Alibaba Cloud unveiled a strategic upgrade to its ODPS big data platform at the 2026 Yunqi Conference, introducing AI-native, multimodal capabilities across MaxCompute, Hologres, and DataWorks to support Agentic AI workloads with vector search, heterogeneous compute, data sandboxes, and semantic knowledge graphs.
At Yunqi 2026, Alibaba Cloud unveiled a strategic upgrade to its ODPS big data platform, introducing agent-native architecture and multimodal computing across MaxCompute, Hologres, and DataWorks to support large model data refinement, embodied intelligence, and autonomous data operations with SQL AI, vector search, data sandboxes, and semantic knowledge graphs.
Xinfēi Technology, a fintech data‑intelligence provider, cut its multi‑country data‑warehouse rollout from three months to about two weeks by adopting Alibaba Cloud’s DataWorks Data Agent, which unified data ingestion, task development, quality configuration, lineage analysis and release verification, introduced Skills and an enterprise semantic layer, and achieved up to six‑fold efficiency gains across ODS, DWD, DWS, DQC and reporting.
The article analyzes how Taobao Live’s data team replaced traditional ETL bottlenecks with an AI‑native, three‑layer architecture built on DataWorks Data Agent, adopting NL2DSL2SQL, multi‑agent orchestration, and standardized pipelines to achieve near‑full automation and higher accuracy.
The article systematically outlines DataWorks Data Agent’s progression from a Copilot‑assisted tool to human‑AI collaboration and finally AI‑driven autonomy, details its four‑agent product matrix covering data development, operations diagnostics, autonomous governance and ChatBI, describes three architecture iterations (Dify, AgentScope, QwenCode/OpenClaw) and a cloud‑managed deployment, and cites real‑world efficiency gains such as cutting development cycles from hours to minutes.
Cainiao combines a decade of logistics data-warehouse experience with Alibaba Cloud’s DataWorks Data Agent to build the SuperETL intelligent system, which orchestrates nine fine-grained skills, enforces safety hooks, and boosts data-development efficiency by 2-3× while achieving over 80% AI automation in key scenarios.
The article details how Taobao Live’s data engineering team replaced traditional ETL bottlenecks with a three‑layer, AI‑native architecture built on DataWorks Data Agent, using NL2DSL2SQL, ontology‑driven knowledge bases, and multi‑agent collaboration to achieve near‑100% code generation and higher accuracy.
The article systematically outlines DataWorks Data Agent’s three‑stage evolution—from Copilot assistance to human‑AI collaboration and finally AI‑driven autonomy—details its four‑agent product matrix covering the full data lifecycle, describes the cloud‑managed engineering rollout, and presents a Taobao flash‑sale case where development cycles shrank from hours to minutes, highlighting efficiency gains, security measures, and architectural iterations.
This article walks through using DataWorks Data Agent to automate end‑to‑end data‑warehouse development—from preparing source tables and a structured requirement document, uploading it, crafting task commands, selecting execution modes and models, to the agent generating SQL, building workflows, publishing them, and producing a final report—all without writing SQL manually.
DataWorks Data Agent advances from an assisted, code‑completion tool to a fully autonomous data‑intelligent agent, using a dual‑engine CLI/Claw architecture, unified runtime, open Skill ecosystem, and CPU‑GPU co‑optimization to automatically understand requirements, explore data, generate code, execute tasks, and deliver end‑to‑end results for developers and operators.
The article analyzes DataWorks Data Agent’s evolution from a helper‑style tool to an autonomous data‑centric AI agent, detailing its five‑stage roadmap, dual‑engine CLI/Claw architecture, unified runtime kernel, open skill ecosystem, and CPU‑GPU joint optimization for enterprise‑grade data automation.
The article details how DataWorks Data Agent integrates logistics industry standards and a skill‑based orchestration to overhaul the data development workflow, delivering 2‑3× efficiency gains and up to 80% AI‑automated task completion through SuperETL, hooks, and CLI tools.
The article outlines DataWorks' evolution from a decade‑long big‑data governance platform to an AI‑driven Copilot and autonomous Agent system, detailing its technical foundations, tool‑adaptation layer, context engineering, security safeguards, and future vision of a professional, open, and intelligent big‑data development ecosystem.
