EVA v3.1 focuses on making EVA easier to access for users operating multiple EVA servers and large numbers of cameras, while helping administrators manage accounts and permissions more efficiently.

This release introduces unified authentication and SSO, which lets users access Apps across multiple EVA servers with one login; Knowledge-based EVA Chat, which can answer questions using manuals and customer documents; and camera groups, which organize cameras by work area and purpose.

This release includes the following major updates:

• Unified authentication and SSO for accessing multiple EVA servers with one login
• Knowledge-based EVA Chat grounded in EVA manuals and customer documents
• Camera groups for organizing cameras by work area, location, and purpose
• M2M authentication for secure API access from external systems

Unified Authentication and SSO Across Multiple EVA Servers​

A single EVA server can connect approximately 100 cameras. As operations grow and multiple EVA servers need to be managed, users previously had to log in to each server repeatedly, while administrators had to configure accounts and permissions separately on every server.

As the number of servers increases, so does the work of creating the same users repeatedly and managing password policies and permissions independently. A permission change or account deactivation on one server could also leave the previous state in existing sessions on other servers.

EVA v3.1 applies unified authentication and SSO through a central authentication server.

Log in once through the App on EVA Server A
  → Central authentication completed
  → Access the App on EVA Server B
  → Continue without another login

After the initial login, users can access every EVA server for which they have permission without entering another ID or password. Administrators can manage users and server-specific access permissions from a central account screen instead of creating users individually on every server.

Whether there are two EVA servers or dozens, users no longer need to log in to each server separately, and administrators can apply the same account and security policies from one place.

Security policies are applied consistently​

Account deletion, deactivation, and permission changes are now reflected immediately in existing sessions across multiple servers. Administrators do not need to configure the user again on every server or log the user out manually.

M2M authentication for external integrations​

EVA APIs can be called not only by browser-based users, but also by external systems such as EVA Mentor and EVA Scope.

Because external systems do not log in as a user, EVA applies M2M authentication using a Client ID and Client Secret instead of a user account.

External system
  → Request an Access Token with Client ID + Client Secret
  → Call EVA App APIs within the permitted scope
  → EVA Backend validates the token and API permissions

The API areas and Read/Write permissions required by each external system can be limited, so a general user account does not need to be shared for integrations.

What changes for users and administrators?​

• No repeated login is required when using multiple EVA servers.
• Users and access permissions can be managed centrally instead of being created separately on every server.
• Permission changes and account deactivation are reflected immediately in existing sessions.
• Administrators can control concurrent logins and log out across all servers.
• External systems use limited M2M permissions instead of user accounts to access EVA APIs.

Knowledge-Based Chat Using EVA Manuals and Customer Documents​

When operating EVA, users often need to check manuals for questions about detection intervals, scenario configuration, and how to use features. Previously, answers were mainly generated by placing content for each question type in the Chat prompt in advance.

In EVA v3.1, Chat searches Knowledge for documents related to the question and generates an answer grounded in the retrieved content.

User question
  → Search for related documents
  → Build the relevant pages into the answer context
  → Generate an answer grounded in the documents

💡 For technical details on the tool-calling architecture and Knowledge retrieval flow behind Knowledge-based Chat, see the Tech Blog.
→ Tech Blog | From Router-Based Agents to Tool-Calling Agents

This allows EVA to do more than generate a general answer: it can hold a conversation based on the features and usage instructions defined in the EVA manuals.

Customer-specific documents can also be added​

In addition to the standard EVA manuals, customers can add the documents they need for their operations to Knowledge.

For example, the following documents can be used together:

• Customer-specific operating manuals
• Site-specific equipment or process guides
• Internal safety regulations and work procedures
• Scenario operation guides created during EVA deployment
• Inspection and response documents used only at a specific server or site

Added documents go through the Ingest process and are managed as searchable Knowledge. When a user asks a question, Chat finds related documents and uses them as the basis for its answer.

“When an alarm for a worker not wearing a safety helmet occurs in our process, what should we check first?”

If the customer’s operating guide contains the relevant procedure, EVA Chat can answer based on that site-specific procedure instead of providing only a general explanation.

How document-based answers work​

Questions that require current system state use Runtime information, while questions about features or operating procedures search the relevant Knowledge documents.

What changes for users?​

• Customer and site-specific documents can be added to use organizational knowledge.
• Answers grounded in relevant document content can be distinguished from general answers.
• Users can check current settings, feature explanations, and site operating procedures in one conversation.

Camera Groups That Show Only the Cameras You Need​

Previously, every user saw the same camera list. As the number of cameras grew, it became harder to find the right camera and more difficult to limit access based on each user.

EVA v3.1 lets administrators group cameras and assign only the groups each user needs.

For example, cameras can be organized into groups such as:

• Plant A
• 2FCC process
• Safety helmet detection
• First-floor entrance

A camera can belong to multiple groups at the same time. This makes it possible to combine process, location, and business-purpose criteria instead of classifying each camera in only one way.

How to use camera groups​

1. Enter a group name and description.
2. Add cameras to the group.
3. Assign the users who should be able to view the group.
4. Modify the groups assigned to existing cameras when needed.
5. Change the display order based on importance as the number of groups grows.

📷 Camera group settings

When adding cameras to a group, users can select the required cameras from the registered camera list.

📷 Adding cameras to a group

Permissions by user type​

If a Manager does not belong to any group, cameras can still be registered without a group. Cameras not connected to a group remain visible to users who need to access them, as before.

What changes for users?​

• Users can quickly check the cameras assigned to them.
• The right camera is easier to find even in environments with many cameras.
• Cameras can be organized around processes, locations, and operational purposes.
• Separating access by user improves security.
• Changing the group order also changes the order shown in the camera list and related settings screens.

A Suggested EVA v3.1 Workflow​

The features in this release can be used together in the following workflow:

1. Log in with SSO: Log in once and access the EVA servers you are authorized to use.
2. Configure camera groups: An administrator creates groups by process or location and assigns the responsible users.
3. Check the required cameras: Users view only the cameras they are authorized to access.
4. Add Knowledge documents: The customer’s manuals and site operating documents are registered in EVA Knowledge.
5. Use EVA Chat: Users ask questions about current settings, feature usage, and site response procedures based on the documents.

