Official account of DaTaobao Technology
This article introduces a test‑driven AI programming loop that tackles the “last‑mile” problem of AI‑generated code by adding automated acceptance, self‑testing, bug fixing, and continuous iteration, demonstrated through a favorite‑count feature repair case and outlining future enhancements.
This comprehensive guide explains the underlying principles of AI coding assistants—including token calculation, tool calling, codebase indexing, and Merkle tree synchronization—while offering actionable best‑practice recommendations for prompt engineering, incremental development, documentation, security compliance, and effective team adoption.
This article reveals the core methodology of applying AI coding to complex client-side development, discusses practical challenges, prompt design, task decomposition, efficiency improvements, and provides actionable guidelines and architectural rules for integrating AI into UI and service layers.
The article explains how AI is shifting from low‑formal Prompt Engineering to medium‑formal Context Engineering by applying language formalization concepts such as the Chomsky hierarchy, improving traceability, reliability, and system verification while sacrificing some unrestricted LLM expressiveness.
The article describes WaterFlow, an AI‑driven end‑to‑end development platform at Taobao that turns natural‑language requirements into PRDs, multi‑platform code, tests and releases, cutting iteration time from a week to two days and shipping over 30 features with more than 54,000 lines of generated code.
This article provides an in‑depth technical breakdown of Anthropic's Claude Code terminal AI programming tool—including its layered system architecture, command execution pipeline, context management, security model, binary feedback mechanism, and the newly released iFlow CLI 2.0 with sub‑agents, MCP tool integration and multi‑mode operation—illustrated with code snippets and real‑world usage examples.
This article details how a multimodal AI model was integrated to detect and improve ID card photo quality, covering common image issues, differences between OCR and multimodal extraction, deployment strategies, performance metrics, cost estimation, and the resulting business and technical benefits.
This article explains how a multi‑agent AI system shifts asset‑loss control from reactive to proactive by building a full‑link protection framework that extracts knowledge, identifies risks, automatically deploys safeguards, and continuously learns from incidents, delivering faster, more accurate financial security for e‑commerce platforms.
This article details how the author transformed a constrained Weex/Muise front‑end project for the “giraffe” search page into an AI‑driven workflow, building a structured knowledge base, defining project‑level rules, and using RAG techniques to accelerate component, tracking, and payment integration, ultimately reducing development time by 60% and proposing a new “AI programming as context engineering” paradigm.
This article explains why AI coding assistants like Cursor and Claude fail to read external Java libraries, explores naive "feed‑the‑code" tricks, evaluates built‑in IDE tools, and ultimately presents a robust solution using a local decompilation pipeline (MCP) that lets LLMs query class definitions and generate correct backend code.
