Author

Xike

Stupid is as stupid does.

Articles

Likes

Views

Comments

Latest from Xike

18 recent articles

Xike

Jul 24, 2026 · Operations

CI/CD Fundamentals: Understanding the Core Principles of Continuous Delivery

This article explains the fundamental concepts of CI/CD, clarifies the distinction between Continuous Integration, Continuous Delivery and Continuous Deployment, describes pipeline components such as stages and jobs, outlines common triggers, artifacts, caches and secrets, and shows how tools like GitLab, Jenkins and Harbor fit together in a complete delivery workflow.

CI/CDContinuous DeliveryContinuous Integration

0 likes · 13 min read

CI/CD Fundamentals: Understanding the Core Principles of Continuous Delivery

Xike

Jul 13, 2026 · Backend Development

Getting Started with a Hands‑On Microservices Learning Project

This article introduces a runnable microservices learning project built with three independent Spring Boot applications (gateway, order, stock) and middleware such as Nacos, MySQL, Redis, RocketMQ, and Seata, guiding readers through cloning the repository, starting the environment with Docker Compose, and verifying the end‑to‑end product‑order‑stock flow.

Docker ComposeMicroservicesNacos

0 likes · 12 min read

Getting Started with a Hands‑On Microservices Learning Project

Xike

Jul 6, 2026 · Backend Development

Seeing the Full Request Journey: Completing Spring Boot Trace Integration

This guide shows how to extend an existing Prometheus‑Grafana‑Loki stack with SkyWalking to capture full request traces in Spring Boot, explaining trace fundamentals, automatic instrumentation, manual spans, log‑trace correlation, cross‑service topology, and production considerations.

Distributed TracingLogsSkyWalking

0 likes · 17 min read

Seeing the Full Request Journey: Completing Spring Boot Trace Integration

Xike

Jul 1, 2026 · Artificial Intelligence

How Skill Packages Turn AI Agents into Scenario Experts

The article explains how reusable Skill packages encapsulate domain knowledge, standard workflows, and output formats to enable AI agents to act professionally in specific contexts, addressing token efficiency, team conventions, and seamless integration with Loop, Harness, Context, Tool Use, and MCP.

AI agentsAgent workflowContext engineering

0 likes · 15 min read

How Skill Packages Turn AI Agents into Scenario Experts

Xike

Jun 26, 2026 · Artificial Intelligence

How Harness Puts a ‘Bridle’ on AI: Keeping Programming Agents Under Control

The article explains how the Harness framework acts as an operating system for LLM‑driven programming agents, enforcing permissions, step limits, state management, and human‑in‑the‑loop controls to make AI agents reliable, auditable, and safely interruptible.

AI agentsAgent LoopHarness framework

0 likes · 13 min read

How Harness Puts a ‘Bridle’ on AI: Keeping Programming Agents Under Control

Xike

Jun 25, 2026 · Artificial Intelligence

Why AI Code Generation Uses a Loop Instead of Simple Q&A

The article explains that AI-powered code writing relies on an Agent Loop—Plan, Act, Observe, Reflect—rather than a single question‑answer exchange, detailing each phase, termination rules, common pitfalls, and practical guidelines for building reliable iterative agents.

AI codingAgent LoopAutomation

0 likes · 9 min read

Why AI Code Generation Uses a Loop Instead of Simple Q&A

Xike

Jun 19, 2026 · Backend Development

Implementing Streamable HTTP with SSE for Real‑Time Chat in FastAPI

This article walks through adding a POST /v1/chat/stream endpoint that uses Server‑Sent Events (SSE) to stream structured events—including status, tool calls, token deltas, and completion—into a static web page, enabling a multi‑turn, typewriter‑style chat UI while preserving the original synchronous /v1/chat API for backward compatibility.

FastAPIJavaScriptapi

0 likes · 21 min read

Implementing Streamable HTTP with SSE for Real‑Time Chat in FastAPI

Xike

Jun 11, 2026 · Artificial Intelligence

Adding Memory: Enabling Multi‑Turn Conversations in an LLM Agent

This guide demonstrates how to replace a simple message list with a ContextManager that tracks user and assistant turns, estimates token usage, applies a sliding‑window truncation based on a token budget, and provides a single build_for_llm entry point to keep multi‑turn dialogues stable and observable.

AgentLLMPython

0 likes · 11 min read

Adding Memory: Enabling Multi‑Turn Conversations in an LLM Agent

Xike

Jun 10, 2026 · Artificial Intelligence

Step 0: Build a Conversational Entry Point for Your AI Agent

This tutorial launches the Agent series by showing how to create a minimal, CLI‑driven entry point that wraps the model API in a Brain.chat() method, configures credentials via a .env file, handles errors gracefully, maintains multi‑turn conversation state, and outlines the project structure and next development steps.

AI AgentCLIEnvironment Variables

0 likes · 15 min read

Step 0: Build a Conversational Entry Point for Your AI Agent

Xike

Jun 9, 2026 · Artificial Intelligence

From Demo to Production: Key Practices for Engineering LLM Agents

The article explains how to transform a prototype LLM agent into a reliable production service by defining service contracts, externalizing configuration, handling session state, implementing multi‑level rate limiting, and integrating observability, deployment, and rollback mechanisms to avoid common engineering pitfalls.

ConfigurationLLM agentsdeployment

0 likes · 25 min read

From Demo to Production: Key Practices for Engineering LLM Agents