For example, an administrator can group cameras for the 2FCC process across multiple EVA servers and make them visible only to the responsible staff. After logging in once with SSO, a staff member can check the required cameras without logging in to each server and ask EVA Chat, “When a fire alarm occurs, what should I check first according to our site procedure?”

Closing: Less Repetition, More Site Knowledge​

EVA v3.1 focuses on reducing the repeated work involved in operating multiple EVA servers and many cameras: logging in, managing accounts and permissions, finding cameras, and checking manuals.

• SSO connects login and account/permission management across multiple EVA servers.
• Knowledge-based Chat uses EVA manuals and customer documents as the basis for conversation.
• Camera groups show users only the cameras they need.
• M2M authentication provides external systems with only the API permissions they require.

As a result, EVA is evolving into a platform that is easier to access, able to use organizational knowledge, and adaptable to each user’s work.

EVA will continue expanding its Knowledge-based capabilities so that customer documents and operating practices can be used more effectively within the product.

This release is not just about adding new features. It focuses on making EVA easier to adopt, easier to configure, and more efficient to operate at scale.

Key Updates​

• Detection Modes & Advanced Settings to reduce configuration complexity
• Scenario Templates for reusing validated detection scenarios
• Multi-Scenario Architecture supporting up to four scenarios per camera
• Bulk Camera Registration for large-scale deployments

Detection Modes & Advanced Settings: Easier Configuration, Smarter Detection​

Achieving reliable detection results requires selecting the right detection strategy for each scenario.

Previously, users needed to understand and manually configure settings such as VM, VM + VLM, and Frame Mode. For first-time users, it was often difficult to determine which options were most appropriate for a given use case.

EVA v3.0 significantly simplifies this process.

When a user describes a scenario, the EVA Agent analyzes the request, selects the most suitable detection mode, and automatically configures the required settings.

Depending on the characteristics of the scenario, EVA applies one of the following detection modes:

For example, a scenario such as "Detect workers not wearing safety helmets" will automatically use PPE Mode, while a scenario such as "Detect fire or smoke incidents" will use Thinking Mode.

This allows users to benefit from the most appropriate detection strategy without needing in-depth knowledge of EVA's underlying detection architecture.

Advanced options have also been moved into a dedicated Advanced Configuration section.

General users can quickly deploy scenarios using EVA's recommended settings, while experienced users can access advanced controls whenever fine-tuning is required.

📷 Automatic Detection Mode Selection and Configuration by EVA Agent

For a deeper technical explanation of how detection modes work, please refer to the following technical articles:

• Thinking Mode: Reasoning-Based Risk Detection
• PPE Mode: Personal Protective Equipment Detection

What’s Improved​

• New users can configure scenarios without understanding every advanced option.
• Detection modes are automatically selected based on scenario characteristics, reducing configuration effort.
• Advanced settings are separated into a dedicated section, making the primary workflow more intuitive.
• Experienced users can still fine-tune detection behavior when necessary.

Scenario Templates: Create Once, Reuse Across Multiple Cameras​

One of EVA's greatest strengths is the flexibility to create detection scenarios using natural language.

However, when managing multiple cameras, users often find themselves creating the same or very similar scenarios repeatedly. Common use cases such as helmet violation detection, worker fall detection, and fire or smoke detection are frequently applied across multiple cameras.

Previously, users had to manually recreate or copy these scenarios for each camera.

EVA v3.0 introduces Scenario Templates, allowing users to save and reuse validated scenarios across their deployment.

Once a scenario has been tested and verified in operation, it can be saved as a template and quickly applied to additional cameras without requiring manual reconfiguration.

📷 Selecting and Applying a Scenario Template

What’s Improved​

• Reduce setup time by eliminating the need to recreate identical scenarios across multiple cameras.
• Maintain consistent configurations across cameras by reusing validated scenarios.
• Help new users deploy EVA more easily by leveraging existing templates.
• Minimize configuration errors caused by repetitive manual input.

Multi-Scenario Architecture: Independently Manage Multiple Situations on a Single Camera​

In real-world environments, a single camera rarely monitors just one type of event.

For example, a production-line camera may need to monitor fire incidents, worker falls, restricted-area intrusions, and other safety-related situations simultaneously.

Previously, EVA handled multiple detection requirements within a single scenario. As detection requirements increased, scenarios became more complex and more difficult to maintain.

To address this limitation, EVA v3.0 introduces a Multi-Scenario Architecture, allowing up to four independent scenarios per camera.

Users can now create, manage, and configure multiple detection scenarios independently. Each scenario can have its own detection targets, settings, and operational lifecycle.

Specific scenarios can also be modified, disabled, or updated without affecting others.

📷 Multi-Scenario Creation and Management per Camera

Webhook integration has also been enhanced.

Previously, all detection events generated by a camera were delivered through the same notification channel. With EVA v3.0, users can configure notifications on a per-scenario basis, allowing external systems to receive only the events that matter.

What’s Improved​

• Manage multiple detection objectives more effectively on a single camera.
• Update or maintain individual scenarios without impacting others.
• Improve operational visibility by separating complex requirements into dedicated scenarios.
• Increase integration efficiency by selectively forwarding only relevant detection events.

Bulk Camera Registration: Less Repetitive Work, Faster Deployment​

Registering cameras is often one of the most time-consuming tasks when deploying EVA.

In environments with dozens or even hundreds of cameras, administrators must repeatedly register cameras, enter RTSP information, and apply detection scenarios.

As deployments grow, repetitive configuration increases the risk of input errors, missing settings, and inconsistent configurations. For large-scale projects spanning multiple production lines or sites, camera onboarding can become a significant deployment bottleneck.

EVA v3.0 introduces Bulk Camera Registration to streamline this process.

Administrators simply fill out the provided Excel template with the following information:

After uploading the completed Excel file, EVA automatically registers cameras and applies the specified scenario templates.

