Tibor Kiss

Box is one of the original information sharing and collaboration platforms of the digital era. They’ve helped define how we work, and have continued to evolve those practices alongside successive waves of new technology. One of the most exciting advances of the generative AI era is that now, with all the data that Box users have stored, they can get considerably more value out of those files by using AI to search and synthesize their information in new ways.

That’s why Box created Box AI Agents, to intelligently discern and structure complex unstructured data. Today, we’re excited to announce the availability of the Box AI Enhanced Extract Agent. The Enhanced Extract Agent runs on Google’s most advanced Gemini 2.5 models, and they also feature Google’s Agent2Agent protocol, which allows secure connection and collaboration between AI agents across dozens of platforms in the A2A network.

The Box AI Enhanced Extract Agent gives enterprises users confidence in their AI, helping overcome any hesitations they might feel about gen AI technology and using it for business-critical tasks.

In this post, we’ll take a closer look at how our teams created the Box AI Enhanced Extract Agent and what others building new agentic AI systems might consider when developing their own solutions.

Getting more content with confidence

When it comes to data extraction, simply pulling out text from documents is no longer sufficient. A core objective that businesses need peace of mind on is uncertainty estimation, which we define as understanding how uncertain the model is about particular extraction. This is paramount when an organization is processing vast quantities of documents — such as searching tens of thousands of items where you’re trying to extract all the relevant and related values in each of those items — and you need to guide human review effectively and with confidence. The goal isn’t just high accuracy, but also a reliable confidence score for each piece of extracted data.

With the Box AI Enhanced Extract Agent, we wanted to transform how businesses interact with their most complex content — whether that’s scanned PDFs, images, slides, and other diverse materials — and then turn it all into structured, actionable intelligence. 

Box and Box AI are already available on Google Cloud Marketplace. 

For instance, financial services organizations can automate loan application reviews by accurately extracting applicant details and income data; legal teams can accelerate discovery by pinpointing critical clauses in contracts; and HR departments can streamline onboarding by processing new hire paperwork automatically. In each of these cases, all extracted data like key dates and contractual terms can be validated by the crucial confidence scores that this Box and Google collaboration delivers. This confidence score helps ensure reliable, AI-vetted information powers efficient operations and proactive compliance without extensive manual effort.

Powering enhanced data extraction with Gemini 2.5 Pro

Box’s Enhanced Extract Agent leverages the sophisticated multimodal, agentic reasoning and capabilities of Google’s Gemini 2.5 Pro as its core intelligence engine. However, the relationship goes beyond simple API calls.

“Gemini 2.5 Pro is way ahead due to its multimodal, deep reasoning, and code generation capabilities in terms of accuracy compared to previous models for these complex extraction tasks,” Ben Kus, CTO at Box said. “These capabilities make Gemini a crucial component for achieving Box’s ambitious goals of turning unstructured content into structured content through enhanced extraction agents.”

To build robust confidence scores and enable deeper understanding, Box’s AI Agents acquire specific, granular information that the Gemini 2.5 Pro model is uniquely adept at providing.

An agent-to-agent protocol for deeper collaboration

Box is championing an open AI ecosystem by embracing Google Cloud’s Agent2Agent protocol, enabling all Box AI Agents to securely collaborate with diverse external agents from dozens of partners (a list that keeps growing). By adopting the latest A2A specification, Box AI can ensure efficient and secure communication for complex, multi-system processes. This empowers organizations to power complex, cross-system workflows—bringing intelligence directly to where content lives, boosting productivity through seamless agent collaboration.This advanced interplay leverages the proposed agent-to-agent protocol in the following manners:

1. Box’s AI Agents: Orchestrate the overall extraction task, manages user interactions, applies business logic, and crucially, performs the confidence scoring and uncertainty analysis.

2. Google’s Gemini 2.5 Pro: Provides the core text comprehension, reasoning, and generation; and in this enhanced protocol, Gemini models also aim to furnish deeper operational data (like token likelihoods) to its counterpart.

