Recognizing real-time data innovations for the agentic era

Today, many organizations operate with data that’s trapped in silos, in disconnected legacy systems and is days or hours old. However, the rise of AI presents the need and opportunity to unify these environments, tap into unstructured data from audio, video, and text files, which together, makes up more than 80% of enterprise data and enable business decisions informed by real-time data. Data teams navigating AI also face a new set of challenges such as automating complex workflows and apps, grounding them in enterprise data, activating real-time insights on multimodal data, and building a foundation that inspires trust in AI. 

Google’s Data Cloud is an AI-native platform designed to unify an organization's entire data foundation and enable intelligent applications and agentic experiences. Data Cloud integrates Google infrastructure, intelligence, and data platform with pioneering AI advancements, including Gemini for working with data, automation of metadata management and governance, and flexible workflows for developers, allowing customers to focus on innovation and business outcomes rather than integration challenges. 

Recently, Google Cloud was honored to be recognized as a Leader in the 2025 Gartner® Magic Quadrant™ for Data Integration Tools. In Google Cloud opinion this demonstrates Data Cloud’s tight integration with data integration tools and vision for AI, including customer use cases for multimodal data processing, and scalable, efficient vectorization. In addition, Google Cloud was recognized as a leader in the Forrester Wave™ :Streaming Data Platforms, Q4 2025. In this blog post, Google Cloud take a look at recent updates and innovations that we believe made recognition from these two leading analyst firms possible.  

Boost productivity with Gemini-powered intelligence

Data agents are revolutionizing the way different data roles operate by bringing automation, intelligence, and natural language capabilities into their daily workflows. Whether you’re a data analyst querying and visualizing data more efficiently, a developer building smarter applications, or a data scientist accelerating model development, agents can help streamline repetitive tasks and boost your productivity. Data engineers benefit from automated data preparation and pipeline management, while ML engineers can deploy and monitor models more effectively. Even business users, who traditionally rely on technical teams for insights, can now interact with data directly using natural language. 

Recent innovations to Gemini with BigQuery for data engineering provide automation to build data pipelines to ingest, transform, and validate data. This includes data transformations like data cleaning, deduplication, formatting, standardizing, joins, and aggregations as well as data quality to enforce rules and standards. Building on these capabilities, the Data Engineering Agent further accelerates productivity by intelligently automating these standard integration patterns and proactively monitoring pipeline health.

Speed efficiency with multimodal automation and governance

Google Cloud is removing the friction to build AI applications using autonomous vector embedding for multimodal data. Building on Google Cloud BigQuery Vector Search capabilities, data teams can build, manage, and maintain complex data pipelines without needing to update vector embeddings. BigQuery now takes care of this automatically with added capabilities for agents to connect user intent to enterprise data. This is powering customer systems like the in-store product finder at Morrisons, which handles 50,000 customer searches on a busy day.

Google Cloud are also helping organizations ensure their data platform acts as a real-time brain for AI, including orchestration and AI-infused services. Governance is foundational to data and AI success. In today’s world of distributed data spanning lakes, warehouses, and operational systems, intelligence is impossible without unified governance. 

New automated cataloging with Dataplex Universal Catalog allows data teams to discover, ingest, and index metadata from a wide range of sources, minimizing the effort involved in cataloging data, and providing a near-real-time view of your data and AI landscape. Dataplex provides context to your data teams and your agents beyond the normal scope of a universal catalog. It leverages Gemini to continuously derive relationships and auto-generate business semantics, providing AI agents with trusted, real-time context. Ericsson uses Dataplex to deliver a unified business vocabulary to users, including data classification, ownership, retention policies, and sensitivity labels. This allows different data personas to instantly understand a data origin, increasing trust and reducing investigation time. 

Optimize workloads for broad usability 

Managing data across cloud and hybrid environments can be piecemeal, leading to costly inefficiencies, redundant storage, and complex data movement.

To help, visual pipelines provide a code-free user experience for designing, deploying, managing and monitoring pipelines, with a metadata-driven approach to improving developer productivity. And enhancements to data preparation in BigQuery provide a single platform to clean, structure, enrich and build data pipelines. 

For ML transformations supporting retrieval augmented generation (RAG) use cases, recent innovations enhance model inference to ML models in real-time or batch. And support for libraries and frameworks for multimodal data allows data teams to leverage multiple models in a single pipeline, improving accuracy and recall.

Integrating real-time data and context for AI

Agents need context in order to be effective and are significantly limited when they rely on static or outdated information. To make accurate decisions that genuinely help users and the business, they need real-time access to the current state of your systems and users. Google Cloud launched Managed Service for Apache Kafka last year to help you integrate your operational and transactional data into your AI and data platform that in turn can then power your AI agents. This year, Google Cloud added critical enterprise capabilities such as Apache Kafka Connect, VPC Service Controls, mutual TLS authentication, and Kafka access control which have helped customers like MadHive deploy to production in a matter of months. To enable new streaming architectures, we added User-Defined Functions support (UDFs) in Pub/Sub for transforming messages (like JSON) before they go to destinations like BigQuery, allowing custom logic, validation, and enrichment on the streaming data and making Pub/Sub pipelines more powerful and flexible. We also enhanced Dataflow, the advanced unified streaming and batch processing engine with critical capabilities such as parallel updates, Managed I/O, Google Cloud TPU support, speculative execution and more to bring the power of AI enabled data processing to advanced stream processing use cases such as continuous ML feature extraction and real time fraud detection.