In addition, if registration fails, EVA provides detailed error information for each failed camera. Issues such as invalid RTSP addresses, missing required fields, or non-existent scenario templates can be identified immediately, allowing administrators to resolve problems quickly.

📷 Camera Registration Results and Failure Analysis

What’s Improved​

• Register multiple cameras simultaneously to significantly reduce deployment time.
• Eliminate repetitive configuration tasks and reduce administrative effort.
• Apply standardized scenario templates across multiple cameras for greater consistency.
• Quickly identify failed registrations and their root causes to accelerate troubleshooting.

Closing Thoughts: Less Setup, More Deployment​

The true value of AI-powered video analytics is not only in detection performance, but also in how easily and reliably it can be operated in real-world environments.

EVA v3.0 focuses on reducing repetitive tasks and improving operational efficiency through Scenario Templates, Multi-Scenario Architecture, Detection Mode Automation, and Bulk Camera Registration.

Configuration is now simpler, operations are more structured, and scaling across large deployments is easier than ever.

EVA will continue to evolve not only through advances in AI technology, but also by improving the day-to-day experience of the people who operate it.

🚀 Coming Soon: Preview of v3.1​

• Camera Group Management
• Single Sign-On (SSO) Integration

In close collaboration with Rebellions, the EVA team has continuously advanced the technology stack and successfully built a production-grade NPU-based runtime environment for EVA. We are now moving beyond technical validation and officially entering the phase of commercial service deployment.

1. ATOM-MAX NPU Performance Validation: A New Standard for VLM Inference (As-Is)​

EVA recently evaluated operational feasibility with the Qwen3 VL 8B model on Rebellions' latest ATOM-MAX NPU environment. This was not just a benchmark for model accuracy, but a validation of key operational requirements for real industrial services.

• Rebellions ATOM / Qwen3 VL 8B / Accuracy 0.7996 / F1 0.6733
• GPU A100 / Qwen3 VL 8B FP8 / Accuracy 0.7779 / F1 0.5979

Compared with GPU (A100), EVA achieved equivalent or better performance on overall inference metrics. In particular, in fire and smoke detection scenarios, the NPU environment demonstrated stronger processing capability, proving applicability to high-complexity industrial safety monitoring.

2. Optimization and Stability for Commercial Operations (As-Is)​

In real-world deployments, AI systems must handle far more than clean benchmark inputs. Mixed text-image requests and multiple simultaneous camera streams can easily create bottlenecks. To address this, EVA has continuously improved optimization at both the NPU compiler and system levels.

It is critical to build a resource orchestration framework that efficiently distributes CPU, memory, and NPU workloads, so multiple AI Agents can run concurrently without performance degradation. It is equally important to resolve unexpected failures and ensure stable, uninterrupted operation when text-only and image-analysis requests arrive at the same time.

• Complex data processing stabilization: We fully resolved potential malfunctions in multi-core environments where Text Only and Text + Image requests are mixed, significantly improving operational reliability.
• Resource efficiency optimization: By precisely controlling data processing policies across CPU, memory, and NPU, we achieved a high-efficiency runtime where multiple VLM instances can run simultaneously without inference speed degradation.

3. Throughput Optimization Based on Parallel Architecture (To-Be)​

EVA is also pushing forward full-stack parallelization to maximize the multi-core architecture of Rebellions NPU and further advance end-to-end technology integration.

• Parallelization strategy: We are developing techniques to remove VLM inference bottlenecks by applying data parallelism (DP) to the Vision Encoder and tensor parallelism (TP) to the Text Decoder.
• Integrated operations strategy: We are defining the optimal number of concurrent instances and core allocation ratios across multiple NPU resources. This enables GPU-level throughput while significantly improving performance-per-watt and reducing TCO (Total Cost of Ownership).

Closing: The Commercial Era of Efficient Industrial AI​

The combination of EVA and Rebellions NPU is not a simple hardware replacement. It represents a full-stack transformation toward always-on AI inference in the field with predictable operations and a strong balance of high performance, high efficiency, and high stability. Based on validated NPU optimization technologies, EVA will accelerate digital transformation in industrial environments with a more cost-efficient operating model.

Related Reading​

• EVA on NPU Technology Roadmap
• EVA X Rebellions Technology Collaboration

When introducing Vision AI to the field, the focus often falls solely on detection performance—how accurately it can find things.
However, once you move into real-world operations, a fundamental truth becomes clear: "Operational continuity is just as important as detection performance."
Detection scenarios constantly change, the number of cameras grows, and light and shadows shift from moment to moment.
No matter how sharp the vision is, if configuration is complex and the system is fragile to environmental changes, earning trust in the field is difficult.
EVA v2.7 began with a clear goal: to reduce operational friction in real-world environments to zero.

• Model selection fatigue: The operational burden of having to find and compare the optimal model whenever a scenario changes
• Lighting uncertainty: Instability caused by brightness changes due to time of day and weather, leading to degraded detection performance
• Limits of detection area setup: Simple configuration methods that fail to reflect complex real-world structures such as pillars, walls, and corridors
• Fragmented management: Scattered information across individual cameras that hinders intuitive understanding and rapid response

This update goes beyond adding features. Guided by the principle of "Simpler setup, more precise detection", EVA v2.7 lays a solid foundation to elevate operational quality in the field.
Experience the evolution of EVA v2.7, where complexity is hidden behind the technology and only clarity is delivered.

“Which model is best?”—Now EVA decides for you​

Automatic Vision Model (VM) Recommendation Based on Detection Scenarios​

One of the most frustrating moments in operating Vision AI is standing in front of a long list of AI models, unsure which one to choose.
Questions like “Is Model A better for fall detection, or is Model B more accurate?” or “Which model responds more sensitively to nighttime fire detection?” create psychological pressure and consume valuable time.
EVA v2.7 completely removes this technical barrier. Once the operator defines a detection scenario, EVA automatically recommends the Vision Model (VM) optimized for that scenario.