This protocol, for example, allows Box’s Enhanced Extract Agent to “look under the hood” of Gemini 2.5 Pro to a greater extent than typical AI model integrations. This deeper insight is essential for:

• Building Reliable Confidence Scores: Understanding how certain Gemini 2.5 Pro is about each generated token allows Box AI’s enhanced data extraction capabilities to construct more accurate and meaningful confidence metrics for the end-user.

• Enhancing Robustness: Another key area of focus is model robustness ensuring consistent outputs. As Kus put it: “For us robustness is if you run the same model multiple times, how much variation we would see in the values. We want to reduce the variations to be minimal. And with Gemini, we can achieve this.” 

Furthering this commitment to an open and extensible ecosystem, Box AI Agents will be published on Agentspace and will be able to interact with other agents using the A2A protocol. Box has also published  support for the Google’s Agent Development Kit (ADK) so developers can build Box capabilities into their ADK agents, truly integrating Box intelligence across their enterprise applications.

The Google ADK, an open-source, code-first Python toolkit, empowers developers to build, evaluate, and deploy sophisticated AI agents with flexibility and control. To expand these capabilities, we have created the Box Agent for Google ADK , which allows developers to integrate Box’s Intelligent Content Management platform with agents built with Google ADK, enabling the creation of custom AI-powered solutions that enhance content workflows and automation. 

This integration with ADK is particularly valuable for developers, as it allows them to harness the power of Box’s Intelligent Content Management capabilities using familiar software development tools and practices to craft sophisticated AI applications. Together, these tools provide a powerful, streamlined approach to build innovative AI solutions within the Box ecosystem.

Continual learning and human-in-the-loop, for the most flexible AI

The vision for enhanced extract includes a dynamic, self-improving system. “We want to implement that cycle so that you can get higher and higher confidence,” Kus, Box’s CTO, said. “This involves a human-in-the-loop process where low-confidence extractions are reviewed, and this feedback is used to refine the system.”

Here, the flexibility of Gemini 2.5 Pro, particularly concerning fine-tuning, enables continual improvement. Box is exploring advanced continual learning approaches, including:

• In-context learning: Providing corrected examples within the prompt to Gemini 2.5 Pro.

• Supervised fine-tuning: Google Cloud’s Vertex AI allows Box to store the fine-tuned weights in the company’s system and then just use them to run their fine-tuned model.

Box AI’s Enhanced Extract Agent would manage these fine-tuned adaptations (for example through small LoRA layers specific to a customer or document template) and provide them to the Gemini 2.5 Pro agent at inference time. “Gemini 2.5 Pro can be used to leverage these adaptations efficiently, using the context caching capability of Gemini models on Vertex AI to tailor its responses for specific, high-value extraction tasks using in-context learning. This allows for ‘true adaptive learning,’ where the system continuously improves based on user feedback and specific document nuances,” Kus said.

The future: Premium document intelligence powered by advanced AI collaboration

The Enhanced Extract Agent — underpinned by Gemini 2.5 Pro’s features such as multimodality, intelligent reasoning, planning and tool-calling, and large context windows — is envisioned as as a key differentiator that Box leverages in developing their AI Hub and Agent family. Box views the Enhanced Extract Agent as a fundamental way in which organizations can build more confidence in how they deploy AI in the enterprise.

For the Google team, it’s been exciting to see the production-grade, scalable use of our Gemini models by Box. Their solution not only provides extracted data, but meta-data semantics enabling a high degree of confidence and a system that uses the Box content and agents on top of Gemini models to enable the Enhanced Data Extraction Agent to adapt and learn over time.

The ongoing collaboration between Box and Google Cloud focuses on unlocking the full potential of models like Gemini 2.5 Pro for complex enterprise use cases, which are rapidly redefining the future of work and paving the way for the next generation of document intelligence powering the agentic workforce.

To reimagine your data, your assets, and your workplace, access Box and Box AI now in Google Cloud Marketplace.

Hospitals, while vital for our well-being, can be sources of stress and uncertainty. What if we could make hospitals safer and more efficient — not only for patients but also for the hard-working staff who care for them? Imagine if technology could provide an additional safeguard, predicting falls, or sensing distress before it’s even visible to the human eye.

