Official JD Tech public account delivering best practices and technology innovation.
This article introduces JD's open‑source JoyAgent‑JDGenie, a lightweight multi‑agent framework, explains its architecture and performance, and provides step‑by‑step instructions for local Docker deployment, configuration, and usage for creating AI‑driven applications.
JD.com’s Genie open‑source AI agent introduces eight powerful capabilities—including plug‑in multi‑agent support, iterative planning, cross‑task context sharing, digital employee enhancements, deep model‑plus‑search, CodeTool for code lifecycle, refined system prompts, and a configurable MCP server—designed to boost intelligent workflow efficiency.
This article presents a thorough evaluation of the open‑source JoyAgent‑JDGenie multi‑agent AI framework, covering its background, test cases for restaurant recommendation and travel planning, deployment steps, performance metrics, and concluding recommendations, highlighting its efficiency, ease of deployment, and result quality.
This article presents a comprehensive migration plan for a legacy MongoDB‑based system, detailing scope analysis, dual‑write implementation, data source selection, bulk and incremental migration strategies, and a three‑pronged online approach (monitoring, gray release, rollback) to ensure a smooth cut‑over without service disruption.
This article describes how integrating causal inference with large language models and Retrieval‑Augmented Generation can automate and explain e‑commerce product pricing, detailing the three‑step workflow, reinforcement‑learning rewards, experimental results, and future directions for end‑to‑end RAG‑LLM training.
Learn how Spring interceptors work, their relationship with WebApplicationContext, various types, configuration methods, execution flow, advanced features, and practical examples such as logging and authentication, plus a comparison with servlet filters and demo results.
JD Advertising built a massive ad‑data warehouse on Apache Doris, reaching nearly 1 PB and 18 trillion rows, then implemented a hot‑cold data tiering strategy—first a lake‑based approach, later a native tiering solution in Doris 2.0—reducing storage costs by 87% and boosting query performance over tenfold.
This article shares the JD developer’s experience at the 2025 Huawei Developer Conference, detailing how the Cangjie language and a dual‑thread architecture were used to analyze and optimize high‑frequency JS API calls in JD mini‑programs on HarmonyOS, achieving up to 50% faster execution and a 20% reduction in cold‑start time.
Learn how to leverage MyBatis-Plus’s type-safe LambdaQueryWrapper together with Spring Boot’s @Async annotation to build efficient, asynchronous database operations, covering basic usage, advanced thread-pool configuration, exception handling, transaction management, and real-world scenarios for backend developers.
New developer Li Ming’s frustrating onboarding experience highlights hidden business rules, undocumented code, and poor knowledge transfer, prompting him to build an AI‑driven knowledge base that links code changes, requirements, and operational docs, ultimately streamlining troubleshooting, accelerating feature development, and improving knowledge retention across teams.