• Expert-level results without expertise: You don’t need to know the detailed characteristics of each model. Simply selecting a scenario instantly recommends the best model combination for the site.
• Consistently high detection quality: Prevents detection performance from varying based on operator experience, ensuring the system consistently delivers optimal performance in any environment.
• Dramatically reduced setup time: By eliminating the need to test and compare multiple models, the workflow for building new scenarios and deploying them on-site becomes significantly faster.

While EVA’s internal capabilities continue to grow more advanced and complex, the interface users encounter is becoming even simpler. EVA absorbs the technical complexity so users can focus solely on what matters most: safety and operations.

Drawing Real-World Detail with Lines and Surfaces​

Precise Area Configuration with Polygon-Based Detection Zones​

Real-world sites never behave like neat rectangular diagrams. Thick pillars block the view, corridors twist and turn, and certain areas take on irregular shapes due to machinery and equipment.
Traditional rectangle-based configuration was easy to set up, but it was always slightly insufficient for fully capturing complex real-world environments.
To overcome these physical limitations, EVA v2.7 introduces polygon-based free-form area configuration.
Now, instead of forcing spaces to fit the system, the system flexibly adapts to the actual shape of the space.

• Seamless handling of complex structures: Precisely draw only the truly relevant detection areas by freely connecting points while avoiding obstacles such as pillars, walls, and storage units.
• Fundamental reduction of false positives: By perfectly filtering unnecessary movements near boundaries or interference from adjacent zones at the software level, alert reliability is significantly improved.

EVA is evolving not by simplifying and distorting real-world spaces, but by acknowledging and faithfully reflecting their three-dimensional complexity. This goes beyond convenience—it becomes a key indicator of how accurately Vision AI understands the real world.

A Steady Gaze Under Any Light​

Screen Brightness Adjustment for Lighting Optimization​

Environmental conditions in the field are never static—harsh midday sunlight, suddenly dark scenes during heavy rain, or insufficient lighting at night. For Vision AI, these lighting changes are among the most challenging factors affecting detection accuracy.
EVA v2.7 introduces a new brightness optimization feature that allows operators to immediately control these uncertainties.
Without modifying the video source itself or making complex camera setting changes, all lighting optimization is handled directly within EVA’s screen brightness settings.

• Intuitive slider control: Adjust brightness precisely using a slider ranging from -50 to +50. Reduce brightness when objects appear washed out, or increase it when shapes are unclear due to darkness.
• Instant real-time application: Changes are applied immediately without rebooting or reconnecting streams. Operators can find the optimal “golden brightness” in real time.
• Maximum environmental adaptability: Even cameras in poorly lit blind spots or areas with drastic lighting changes throughout the day can now maintain stable, 24/7 detection quality through software-based correction alone.

Light may change, but EVA’s detection performance should not. With this update, experience a robust vision that remains steady under even the harshest lighting conditions.

From Detection to Action​

On-Site Automation Through Expanded Workflow Builder Webhook Channels​

The true completion of field operations is not answering “What was detected?” but “So what action should be taken?”
If Vision AI once stopped at identifying and notifying critical situations, it must now extend into automating the response that follows.

EVA v2.7 significantly expands Webhook channels for integration with Workflow Builder.
By removing the complex development effort previously required for external system integration, EVA now provides a fast lane where captured Real World Data leads directly to immediate action.

• Integration with intelligent Workflow Builder: Detection data sent by EVA is interpreted and branched in real time within Workflow Builder. For example: “If PPE non-compliance is detected → First, send a messenger alert; second, broadcast a warning.”
• Physical action triggers: Move beyond digital notifications to immediately trigger real-world actions such as alarms, access gate control, or emergency equipment shutdown—securing the critical golden time before human intervention.
• Unlimited scalability: Combine EVA with thousands of apps supported by Workflow Builder—including email, ERP systems, and IoT devices—to design custom response scenarios tailored to your site.

EVA now stands at the center of an integrated response process that flows from [Detection → Workflow Optimization → Immediate Action]. Experience the true value of Physical AI, where data transforms into tangible safety and operational efficiency.

An Optimized Layout That Expands the Operator’s View​

Complete Overhaul of Camera Detail Screen UI/UX​

As the number of cameras to manage increases, even a single unnecessary click or eye movement significantly adds to operator fatigue.
EVA v2.7 reorganizes previously scattered configuration elements according to the operator’s workflow. Now, with "easy configuration and clear information", management becomes intuitive.

• Top-fixed core settings (Action Zone): Frequently adjusted items—camera name, detection scenario, detection targets and areas, alert channels—are now placed prominently at the top of the streaming screen for instant access.
• Unified information layer at the bottom (Information Zone): System operation status, such as the active model and inference cycle, is consistently organized in the lower section, dramatically improving situational awareness across multiple cameras.
• Clean feature organization (More Menu): Less frequently used functions like brightness adjustment or camera deletion are neatly consolidated into the top “more” (···) menu, minimizing visual clutter during everyday operations.

This UI overhaul is more than a visual refresh—it is an update that enhances EVA as a tool designed to accelerate operator response speed.

Closing: “Easy-to-Operate AI” Is the Most Powerful AI​

The true value of Vision AI is not proven by high accuracy in a laboratory, but by its ability to operate reliably every day amid the complexity of real-world sites.
EVA v2.7 builds upon strong detection fundamentals with a solid layer of operational sustainability.
Setup is lighter, operations are more stable, and external integration is more flexible. EVA will continue to evolve as a platform that prioritizes the real challenges faced by operators behind the technology.

🚀Coming Soon: A Preview of v3.0​

• Detection scenario preset features
• Improved multi-scenario input and management structure
• Support for large-scale camera registration

EVA v2.6 is a release that begins with a real operational question: "How should detection results be interpreted, and which alerts should be handled first?" As accurate detection performance has become the baseline, what matters more in the field today is the clarity of operational judgment—questions such as "Is this alert truly critical?" and "Does this situation require immediate action?" This v2.6 update goes beyond what AI sees, focusing instead on how operators understand and utilize detection results.