Many hospitals today still rely on paper-based processes before transforming critical information to digital systems, leading to frequent — and sometimes, remarkably absurd — inefficiencies. In-person patient monitoring, while standard practice, can be slow, incomplete, and subject to human error and bias. In one serious incident, shared by hospital staff, a patient fell shortly after getting out of bed at 5 a.m. and wasn’t discovered until the routine 6:30 a.m. check. Events like this underscore the need for continuous, 24/7 in-room monitoring solutions that can alert staff immediately in high-risk and emergency situations. 

Driven by a shared vision to enhance patient care, healthcare innovator Hypros and Google Cloud joined forces to develop an AI-assisted patient monitoring system that detects and alerts staff to in-hospital patient emergencies, such as out-of-bed falls, delirium onset, or pressure ulcers. This innovative privacy-preserving solution enables better prioritization of care and a strong foundation for clinical decision-making — all without the use of invasive cameras.

Privacy-preserving, AI-assisted patient monitoring

While the need for 24/7 patient monitoring is clear, developing these solutions raises important concerns around privacy and professional conduct. Privacy is paramount in any patient-monitoring technology for both the individuals receiving care and the professionals providing it. Even seemingly simple aspects, such as interventions within the patient’s immediate surroundings, require strict compliance with hospital hygiene policies — a lesson reinforced during the COVID-19 pandemic.

It’s crucial to monitor and correct any mistakes without singling out individuals. By using tools like low-resolution sensors, we can protect people’s identities and reduce the risk of unfair judgment, keeping the focus squarely on improving care. This approach is especially valuable, since the root cause of errors, more often than not, extend beyond the individual. As a result, ethical technology deployment of monitoring, AI or otherwise, means ensuring that the efficiencies or insights gained never compromise fundamental rights and well-being.

The approach for continuous patient monitoring hinges on two key innovations: 

1. Non-invasive IoT devices: Hypros developed a novel battery-powered Internet of Things (IoT) device that can be mounted on the ceiling. This device uses low-resolution sensors to capture minimal optical and environmental data, creating a very low-detail image of the scene. The device is designed to be non-invasive, preserving anonymity while still gathering the crucial information needed to detect any meaningful changes in a patient’s environment or condition.

2. Two-stage AI workflow: Hypros employ a two-stage machine learning (ML) workflow. Initially, they trained a camera-based vision model using AutoML on Vertex AI to label sensor data from simulated hospital scenarios. Next, they use this labeled dataset to train a second model to interpret low-resolution sensor data.

The following sections explain how Hypros implemented these innovations into their patient monitoring solution, and how Google Cloud assisted Hypros in this endeavor.

Low resolution, high information: Securing patient privacy

To address the critical need for patient privacy while enabling effective hospital bed monitoring, Hypros developed a compact, mountable IoT device (see Figure 1) equipped with low-resolution optical and environmental sensors. This innovative solution operates on battery power, facilitating easy installation and relocation to various bed locations as needed.

The device’s low-resolution optical sensors are effective for protecting patient privacy, they also can make data interpretation and analysis more complex. Additionally, low sampling rates and environmental factors can introduce noise and sparsity into the data, resulting in an incomplete representation of human behavior in the hospital. The combination of low-resolution imaging, limited sampling rates, and environmental noise creates a complex data landscape that requires sophisticated algorithms and interpretive models to extract meaningful insights.

Despite these challenges, Hypros’ device represents a significant advancement in privacy-preserving patient monitoring, offering the potential to enhance hospital workflow efficiency and patient care without compromising individual privacy.

Patient monitoring with AI: Overcoming low-resolution data challenges

While customized parametric algorithms can partially interpret sensor data, they have difficulty handling complex relationships and edge cases. ML algorithms offer clear advantages, making AI a vital tool for a patient monitoring system.

However, the complexity of their sensor data makes it difficult for AI to independently learn the detection of critical patient conditions, and thus, unsupervised learning techniques would not yield useful results. In addition, manual data labeling can quickly become expensive as tight monitoring sends readings every few seconds, quickly producing large volumes of data.

To solve these issues, Hypros adopted an innovative approach that would allow AI to learn how to detect scenarios from their monitoring devices with minimal labeling effort. They found that using pre-trained AI models, which require fewer examples to learn a new image-based task, can simplify labeling image data. However, these models struggled to interpret their low-resolution sensor data directly.

