Official JD Tech public account delivering best practices and technology innovation.
The article explains how Easy Code Reader MCP Server integrates with Joycode and large language models to automatically retrieve and analyze Java source code across multiple projects or JAR files, improving code‑agent accuracy and developer productivity.
This article outlines the motivation, design, architecture, engineering implementation, large‑model selection, and future improvement plans for an AI‑driven experiment analysis agent that integrates data aggregation, modular workflow orchestration, and interactive frontend features to streamline AB‑test insights.
The article explains how JD.com's AI virtual try‑on system Oxygen Tryon uses advanced computer‑vision and generative models to let shoppers instantly preview clothing on their own photos, dramatically improving purchase decisions, reducing return rates, and outlining technical challenges, innovations, and future development plans.
JoyCode Agent reaches a 74.6% pass rate on the authoritative SWE‑bench Verified benchmark, ranking in the global top‑3, and is now open‑source, showcasing a high‑efficiency, test‑driven, iterative approach to automated code repair that dramatically reduces token consumption while improving success rates.
This article examines a real-world incident where a massive cache key and cache penetration during a high‑traffic promotion caused Redis overload and a system outage, then details root‑cause analysis, mitigation steps like serialization changes, compression, lock‑based fallback, and preventive best practices.
This article details how JD Finance re‑engineered its complex chart rendering pipeline on the mobile app by integrating Apache ECharts via a custom WebView, introducing a reusable cache, automatic retries, and performance measurements that cut first‑screen rendering time by 200 ms and raised success rates to near 100 %.
This article explains the core concepts, working principles, advantages, drawbacks, and typical use cases of WebSocket, Server‑Sent Events, and WebRTC, and provides a detailed comparison to help developers select the most suitable real‑time communication technology for their web applications.
Over the past year, generative recommendation has made substantial progress by leveraging large language models' powerful sequence modeling and reasoning abilities, introducing a new paradigm that replaces complex handcrafted features, addresses traditional recommendation bottlenecks, and outlines the evolution, core technologies, engineering challenges, and future directions of LLM‑based recommendation systems.
This article details a backend developer's two‑year AI journey, the challenges of rapid model advances, and how applying microservice principles to Retrieval‑Augmented Generation (RAG) creates a scalable, multi‑agent platform for insurance knowledge, memory, and intelligent agents.
This article explains Apache Hudi's architecture, including its timeline mechanism, file layout, indexing strategies, table types (COW and MOR), query options, storage format versioning, backward compatibility, and key configuration settings for managing data lake tables.