• Clearer prioritization criteria as the number of alerts increases
• A structure that accumulates detection results as operational metrics, not just isolated incidents
• Detection that understands the flow of a situation, not just a single image
• Selectable detection processes that do not treat all scenarios equally
  

v2.6 represents a step forward for EVA—from a simple detection system to an AI operations platform that supports operator decision-making.

Emergency Alert Settings: Making Critical Alerts Impossible to Miss​

As the number of scenarios increases, so does the volume of alerts. When all alerts are displayed with the same level of importance, operators are once again forced to rely on human judgment to determine priorities. To reduce this burden, v2.6 introduces a feature that allows text-based definition of alert types requiring urgent response. Alerts designated as emergency alerts are clearly distinguished from general alerts, enabling operators to immediately recognize situations that must be checked first—even among a large number of notifications.

As alerts increase, what matters is not the number of alerts, but which alert requires action first. Emergency alert settings in v2.6 make operational judgment criteria clearer and more actionable.

Expanded False/True Detection Feedback: Managing Feedback as Operational Records and Metrics​

Previously, feedback could only be recorded for false detections. In v2.6, feedback can now be entered for true detections as well. Operators can explicitly record whether each detection result is false or true, and this data is accumulated and managed as scenario-level true detection rate metrics. As a result, detection results evolve from simple event logs into quantitative data used to evaluate and improve operational quality.
In addition, feedback history functions as an operational record, allowing teams to trace which alerts were actually reviewed and what decisions and responses were made. UI improvements also ensure that operators can immediately see whether feedback has been entered directly from the alert list in the chat window—without navigating to a detail page.

Main Screen Improvements: Only the Information Operators Truly Need, Presented More Intuitively​

The main screen is where operators spend most of their time. In v2.6, the list structure has been reorganized based on actual operational workflows. Information with low immediate decision-making value—such as model names or detection targets—has been removed. Instead, columns have been restructured around operation-focused information, including alert severity, recent alert summaries, scenario summaries, and webhook configuration status. This enables operators to grasp what is happening right now and what actions are required at a glance, allowing for faster and more confident responses.

Multi-Image-Based Detection: Understanding Situations as a Flow, Not a Single Image​

Most real-world situations do not occur in a static moment, but within a sequence of continuous changes. Traditional single-image-based detection evaluates only a single frame, making it difficult to accurately assess scenarios where context before and after an action is critical.
For example, a person lying on the floor in a gym could be stretching, resting, or experiencing a real medical emergency.
This distinction is difficult to determine without considering preceding and subsequent frames. To address this limitation, v2.6 introduces multi-image-based detection. By analyzing multiple consecutive images together, EVA can comprehensively assess motion flow and state changes. This significantly improves detection accuracy for scenarios where the process of an action—such as intrusion, assault, or collapse—is essential.
EVA is no longer reacting to isolated moments, but evolving toward an approach that understands how situations unfold over time.

💡 For a detailed explanation of the technical design and decision logic behind multi-image-based detection, please refer to our Tech Blog.
→ Tech Blog | Multi-Frame-based VLM Detection: Beyond Single-Image Limitations Toward Temporal Context

VM Only Detection: When Faster Alerts Matter More Than Complex Interpretation​

Not all detections require complex scenario interpretation. In some environments, "the presence of a specific object" alone is immediately meaningful.
Previously, EVA followed a pipeline of Vision Model (VM) → Vision Language Model (VLM), performing scenario interpretation after object detection. While effective for complex judgments, this approach could introduce unnecessary latency for simpler scenarios.
To address this, v2.6 introduces a new VM Only detection process. Alerts are triggered immediately upon object detection, bypassing the VLM stage and thereby improving both detection speed and resource efficiency.
For example, in scenarios such as "Notify me when an ambulance appears," faster responses are possible through object detection alone, without complex interpretation. Operators can now choose detection methods based on scenario characteristics—distinguishing between cases where accurate interpretation is critical and those where rapid response is the priority.

EVA is not simply a system that generates alerts.
It aims to be an AI operations platform where operator judgment and experience are continuously accumulated.
v2.6 most clearly represents this direction.
Beyond improving detection accuracy, it enhances operational judgment flows, prioritization, records, and metrics together.
EVA will continue to evolve to better understand complex real-world environments and support operators in making faster, clearer decisions.
Your usage experiences and feedback are the most important foundation for taking EVA to the next level.

🚀 Coming Soon: A Preview of v2.7​

• Scenario-based automatic detection configuration
• Polygon-based detection area settings
• Change history alerts for detection scenarios and targets

EVA Signs Supply Agreement with KOCOM and Golden Seoul Hotel – A New Milestone for Expansion into Construction and Hospitality Markets​

EVA has taken its first meaningful step toward strategic collaboration with KOCOM, a leading smart home solutions provider in Korea. The two companies have signed an EVA license supply agreement and will officially launch a project to apply AI-based video analytics in real-world operational environments.

This agreement goes beyond a simple solution supply contract. It represents a strategic partnership aimed at expanding AI-driven safety management systems across diverse industries.

A Validation-Driven Collaboration Beginning with KOCOM Headquarters and Golden Seoul Hotel​

Under this agreement, EVA will first be deployed at KOCOM headquarters and Golden Seoul Hotel. By leveraging AI video analytics in real operational environments, the system will detect hazardous situations, identify abnormal behaviors, and manage operational risks in real time—raising on-site safety standards to a new level.

Hotels and office facilities accommodate large numbers of people daily, making proactive risk detection and response systems essential. This deployment is expected to serve as a key validation reference, demonstrating EVA’s stability and operational effectiveness in real-world settings.

💡 Expected Impact: Moving beyond simple monitoring, AI will recognize situations and proactively manage risks to create an intelligent safety operation environment.

Securing Strategic References for Expansion into Construction and Hospitality Markets​

KOCOM brings extensive experience and market networks in smart homes, intercom systems, CCTV, and construction-focused security solutions. By combining EVA’s AI analytics technology with KOCOM’s industry expertise, a scalable model for AI-driven safety solutions—centered on construction and hospitality markets—is expected to gain momentum.