Therefore, they use a two-step process. First, they train a camera-based vision model using camera data to produce a larger, labelled dataset.Then, they transfer these labels to concurrently recorded sensor data, which they use to train a patient monitoring model. This unique approach enables the system to reliably detect events of interest, such as falls or early signs of delirium, without compromising patient privacy.

Driving healthcare innovation with Google Cloud

Hypros relied heavily on Google Cloud to build their patient monitoring system, particularly its data and AI services. The first crucial step was collecting useful data to train their AI models.

They began by replicating a physical hospital room environment within their offices. This controlled setting enabled them to simulate various realistic scenarios, gather data, and record video. During this phase, they also collaborated closely with hospitals to ensure that the characteristics specific to each use case were accurately determined.

Next, they trained a camera-based vision model with AutoML on VertexAI to label sensor data. This process was remarkably straightforward and efficient. Within approximately two weeks, their initial AutoML camera-based vision model used for labeling achieved an average precision exceeding 91% across all confidence thresholds. Already impressive, the actual performance was higher as labeling discrepancies artificially lowered the results.  

Subsequently, they labeled various video recordings from hospital beds and correlated these labels with their device data for model training. This approach allowed the model to learn how to interpret sensor data sequences by observing and learning from the corresponding video. For training use cases that didn’t incorporate video information, they relied on data or simulation methodologies from their hospital partners.

The speed of development cycles is also a critical competitive advantage. Therefore, they mapped every step in their workflow and model development cycles (see Figure 4) to the following Google Cloud services:

• Cloud Storage: Stores all raw data, enabling easy rollbacks and establishing a clear baseline for ongoing improvements.

• BigQuery: Stores labeled data for easier querying, and analysis querying and analysis. Easy access to the right data helps them iterate, analyze, debug, and refine their models more efficiently.

• Artifact Registry: Hosts their custom Docker images in ETL and training pipelines. Fewer downloads, shorter builds, and better software dependency management provides smoother, more optimized operations.

• Apache Beam with Dataflow Runner: Processes large volumes of data at high speed, keeping their pipelines fast and maximizing their development time.

• Vertex AI: Provides a unified platform for model registration, experiment tracking, and visualizing results in TensorBoard; training is done with TensorFlow and TFRecords, using customized resources (like GPUs) and easy deployment options simplify rolling out new model versions.

With Google Cloud’s ability to handle petabytes of data, they know their workflows are highly scalable. Having a powerful, flexible platform lets them focus on delivering value from data insights, rather than worrying about infrastructure.

Further possibilities: Distilling nuanced information

The development of their system has sparked more ideas about ways hospitals can benefit from using sensor data and AI. They see three main areas of care where continuous patient monitoring can help: patient-centric care for better outcomes, staff-centric support to optimize their time, and environmental monitoring for safer spaces.

Some potential use cases include:

• People detection: Anonymously detect individuals to improve operations, such as bed occupancy for patient flow management.

• Fall prevention and detection: Alert staff about patient falls or flag restless behavior to prevent them.

• Pressure ulcers: Monitor 24/7 movement to aid clinical staff in repositioning patients effectively to prevent the development of pressure ulcers (bedsores).

• Delirium risk indicators: Track sleep disruption factors like light and noise, which are potential indicators of delirium risk (final correlation requires additional data from other sources).

• General environmental analysis: Monitor temperature, humidity, noise, and other environmental data for smarter building responses in the future (e.g., energy savings through optimized heating) and more effective patient recovery.

• Hand hygiene compliance: Anonymously track hand disinfection compliance to improve hygiene practices in combination with solutions like the Hypros’ Hand Hygiene Monitoring solution – NosoEx.

Instead of stockpiling sensor data, their system uses advanced AI models to interpret and connect data from multiple streams — turning simple raw readings into practical insights that guide better decisions. Real-time alerts also bring timely attention to critical situations — ensuring patients receive the swift and focused care they deserve, and staff can perform at their very best.