This article explains how DataWorks integrates data quality specifications directly into the SQL development workflow using Data Contracts, addressing governance lag, versioning gaps, and trust issues while providing a unified, version‑controlled, and automated quality assurance process for offline data pipelines.
This guide walks you through setting up a secure, elastic, and high‑performance AI data processing platform on Alibaba Cloud by combining DataWorks, MaxCompute, and MaxFrame, covering the four essential steps, code examples, best‑practice tips, and common troubleshooting advice.
Alibaba Cloud’s DB‑Surfer NL2SQL agent combines task‑planning, metadata linking, and a modular architecture to achieve state‑of‑the‑art performance on the Spider 2.0‑Snow benchmark and is now integrated into DataWorks Copilot, dramatically improving enterprise data query efficiency.
This article chronicles ODPS's 15‑year journey from its exploratory beginnings to a modern, AI‑enabled big data platform, detailing its four development phases, architectural layers, SQL engine upgrades, real‑time processing, lakehouse integration, and the new Data+AI capabilities offered by MaxCompute and DataWorks.
This guide explains how to use Alibaba Cloud DataWorks to create the necessary resources, configure Milvus and MaxCompute data sources, set up an offline single‑table synchronization task, and verify the imported vectors, enabling efficient AI‑driven vector search on large structured datasets.
WeddingJoy, a comprehensive wedding service platform, transformed its data infrastructure by adopting Alibaba Cloud DataWorks, addressing challenges of massive heterogeneous data, improving data governance, enabling AI-driven insights, and boosting development efficiency across its ecosystem.
This article details a comprehensive DataOps implementation using Alibaba Cloud's DataWorks, Flink, StarRocks, MaxCompute, and Yunxiao pipeline, covering four-layer architecture, standardized development, automated CI/CD with gray releases, full-chain quality monitoring achieving 80% self-healing, cross-team collaboration, cost optimization, and a phased rollout roadmap delivering 30% faster delivery and 30% cost reduction.
This tutorial walks through using DataWorks Notebook with GPU support to combine the open‑vocabulary visual model RAM and the language model BERT for zero‑shot multimodal image captioning, covering environment setup, model installation, dataset preparation, tagging code, and result visualization.
This step‑by‑step guide explains how to use Alibaba Cloud's MaxCompute, DataWorks, and the AI platform PAI to build a custom dataset, fine‑tune the DeepSeek‑R1 distilled model, and deploy the resulting model for practical applications.
This tutorial shows how to use Alibaba Cloud DataWorks' serverless GPU resource groups together with the open‑source LLaMA‑Factory framework to fine‑tune the Qwen2‑VL‑2B multimodal model for tourism‑domain Q&A, covering environment setup, dataset preparation, parameter configuration, training, and interactive inference.
This guide walks you through setting up a personal DataWorks Notebook, performing interactive SQL development with engines like MaxCompute, creating Python visualizations, building ipywidgets for dynamic queries, and leveraging the AI‑powered Copilot to rewrite, explain, and comment code, all within a unified big‑data platform.
This guide walks you through setting up Alibaba Cloud DataWorks, creating a workspace and personal development environment, and importing a Kaggle house‑price prediction notebook to perform data loading, cleaning, feature engineering, model training, and evaluation—all without writing code from scratch.
This article introduces Alibaba Cloud DataWorks' intelligent data modeling tool, outlines the data demand flow, shares best practices and practical demonstrations of data warehouse modeling, discusses model application and data asset management, and answers common questions while highlighting its commercial availability.
This article introduces Alibaba Cloud DataWorks' intelligent data modeling tool, outlines the data demand flow, shares best practices and hands‑on demonstrations for data warehouse modeling, discusses common challenges and their solutions, and provides Q&A and product details for developers and data engineers.
This article presents Alibaba's experience in addressing large‑scale data stability challenges by outlining common problems, governance principles, baseline monitoring, team collaboration methods, practical implementations, and proactive measures to ensure reliable and accurate data production on the DataWorks platform.
This article presents a comprehensive case study of Taobao's data model governance, detailing the background challenges, the four‑pillar solution framework, specific governance practices such as invalid table decommissioning, data handover, public layer operations, incremental control, productization, future plans, and a Q&A session.
This step‑by‑step tutorial shows how to set up Alibaba Cloud DataWorks and MaxCompute, bind them together, and use free trial resources to explore public big‑data datasets such as Alibaba e‑commerce, Github events, and custom data with SQL queries and visualizations.