This project will go beyond individual deployments and serve as a standard reference model applicable to multiple domains, including construction site safety management, hotel and commercial facility operations, and integrated smart building management.

🏗️ Market Significance: This initiative marks a starting point in establishing the perception that “AI safety is not an option, but infrastructure.”

A Partnership That Grows Beyond Technology​

This collaboration is not a one-time supply agreement but a long-term partnership focused on jointly developing the market.

EVA is a proven Physical AI solution across various industries, enabling rapid and efficient AI adoption using existing CCTV infrastructure. Combined with KOCOM’s customer touchpoints and industry network, the pace of real market expansion is expected to accelerate.

🤝 Partnership Direction: Building markets together based on technological excellence and delivering tangible value to customers.

A New Leap in the AI Safety Solutions Market​

Starting with deployments at KOCOM headquarters and Golden Seoul Hotel, this project is set to become a flagship reference demonstrating EVA’s competitiveness in the construction and hospitality sectors.

Building on this foundation, the two companies plan to further expand their collaboration in AI-based safety management and continuously introduce solutions applicable across diverse industrial environments.

This partnership is expected to become a meaningful reference for the adoption of AI safety solutions in construction and hospitality markets, while creating a mutually beneficial growth opportunity for both companies in the broader AI solutions landscape.

EVA will continue to drive Physical AI innovation together with its partners, building safer and smarter physical environments.

In a previous post, I shared our commitment to collaborating with Rebellions NPUs to enable 24/7 “always-on AI” for industrial environments.

https://spectrabrain.ai/en/blog/News/rebellions

Today, I’m pleased to announce that this commitment has resulted in a tangible technical milestone.

spectrabrain.ai’s EVA (Evolved Vision Agent) has successfully completed end-to-end service validation on Rebellions’ latest server-grade NPU, ATOM™-Max, integrating Vision models, LLMs, and VLMs into a unified production pipeline.

🛠️ Beyond Running a Model — Executing the Entire Service Pipeline​

Running a single model on an NPU is fundamentally different from operating an entire production service reliably. Through this validation, EVA demonstrated uninterrupted execution of the full pipeline on ATOM™-Max:

Camera Input → Object Detection (Vision) → Scenario Interpretation (VLM) → Situation Assessment (LLM) → Alert & Control Dispatch

This result confirms that complex AI pipelines required in real-world operations — beyond isolated model benchmarks — can be fully orchestrated on NPUs.

Rebellions has also recognized this milestone as “the first real-world operation of a VLM-based AI service on a commercial NPU platform,” expressing strong expectations for future adoption.

📈 Next Phase: Quantifying TCO Innovation Through Stress Testing​

Following successful end-to-end validation, EVA now enters the stress testing phase, simulating real factory environments.

We will analyze system stability, throughput, and power efficiency under extreme conditions where multiple cameras generate simultaneous input streams. The insights gained will be delivered to customers as actionable guidance, including:

1. Optimal NPU Configuration Standards Cost-efficient hardware configuration guidelines based on camera count and required inference performance.

2. Quantified TCO Reduction vs. GPUs Practical economic analysis including power consumption and operational costs — not just hardware pricing.

3. Minimized Deployment Risk Standardized NPU configurations that shorten deployment time and accelerate large-scale adoption.

✨ Conclusion: Reducing GPU Dependence and Enabling Sustainable AI​

The key takeaway from this validation is clear: Multimodal industrial AI has reached a level where real-world operations are possible using NPUs alone.

For organizations that have hesitated to adopt AI due to high GPU costs, the combination of EVA and Rebellions offers a practical and powerful alternative.

By breaking the high-cost barrier and enabling safer, higher-quality, and more productive operations at lower cost, EVA and Rebellions are working together to establish a new standard for sustainable industrial AI.

EVA v2.5 focuses on eliminating recurring inconveniences found in real-world operations and helping users more easily understand and manage the system’s status. This version introduces new features such as automatic face blurring to reduce exposure risks, license‑based operational visibility, and improved usability during configuration. Operators can now experience a more predictable and stable EVA environment.

Automatic Face Blur: Clear in real time, safe when recorded or shared​

Faces detected in images are now automatically blurred, minimizing unnecessary exposure even when images are shared via chat notifications or Webhook. Importantly, the real‑time streaming view during monitoring remains clear, just like before. This means you maintain the same ability to make fast, accurate decisions on site, while only the stored or externally shared images are blurred—reducing the burden during the record‑and‑share stages.

License Status at a Glance: Instantly check how long and how much you can use​

After registering a license key, you can immediately check the remaining validity period, the number of cameras allowed, and whether the license is Trial or Standard. Advance notifications alert you before expiration, preventing accidental lapses, and EVA automatically stops operation once the license expires—avoiding unintended continued operation. Users can now easily verify the installed EVA’s license status without additional inquiries or internal checks, enabling more planned and convenient management.

Object Detection Sensitivity: Adjust with numbers for clearer control of results​

The previous term “Detection Sensitivity” has been updated to the more precise “Object Detection Sensitivity”, and instead of “Low/High,” it is now adjusted using a numeric value between 0 and 1, allowing you to intuitively understand how each setting affects detection results and tune it quickly. Lower values detect more objects across a wider range, while higher values detect only more confident cases. This value is used as the threshold applied by the Vision Model (VM) when detecting objects, and the detected object information is then passed to the Vision‑Language Model (VLM), directly affecting final scenario evaluation. With clearer terminology and detailed guidance, you can select the appropriate value for your environment and achieve the detection performance you want. In addition, the next version will introduce an Agent feature that automatically sets object detection sensitivity based on detection results, adjusting sensitivity for each camera according to its configured scenario—providing even more convenient and stable detection performance for users.

Understand EVA Features More Easily Through Conversation​

If you have questions about the various features and configuration options provided by EVA, you can check them directly through the in-app chat window. The existing guidance capability has been further enhanced, delivering clearer and more structured explanations—including how specific features work, the meaning of configuration values, and how to apply them. You can ask about any EVA-related feature or setting at any time.