The path forward with patient care

Already, Hypros’ patient monitoring system is gaining momentum, with real-world trials at leading institutions like UKSH (University Hospital Schleswig-Holstein) in Germany. As highlighted by their recent press release, the UKSH recognizes the potential of their solutions to transform patient care and improve operational efficiency. In addition, their clinical partner, the University Medical Center Greifswald, has experienced benefits firsthand as an early adopter.

Dr. Robert Fleishmann, a managing senior physician and deputy medical director at the University Medical Center Greifswald, is convinced of its usefulness, saying:

“The prevention of delirium is crucial for patient safety. The Hypros patient monitoring solution provides us with vital data to examine risk factors (e.g., light intensity, noise levels, patient movements) contributing to the development of delirium on a 24/7 basis. We are very excited about this innovative partnership.”

This positive feedback, alongside the voices of other customers, fuels Hypros’ ongoing commitment to revolutionize patient care through ethical and data-driven technology.

By harnessing the power of AI and cloud computing, in close collaboration with Google Cloud, Hypros is dedicated to developing privacy-preserving patient monitoring solutions that directly address critical healthcare challenges such as staffing shortages and the ever-increasing need for enhanced patient safety.

Building on this foundation, Hypros envisions a future where their AI-powered patient monitoring solutions are seamlessly integrated into healthcare systems worldwide. The goal is to empower clinicians with real-time, actionable insights, ultimately improving patient outcomes, optimizing resource allocation, and fostering a more sustainable and patient-centric healthcare ecosystem for all.

Recently, we announced Gemini 2.5 is generally available on Vertex AI. As part of this update, tuning capabilities have extended beyond text outputs – now, you can tune image, audio, and video outputs on Vertex AI. 

Supervised fine tuning is a powerful technique to customize LLM output using your own data. Through tuning, LLMs become specialized in your business context and task by learning from the tuning examples, therefore achieving higher quality output. With video outputs, here’s some use cases our customers have unlocked: 

• Automated video summarization: Tuning LLMs to generate concise and coherent summaries of long videos, capturing the main themes, events, and narratives. This is useful for content discovery, archiving, and quick reviews.

• Detailed event recognition and localization: Fine-tuning allows LLMs to identify and pinpoint specific actions, events, or objects within a video timeline with greater accuracy. For example, identifying all instances of a particular product in a marketing video or a specific action in sports footage.

• Content moderation: Specialized tuning can improve an LLM’s ability to detect sensitive, inappropriate, or policy-violating content within videos, going beyond simple object detection to understand context and nuance.

• Video captioning and subtitling: While already a common application, tuning can improve the accuracy, fluency, and context-awareness of automatically generated captions and subtitles, including descriptions of nonverbal cues.

Today, we will share actionable best practices for conducting truly effective tuning experiments using the Vertex AI tuning service. In this blog, we will cover the following steps:

1. Craft your prompt

2. Detect multiple labels 

3. Conduct single-label video task analysis 

4. Prepare video tuning dataset

5. Set the hyperparameters for tuning

6. Evaluate the tuned checkpoint on the video tasks

I. Craft your prompt

Designing the right prompt is a cornerstone of any effective tuning, directly influencing model behavior and output quality. An effective prompt for video tuning typically comprises several key components, ensuring clarity in the prompt.

• Task context: This component sets the overall context and defines the intention of the task. It should clearly articulate the primary objective of the video analysis. For example….

• Task definition: This component provides specific, detailed guidance on how the model should perform the task including label definitions for tasks such as classification or  temporal localization. For example, in video classification, clearly define positive and negative matches within your prompt to ensure accurate model guidance. 

• Output specification: This component provides how the model is expected to produce its output. This includes specific rules or schema for structured formats such as JSON. To maximize clarity, embed a sample JSON object directly in your prompt, specifying its expected structure, schema, data types, and any formatting conventions. 

II: Detect multiple labels 

Multi-label video analysis involves detecting multiple labels corresponding to a single video. This is a desirable setup for video tasks since the user can train a single model for several labels and obtain predictions for all the labels via a single query request to the tuned model during inference time. These tasks are usually quite challenging for the off-the-shelf models and often need tuning. 

See an example prompt below.

