#AI编程
9454 related articles
Mastering AI Agent Development: From Underlying Logic to Enterprise-Level Practice
From native large models and prompt engineering to RAG and Agents, this article maps the four stages of enterprise LLM adoption, explains the four core problems Agents solve and four mainstream agent types, helping you build an actionable AI Agent development framework.
Transitioning from Traditional Development to LLM Application Development: Avoiding the Three Hurdles 90% of Courses Don't Teach
Traditional backend developers transitioning to LLM application development face three real hurdles—model capability boundaries, requirement judgment, and effect evaluation—not math. This article breaks down the core engineering skills 90% of courses don't teach and offers a practical transition path.
LLM WIKI in Practice: Making Agents Truly Understand Enterprise Business — Building a Troubleshooting Agent from Scratch
Inaccurate agent responses stem from a lack of business understanding. Based on a real order customer service troubleshooting agent case, this article explains how LLM WIKI builds a business knowledge base from codebases, uses incremental updates, and connects to agents via MCP server to achieve business understanding and troubleshooting with zero documentation.
A Computer Science PhD's Take: AI Career Planning for New Graduates — Algorithm vs. Application Development
A CS PhD advises new graduates on AI careers: try algorithm roles first but don't fixate; application development has more openings. Focus on LLM fine-tuning/deployment and agent frameworks (MetaGPT, LangChain), and watch AI + industry implementation to broaden job paths.
Getting Started with Agent Application Development: From Concepts to Practice, Understanding AI Agents
From large model functions to Agent system forms, this article breaks down the six core components of Agents, their essential differences from traditional AI and Workflows, high-frequency interview follow-ups, and production deployment risks, helping developers quickly build a complete cognitive framework for AI agent development.
What an AI Agent Really Is: A Hands-On Guide to Building Your Own
Starting from a Bilibili tutorial, this article explains the essential definition of AI Agents, their relationship to large models, and task-decomposition logic, and explores why rule design is the real barrier to building your own agent, offering developers practical implementation ideas.
LangGraph Crash Course: Building Enterprise-Grade AI Agents and Workflows from Scratch
LangGraph crash course: learn its independence from LangChain, MIT license, FastAPI high-concurrency deployment, human approval, and memory storage for enterprise AI agents.
Loop Engineering: An Engineering Paradigm for AI That Writes Code and Merges PRs Autonomously
Loop Engineering is transforming AI development pipelines: Stripe's Minions system merges over 1,300 machine-generated PRs weekly. This article breaks down Loop Engineering's five core actions, six components, five failure modes, and three safety disciplines, explaining why independent evaluators, state files, and budget caps matter more than full automation.
Two Weeks of Spare Time: I Used AI to Build an Android "Book of Life" for My Parents
Inspired by the "Book of Life" AI Historian app, I took on a two-week challenge—one hour a day after work—using AI coding to build an Android Book of Life agent that turns ordinary people's stories into books.
The Faster AI Writes Code, the Messier the Project? Six Layers of Engineering Governance from YOLO Visual Agent Vol.19
Why does AI coding speed make projects messier? Bilibili's YOLO Visual Agent Vol.19 shares six layers of engineering governance: AGENTS files, task brief and finish review workflows, file-based plans, frontend/backend boundary governance, and automated checks to keep AI-generated code maintainable long-term.
Linux Kernel's AI Civil War: Anti-AI Activist Elected to TAB, Torvalds Scraps AI Disclosure
Anti-AI activist Laurent Pinchart elected to the Linux kernel TAB as Linus Torvalds scraps AI code disclosure. A rundown of the kernel community's AI civil war, both sides' positions, and the impact on open source.
Vercel CLI Adds Budget Management: Control Team Spending from the Terminal
Vercel CLI adds Spend Management budget features: view, set, and delete team budgets with `vercel budgets`, query alert history, and use `--pause` to suspend production deployments on overspend.
Codex CLI 0.164: Preset Slots and Inline Model Parameter Parsing
Codex CLI 0.164.0 adds ten /presets slots, inline parameters for /model and /permissions, and credential masking for remote commands. Here's what these updates mean in practice, their security implications, and upgrade checks.
@ai-sdk/tui 1.0.153 Released: Minor Update to the TUI Toolchain
@ai-sdk/tui 1.0.153 released: a patch update that syncs the ai core package to 7.0.152. Essential upgrade notes for developers working with the AI SDK terminal UI toolchain.
AI SDK Vue 3.0.315 Patch Release: How Vue Developers Should Respond
AI SDK Vue releases patch 3.0.315, syncing with core package ai@6.0.315. No new features or breaking changes. We break down the version info and upgrade advice.
AI SDK Vue 2.0.281 Release Update Analysis
AI SDK Vue 2.0.281 released: a patch update syncing core dependency ai@5.0.281. Analysis of changes, developer impact, and upgrade advice for Vue developers.
AI SDK Vue 4.0.152 Patch Released: Synced Upgrade of the ai Package
AI SDK Vue 4.0.152 patch released, synchronously upgrading the underlying ai package to 7.0.152. This article explains the core changes, impact on Vue AI applications, and upgrade considerations.
AI SDK Workflow Harness 1.0.163 Patch Released, Stability Improved Again
AI SDK workflow harness @ai-sdk/workflow-harness releases patch 1.0.163, with @ai-sdk/harness updated in sync, focusing on stability fixes to help developers build reliable AI workflows.
AI SDK Workflow 2.0.84 Patch Released: ai Package Upgraded to 7.0.152
AI SDK Workflow 2.0.84 is released, a patch update syncing the ai package dependency to 7.0.152. This article explains what the patch change means, the automated release pipeline, and production upgrade advice.
How Does ChatGPT Work Turn Notes into AI Training Packages?
RealPage's Director of AI Enablement Austin Bram shares how he uses ChatGPT Work to quickly transform personal notes and source materials into complete AI training enablement packages, providing personalized, consistent AI education for different teams and roles and improving employees' AI application capabilities.