There is no need to navigate through complex menus one by one. Simply enter your question in natural language to receive immediate guidance for faster and more efficient operations. Beyond basic feature descriptions, EVA provides an enhanced support experience that helps you quickly understand features and configure them with confidence.

Camera Setup: Faster and easier with step navigation + instant save​

The inconvenience of having to navigate back and forth through multiple steps to modify or save values within the four‑step camera configuration screen has been resolved. You can now save at any step, eliminating the need to move to the final step and return again. By clicking the step number at the top of the configuration screen, you can jump directly to the desired step, and the save button in each step allows you to quickly apply only the necessary changes. When configuring multiple cameras consecutively, fewer clicks are required, making the overall setup process significantly faster and more convenient.

EVA continues to evolve based on real operational experiences from our customers.
The EVA development team reflects customer needs and on‑site feedback faster than anyone and continues to advance our technology to enhance accuracy and stability.
We will keep delivering innovations that transform expectations of a “properly built product” into clear value.
Your feedback is the most important driving force that makes EVA a stronger and more complete solution!

🚀Coming Soon: Preview of v2.6.0​

• Improved accuracy with multi‑image‑based detection
• Lightweight Vision Model detection mode for optimized operations
• Significantly enhanced UX for feedback submission and review

POSTECH (Pohang University of Science and Technology), the epicenter of engineering education and research in Korea, has officially confirmed the adoption of spectrabrain.ai’s EVA at its Future Technology Center. This collaboration goes far beyond enhancing campus security—it marks a major milestone in building a Data Living Lab, where all visual data generated on campus is transformed into valuable research assets.

🏛️ The Entire Campus as a Massive AI Laboratory​

An Integrated Indoor & Outdoor Sensor Network​

The POSTECH Future Technology Center will unify its existing campus-wide CCTV infrastructure through the EVA platform. By integrating sensors across the entire campus, the university establishes an infrastructure capable of real-time perception and reasoning—understanding and interpreting events in the physical world without human intervention.

🧪 A New Fuel for R&D​

From “Discarded Footage” to “High-Value Data”​

Until now, campus video data has been treated as ephemeral information, deleted after a certain retention period. EVA fundamentally changes this paradigm by turning video into long-term research assets.

• A Catalyst for LLM & VLM Innovation EVA automatically converts unstructured video into structured data. This creates high-quality multimodal datasets for training next-generation Large Language Models (LLMs) and Vision-Language Models (VLMs), allowing researchers to focus on insight generation rather than data preprocessing.

• Spatiotemporal Metadata Enrichment Instead of storing video alone, EVA enriches data with contextual information—such as congestion levels during exam periods (Time) or in library spaces (Space)—significantly increasing data density and analytical value.

🔒 Privacy-by-Design​

Secure Research Assets, Completed at the Moment of Collection​

As massive volumes of visual data are transformed into research assets, privacy protection stands as the highest priority of the POSTECH Living Lab.

• Immediate Data Processing Raw video captured by cameras is analyzed instantly at the point of collection, before being stored on servers.

• Automatic De-identification Any personally identifiable information detected during analysis is immediately de-identified. This ensures that researchers can securely access high-quality research datasets without privacy concerns.

🚀 A Research Ecosystem Where Students Become Creators​

Student as a Creator​

The POSTECH Living Lab redefines students not as passive service users, but as active producers of technology.

• AI Training with Real-World Data Instead of textbook examples, students train AI models using real data generated from their own campus environment, implementing advanced decision-making logic firsthand.

• Development of On-Site, Practical Services By deploying AI services that solve everyday problems—such as cafeteria queue prediction or classroom energy optimization—students directly experience the full potential of a Physical AI platform.

“Reading the real world as data, interpreting it with AI, and transforming reality for the better.”​

The virtuous cycle that POSTECH and EVA are building together is a compelling example of how a university campus can become a hub for future technologies. As everyday life at POSTECH turns into data—and that data, in turn, shapes the technologies of tomorrow—we invite you to follow this journey into the future.

The core message is clear.
Generous tax incentives will be provided for the adoption of safety facilities leveraging new technologies such as AI,
while severe penalties—at a level that could threaten corporate survival—will be imposed for violations of safety obligations.

This policy is not a recommendation.
By presenting both clear incentives for safety investment and devastating penalties in the event of accidents,
the government is making safety investment a mandatory requirement rather than an optional choice for companies.

Three Key Pillars of the Policy​

• Three-Tier Tax Incentive Package
  Expansion of tax credits up to 12–40% for investments in AI-powered safety facilities
  (R&D tax credit rates: General 2–25%, New Growth & Core Technologies 20–40% / Investment tax credit rates: General 1–10%, New Growth & Core Technologies 3–12%)
  

• Stronger Accountability
  Introduction of new penalty fines equivalent to 5% of operating profit or 3% of revenue in the event of fatal accidents (Legislation and amendments planned for the first half of 2026)

• Intensified Oversight
  Expansion of industrial safety inspectors to 2,095 personnel and introduction of restricted bidding for high-risk construction projects

Safety Investment Is Now State-Supported​

The government has begun recognizing AI-based safety facilities as “New Growth & Core Technologies.”

This signals more than regulatory relaxation—it reflects a shift in perception,
where safety technology investment is now regarded as a core pillar of national competitiveness.

• AI Monitoring Systems Included in Integrated Investment Tax Credits

Tax credit eligibility is significantly expanded to include AI-powered intelligent CCTV monitoring systems,
even beyond legally mandated facilities.
The EVA solution represents the standard for next-generation safety facilities recommended by the government.

• Preferential Treatment for R&D and Facility Investments Under New Growth & Core Technology Designation

Investments in advanced safety technologies utilizing AI and robotics are eligible for tax credits
ranging from up to 12% for facilities to 40% for R&D.
(R&D tax credit rates: General 2–25%, New Growth & Core Technologies 20–40% / Investment tax credit rates: General 1–10%, New Growth & Core Technologies 3–12%)
Now is the optimal time to deploy high-performance EVA solutions at the lowest possible cost.