Challenges and mitigations for multi-label video tasks:

• • The tuned model tends to learn dominant labels (i.e., labels that appear more frequently in the dataset).

  • Mitigation: We recommend balancing the target label distribution as much as possible.

• When working with video data, skewed label distributions are further complicated by the temporal aspect. For instance, in action localization, a video segment might not contain “event X” but instead feature “event Y” or simply be background footage.

  • Mitigation: For such use cases, we recommend using multi-class single-label design described below.

  • Mitigation: Improving the positive:negative instance ratio per label would further improve the tuned model’s performance.

• The tuned model tends to hallucinate if the video task involves a large number of labels per instance (typically >10 labels per video input).

  • Mitigation: For effective tuning, we recommend using multi-label formulation for video tasks that involve less than 10 labels per video.

• For video tasks that require temporal understanding in dynamic scenes (e.g. event detection, action localization), the tuned model may not be effective for multiple temporal labels that are overlapping or are very close.

III: Conduct single-label video task analysis 

Multi-class single-label analysis involves video tasks where a single video is assigned exactly one label from a predefined set of mutually exclusive labels.  In contrast to multi-label tuning, multi-class single-label tuning recipes show good scalability with an increasing number of distinct labels. This makes the multi-class single-label formulation a viable and robust option for complex tasks. For example, tasks that involve categorizing videos into one of many possible exclusive categories or detecting several overlapping temporal events in the video.

In such a case, the prompt must explicitly state that only one label from a defined set is applicable to the video input.  List all possible labels within the prompt to provide the model with the complete set of options. It is also important to clarify how a model should handle negative instances, i.e., when none of the labels occur in the video.

See an example prompt below:

Challenges and mitigations for multi-class single-label video tasks

• Using highly skewed data distributions may cause quality regression on the tuned model. The model may simply learn to predict the majority class, failing to identify the rare positive instances.

• Mitigation: Undersampling the negative instances or oversampling the positive instances to balance the distributions are some effective strategies for tuning recipes. The undersampling/oversampling rate depends on the specific use case at hand

Some video use cases can be formulated as both multi-class single-label tasks and multi-label tasks. For example, detecting time intervals for several events in a video.

• For fewer event types with non-overlapping time intervals (typically fewer than 10 labels per video), multi-label formulation is a good option. 

• On the other hand, for several similar event types with dense time intervals, multi-class single-label recipes yield better model performance . Model inference involves sending a separate query for each class (e.g., “Is event A present?”, then “Is event B present?”).  This approach effectively treats the multi-class problem as a series of N binary decisions. This would mean for N classes, you will need to send N inference requests to the tuned models.

This is a tradeoff between higher inference latency and cost vs target performance. The choice should be made based on expected target performance from the model for the use case.

IV. Prepare video tuning dataset

The Vertex Tuning API uses *.jsonl files for both training and validation datasets. Validation data is used to select a checkpoint from the tuning process. Ideally, there should be no overlap in the JSON objects contained within train.jsonl and validation.jsonl. Learn more about how to prepare tuning dataset and its limitations here. 

For maximum efficiency when tuning Gemini 2.0 (and newer) models on video, we recommend to use the MEDIA_RESOLUTION_LOW setting, located within the generationConfig object for each video in your input file. It dictates the number of tokens used to represent each frame, directly impacting training speed and cost.

You have two options:

• MEDIA_RESOLUTION_LOW (default): Encodes each frame using 64 tokens.

• MEDIA_RESOLUTION_MEDIUM: Encodes each frame using 256 tokens.

While MEDIA_RESOLUTION_MEDIUM may offer slightly better performance on tasks that rely on subtle visual cues, it comes with a significant trade-off: training is approximately four times slower. Given that the lower-resolution setting provides comparable performance for most applications, sticking with the default MEDIA_RESOLUTION_LOW is the most effective strategy for balancing performance with crucial gains in training speed.

V. Set the hyperparameters for tuning

After preparing your tuning dataset, you are ready to submit your first video tuning job! We supports 3 hyperparameters:

• epochs: specifies the number of iterations over the entire training dataset. With a dataset size of ~500 examples, starting with epochs = 5 is the default value for video tuning tasks. Increase the number of epochs when you have <500 samples and decrease when you have >500 samples.

