9 min read

Designing Effective Human-in-the-Loop AI Workflows: When to Automate and When to Involve Humans

AI Step-by-Step

Mar 30, 2026 · Artificial Intelligence

How to Keep LLM Agents in Check with Guardrails

The article explains why LLM agents can over‑promise or execute unauthorized actions, and outlines a three‑layer guardrail system—prompt review, output validation, and tool‑action interception—plus concrete rules, examples, and test cases to ensure safe deployment.

AI safetyLLM agentsPrompt Engineering

0 likes · 11 min read

How to Keep LLM Agents in Check with Guardrails

AI Step-by-Step

Mar 29, 2026 · Artificial Intelligence

Engineering Long-Term Memory for Agents: Practical Architecture and Best Practices

The article explains how to engineer persistent, cross‑session memory for AI agents by persisting key user facts, task states, and decisions in a multi‑layer storage architecture, detailing retrieval before each request and update after each interaction.

AI EngineeringAgent architectureLong-Term Memory

0 likes · 11 min read

Engineering Long-Term Memory for Agents: Practical Architecture and Best Practices

AI Step-by-Step

Mar 29, 2026 · Artificial Intelligence

How RAG Quickly Gives Your Agent Real Business Knowledge

The article explains why agents often lack business understanding, describes Retrieval‑Augmented Generation (RAG) as the fastest way to provide correct, up‑to‑date business context, outlines eight practical RAG patterns, and offers a step‑by‑step checklist for building enterprise‑ready agents.

AgentEnterprise AIGraphRAG

0 likes · 10 min read

How RAG Quickly Gives Your Agent Real Business Knowledge

AI Step-by-Step

Mar 28, 2026 · Artificial Intelligence

How to Evaluate Agent Performance Across Different Scenarios

The article proposes a four‑dimensional framework—task result, output structure, behavior boundary, and long‑term stability—to systematically validate AI agents in varied business contexts such as e‑commerce, manufacturing, insurance, and HR, emphasizing concrete evidence over subjective impressions.

AI AgentR&D managementScenario Validation

0 likes · 10 min read

How to Evaluate Agent Performance Across Different Scenarios

AI Step-by-Step

Mar 22, 2026 · Artificial Intelligence

Why Harness Engineering Is the Key to Stable Agent Loops

The article explains that while an Agent Loop can execute tasks, long‑running stability depends on a well‑designed Harness engineering layer that organizes knowledge, enforces rules, provides verification, and automates cleanup, turning a functional prototype into a reliable production system.

AI agentsAgent LoopHarness Engineering

0 likes · 10 min read

Why Harness Engineering Is the Key to Stable Agent Loops

AI Step-by-Step

Mar 22, 2026 · Artificial Intelligence

How OpenClaw’s Agent Loop Turns Chat into Actionable Tasks

OpenClaw distinguishes itself from ordinary chatbots by employing an Agent Loop—a task‑driving execution chain that normalizes inputs, assembles context, makes model‑based decisions, suspends for tool results, and writes back state, enabling continuous task progression rather than single‑turn replies.

AI AgentAgent LoopOpenClaw

0 likes · 10 min read

How OpenClaw’s Agent Loop Turns Chat into Actionable Tasks

AI Step-by-Step

Mar 19, 2026 · Industry Insights

OpenClaw Reveals How Agents Can Cut Software Usage Costs and Boost Efficiency

The article argues that enterprise software’s biggest bottleneck is not missing features but users’ inability to master complex systems, and demonstrates through OpenClaw how a natural‑language‑driven Agent layer can replace thick manuals with a unified service interface, dramatically reducing training, support, and operational costs.

AgentCustomer SuccessEnterprise Software

0 likes · 13 min read

OpenClaw Reveals How Agents Can Cut Software Usage Costs and Boost Efficiency

AI Step-by-Step

Mar 17, 2026 · Industry Insights

How OpenClaw Redefines Enterprise Software with AI‑Powered Business Integration

The article analyzes OpenClaw as an AI‑driven business‑connection layer that unifies chat entry, tool execution, and event‑driven automation, showing how enterprises can shorten system gaps, automate long‑tail workflows, and adopt a new agent‑based service model without replacing existing ERP or CRM solutions.

AI agentsLLMOpenClaw

0 likes · 8 min read

How OpenClaw Redefines Enterprise Software with AI‑Powered Business Integration