This article explores Alibaba's DataWorks platform and its comprehensive data governance practices, covering application efficiency, security controls, cost optimization, organizational structure, and cultural initiatives that together enable scalable, secure, and cost‑effective data management across the enterprise.
Alibaba’s DataWorks team shares extensive insights on building and evolving a large‑scale data platform, covering the journey from data volume growth to user adoption, and detailing governance challenges such as stability, efficiency, risk control, and cost reduction across four maturity stages.
This comprehensive tutorial walks you through Alibaba DataWorks' data warehouse architecture, covering technical stack selection, three‑layer warehouse design (ODS, CDM, ADS), detailed data modeling with DDL examples, storage strategies, dimension and fact table conventions, and best‑practice hierarchical call standards.
This article presents a comprehensive overview of Taobao's data model governance, detailing the background and problems of the current data architecture, analyzing root causes, proposing a structured governance framework with DataWorks automation, and outlining future plans to improve efficiency, standardization, and product tooling.
This report details Alibaba’s large‑scale data model governance initiative for the DaTao ecosystem, analyzing current data issues such as naming inconsistencies, low reuse, and application‑layer inefficiencies, and presents a comprehensive solution—including a model evaluation system, DataWorks co‑development, intelligent modeling, data map enhancements, and future roadmap—to improve data health, reduce costs, and increase operational efficiency.
This article summarizes Guo Jinshi's presentation on Taobao's data model governance, covering the current data landscape, identified problems, analysis of root causes, proposed governance solutions—including DataWorks intelligent modeling—and future plans, while also providing a Q&A session on practical implementation.
This article outlines the design and implementation of a minute‑level order‑fulfillment timeliness simulation platform, detailing its background, objectives, challenges, architecture built on Alibaba Cloud DataWorks, core workflow nodes, domain model, ER diagram, JSON task templates, and future extensions for supply‑chain routing.
This guide walks through creating a home temperature‑humidity monitoring system with a Raspberry Pi and DHT11 sensor, collecting data via JavaScript, sending it to Alibaba Cloud SLS, processing it through DataWorks and MaxCompute, and visualizing the results in QuickBI dashboards.
Taobao’s rapidly expanding technical data system faced naming inconsistencies, low table reuse, and costly, inefficient data usage, prompting a joint effort with DataWorks to digitize model evaluation, enforce standardized governance, deliver intelligent end‑to‑end modeling tools, and launch a development assistant, resulting in a health‑monitoring dashboard, upgraded data maps, and a roadmap for further automation and architecture refinement.
This article details Alibaba's large‑scale data model governance initiative, analyzing current data issues, presenting a comprehensive solution—including model digitization, public model sinking, productization, daily governance, and search‑enhancement—and outlining achieved results and future plans to further improve data quality, reuse, and operational efficiency.
DataWorks, Alibaba Cloud’s comprehensive PaaS platform, combined with the serverless MaxCompute data warehouse, offers an integrated solution for data integration, development, quality, and services, while detailed naming and layer conventions ensure scalable, maintainable big‑data architectures and effective governance across ODS, CDM, DWD, DWS, and ADS layers.
This presentation details Alibaba Cloud DataWorks Data Integration (DataX), covering its architecture, core design principles, offline and real‑time synchronization mechanisms, deployment modes, product positioning, use‑case scenarios, and its role within the broader DataWorks ecosystem, highlighting its capabilities for large‑scale data movement and processing.
This tutorial explains how to select a technical architecture, design a three‑layer data warehouse (ODS, CDM, ADS), model tables and dimensions, choose storage strategies, handle slowly changing dimensions, synchronize data with DataWorks, and implement dimensional modeling and fact tables using Alibaba MaxCompute for big‑data analytics.
This article explains how new‑retail companies can design and implement a data middle platform using Alibaba Cloud's DataWorks, covering business model analysis, technical architecture, layer‑by‑layer data modeling, governance, security, and the concrete benefits of turning raw data into actionable business insights.
This article examines the long‑standing technical and operational challenges of Alibaba's DataWorks platform—such as heavy legacy baggage, complex environments, tight coupling, and frequent releases—and explains how adopting a cloud‑native microservice architecture, service mesh, and DevOps practices can transform the platform into a flexible, scalable, and future‑proof data development ecosystem.