• learning_rate_multiplier: specifies multiplier for the learning rate. We recommended experimenting with values less than 1 if the model is overfitting and values greater than 1 if the model is underfitting.

• adapter_size: specified the rank of the LoRA adapter. The default values are adapter_size=8 for flash model tuning. For most use cases, you won’t need to adjust this, but a higher size allows the model to learn more complex tasks.

To streamline your tuning process, Vertex AI provides intelligent, automatic hyperparameter defaults. These values are carefully selected based on the specific characteristics of your dataset, including its size, modality, and context length. For the most direct path to a quality model, we recommend starting your experiments with these pre-configured values. Advanced users looking to further optimize performance can then treat these defaults as a strong baseline, systematically adjusting them based on the evaluation metrics from their completed tuning jobs.

VI. Evaluate the tuned checkpoint on the video tasks

Vertex AI tuning service provides loss and accuracy graph for training and validation dataset out of the box. The monitoring graph is updated in real time as your tuning job progresses. Intermediate checkpoints are automatically deployed for you. We recommend selecting the checkpoint corresponding to the epochs that show loss values on the validation dataset have saturated.

To evaluate the tuned model endpoint, See a sample code snippet below:

For best performance, it is critical that the format, context and distribution of the inference prompts align with the tuning dataset. Also, we recommend using  the same mediaResolution for evaluation as the one used during training.

For thinking models like Gemini 2.5 Flash, we recommend setting the thinking budget to 0 to turn off thinking on tuned tasks for optimal performance and cost efficiency. During supervised fine-tuning, the model learns to mimic the ground truth in the tuning dataset, omitting the thinking process. 

Get started on Vertex AI today

The ability to derive deep, contextual understanding from video is no longer a futuristic concept—it’s a present-day reality. By applying the best practices we’ve discussed for prompt engineering, tuning dataset design, and leveraging the intelligent defaults in Vertex AI, you are now equipped to effectively tune Gemini models for your specific video-based tasks.

What challenges will you solve? What novel user experiences will you create? The tools are ready and waiting. We can’t wait to see what you build. 

• Documentation

• Sample notebooks

At Google Cloud, we’re committed to delivering the best performance possible globally for web and API content. Cloud CDN is a high-performance edge caching solution that runs at over 200 points of presence, and we continue to add more features and capabilities to it. Recently we launched invalidation with cache tags, device characterization, 0-RTT early data, and geo-targeting. These powerful first class features address many use cases, but organizations tell us they also need a more flexible, lightweight, edge computing solution.  

We are excited to announce that you can now run Service Extensions plugins with Cloud CDN, allowing you to run your own custom code directly in the request path in a fully managed Google environment with optimal latency. This allows you to customize the behavior of Cloud CDN and the Application Load Balancer to meet your business requirements. 

Service Extensions plugins with Cloud CDN supports the following use cases:

• Custom traffic steering: Manipulate request headers to influence backend service selection.

• Cache optimization: Influence which content is served from a Cloud CDN cache.

• Exception handling: Redirect clients to a custom error page for certain response classes.

• Custom logging: Log user-defined headers or custom data into Cloud Logging.

• Header addition: Create new headers relevant for your applications or specific customers.

• Header manipulation: Rewrite existing request headers or override client headers on their way to the backend.

• Security: Write custom security policies based on client requests and make enforcement decisions within your plugin.

Where you can run your code

Service Extensions plugins run at multiple locations in the request and response processing path. With this launch, you can run plugins before requests to Cloud CDN using an edge extension. In a previous launch, we added the capability to run plugins post the Cloud CDN cache, closer to the origin, via a traffic extension. Now, with support for both edge and traffic extensions, you can choose where you want your code to execute in the processing path.

Service Extensions deep dive

Service Extensions plugins are designed for lightweight compute operations that run as part of the Application Load Balancer request path. Plugins are built on WebAssembly (Wasm), which provides several benefits:

1. Near-native execution speed, and startup time in the single milliseconds

2. Support for a variety of programming languages, such as Rust, C++, and recently Go 

3. Cross-platform portability, so you can run the same plugin in various deployments, or locally for testing

4. Security protections, such as executing plugin logic in a sandboxed environment

Service Extensions plugins leverage Proxy-Wasm, a Google-supported open source project that provides a standard API for Wasm modules to interface with network proxies.

Use Cloudinary’s image & video optimization solution

We are excited to announce our latest partner to integrate their offering with Service Extensions and Cloud CDN. Cloudinary makes an advanced image and video optimization solution and has integrated it with Service Extensions plugins for deployment to Cloud CDN customers. 

Packaged as a Wasm plugin, Cloudinary’s plugin takes directives from Client Requests such as User-Agent information, and content type expressed as MIME types from HTTP Accept headers, to determine the most optimal media type to serve to the end user. The plugin also takes care of Cache Key normalization so that the images and videos are cached properly based on device types and content types. 

“Cloudinary’s image and video solutions help customers manage and optimize their visual media assets at scale while ensuring they are optimized for the best format, device, channel and viewing context. We are excited to partner with the Google team to offer Cloudinary’s image and video optimization solutions to Cloud CDN customers via Service Extensions.”  – Gary Ballabio, VP, Strategic Technology Partnerships, Cloudinary

For more information on Cloudinary’s solution, please review this guide. 

What’s next

To get started with Service Extensions plugins, take a look at our growing samples repository with a local testing toolkit and follow our quickstart guide in the documentation.

With more than a thousand connected data sources available out-of-the-box and an untold number of custom tools, developers rely on Looker’s cloud-first, open-source-friendly model to create new data interpretations and experiences. Today, we are taking a page from modern software engineering principles with our launch of Continuous Integration for Looker, which will help speed up development and help developers take Looker to new places.

As a developer, you rely on your connections to be stable, your data to be true, and for your code to run the same way every time. And when it doesn’t, you don’t want to spend a long time figuring out why the build broke, or hear from users who can’t access their own tools. 

Continuous Integration for Looker helps streamline your code development workflows, boost the end-user experience, and give you the confidence you need to deploy changes faster. With Continuous Integration, when you write LookML code, your dashboards remain intact and your Looker content is protected from database changes. This helps to catch data inconsistencies before your users do, and provides access to powerful development validation capabilities directly in your Looker environment.

With Continuous Integration, you can automatically unify changes to data pipelines, models, reports, and dashboards, so that your business intelligence (BI) assets are consistently accurate and reliable.

Developers benefit from tools that help them maintain code quality, ensure reliability, and manage content effectively. As Looker becomes broadly adopted in an organization, with more users creating new dashboards and reports and connecting Looker to an increasing number of data sources, the potential for data and content errors can increase. Continuous Integration proactively tests new code before it is pushed to production, helping to ensure a strong user experience and success.

Specifically, Continuous Integration in Looker offers:

• Early error detection and improved data quality: Minimize unexpected errors in production. Looker’s new Continuous Integration features help LookML developers catch issues before new code changes are deployed, for higher data quality.

• Validators that:

• Flag upstream SQL changes that may break Looker dimension and measure definitions.

• Identify dashboards and Looks that reference outdated LookML definitions.

• Validate LookML for errors and antipatterns as a part of other validations.

Manage Continuous Integration directly within Looker

Looker now lets you manage your continuous integration test suites, runs, and admin configurations within a single, integrated UI. With it, you can

• Easily monitor the status of your Continuous Integration runs and manage your test suites directly in Looker.

• Leverage powerful validators to ensure accuracy and efficiency of your SQL queries, LookML code, and content.

• Trigger Continuous Integration runs manually or automatically via pull requests or schedules whenever you need them, for control over your testing process.

In today’s fast-paced data environment, speed, accuracy and trust are crucial. Continuous Integration in Looker helps your data team promote developmental best practices, reduce risk of introducing errors in production, and increase your organization’s confidence in its data. The result is a consistently dependable Looker experience for all users, including those in line-of-business, increasing reliability across all use cases. Continuous Integration in Looker is now available in preview. Explore its capabilities and see how it can transform your Looker development workflows. For more information, check our product documentation to learn how to enable and configure Continuous Integration for your projects.