A Single Accident Can Undermine an Entire Company​

Regulatory scrutiny has become significantly more stringent.
The introduction of a punitive penalty framework starting in 2026 makes reactive, after-the-fact responses no longer viable.

• Penalty fines of 5% of operating profit or 3% of revenue in the event of fatal accidents (cap: KRW 100 billion)

Under amendments to the Occupational Safety and Health Act and the Construction Safety Special Act,
companies facing repeated fatal accidents may be fined up to 5% of operating profit or 3% of revenue (legislation and amendments planned for the first half of 2026).

This goes beyond a simple fine—it poses a direct threat to corporate management and sustainability.

EVA intelligently monitors worksites 24/7, proactively identifying and blocking fleeting risk factors that human operators are likely to miss.
Accident prevention is now the most reliable cost-saving strategy.

Why EVA: A Full-Stack AI Safety Solution​

More than just an AI solution, EVA delivers a full-stack AI experience optimized for each customer’s business environment.
Enjoy unparalleled operational efficiency and flexibility—free from dependence on any single technology stack.

1. Freedom to Choose AI Models Optimized for Your Environment​

Select the AI stack best suited to your operational environment while maintaining powerful safety monitoring performance.

Global leading AI models such as HyperCLOVA X, Qwen, Gemma, LLaMA, ChatGPT, and EXAONE,
along with cutting-edge vision models including ultralytics YOLO, OWL-ViT, RT-DETR, and OmDet,
can all be freely deployed on the EVA platform.

2. One-Quarter of the Total Cost of Ownership (TCO) Compared to Competitors​

High deployment costs and slow maintenance hinder growth.
EVA delivers overwhelming cost efficiency—from initial investment through ongoing operations.

Now Is the Right Time. Let EVA Be Your Trusted Safety Partner.​

On January 29, 2026, the Cisco Korea Manufacturing Summit 2026, a key event focused on digital transformation in the manufacturing industry, was successfully held. At this event, spectrabrain.ai showcased its innovative Physical AI solution, EVA, presenting concrete ways to maximize safety and operational efficiency on manufacturing floors. In particular, the co-hosted booth with partner Ringnet and the live customer case presentation left a strong impression on attendees. Here are highlights from the vibrant现场.

1. Capturing Attention on the Floor: “EVA x Meraki” at the Ringnet Booth​

At this summit, spectrabrain.ai demonstrated a real-time Physical AI solution that combines Cisco Meraki with EVA at the Ringnet booth.

The booth featured a live demonstration integrating Meraki cameras, backed by robust cloud-based infrastructure, with EVA, which analyzes visual data much like the human eye and brain. Visitors were able to see firsthand how simply connecting EVA to an existing CCTV infrastructure transforms it into an intelligent system capable of understanding and 판단 complex physical environments on its own.

💡 On-site feedback: Many attendees showed strong interest in the ability to build an advanced AI analytics environment using their existing Meraki infrastructure—without investing in additional high-cost hardware. In particular, real-time dashboard visualizations for worker safety detection and restricted-area intrusion alerts, both critical in manufacturing environments, drew enthusiastic reactions from practitioners.

2. A Customer Case Presentation Filled with Laughter and Empathy​

Starting at 1:00 PM, the Case Study session was held under the theme “An Intelligent Platform Opening the Era of Physical AI.” Rather than a simple feature walkthrough, the session vividly illustrated how EVA is actually being used in real manufacturing sites.

The presentation covered concrete examples of how EVA has been deployed in production environments to protect workers and improve operational efficiency. As demonstrated in locations such as Pyeongtaek Digital Park, scenarios where EVA checks compliance with safety gear requirements or immediately alerts operators to dangerous situations resonated strongly with the audience as practical, real-world solutions.

🗣️ Presentation atmosphere: Although it could have been a dry technical session, the speaker explained how EVA addresses on-site challenges with wit and clarity, keeping the audience engaged throughout. After the session, many attendees followed up with comments like “We want to apply this to our factory right away,” clearly demonstrating that EVA is not just theoretical technology, but a “living technology” ready for immediate deployment.

3. Powerful Technology Designed for Ease of Use: EVA​

The core value of EVA emphasized throughout the summit was “professional AI that anyone can use easily.”

• ✅ Natural language–based control: No complex coding is required. By entering scenarios in everyday language—such as “Find workers not wearing safety helmets”—EVA understands the intent and begins analysis. This enables on-site managers to operate AI systems without being IT experts.
• ✅ Cost-efficient architecture: Through its unique architecture, EVA significantly reduces the operational costs typically associated with high-priced multi-modal LLMs. As a result, enterprises can deploy high-performance AI across manufacturing sites without excessive infrastructure 부담.
• ✅ Beyond detection to action (Physical Action Trigger): EVA does more than just observe. When a risk is detected, it can trigger real-world actions—such as turning on warning lights or controlling gates—by integrating with physical devices, delivering a complete closed-loop system.

4. Moving Forward with Continuous Innovation​

The Cisco Korea Manufacturing Summit 2026 clearly demonstrated the value that spectrabrain.ai EVA can create in the manufacturing industry. The strong interest at the Ringnet booth and the lively interaction during the presentation sessions reinforced our confidence in the direction we are heading.

Together with trusted partners such as Cisco Meraki and Ringnet, spectrabrain.ai will continue to lead innovation in Physical AI, helping manufacturing sites become safer, smarter, and more efficient.

👉 Industrial AI Powered by EVA: Finding the Answer in 'Economic Efficiency' Beyond Performance​

In industrial environments, AI is no longer a function to be called only when needed.

It must be an 'Always-on' system that performs continuous inference 24/7, processing the constant stream of data generated by cameras and sensors.

However, operating massive AI models like Vision-Language Models (VLMs) on expensive GPU-based infrastructure around the clock imposes a significant cost burden on customers.

To break down this cost barrier and accelerate the adoption of industrial AI, spectrabrain.ai EVA has joined forces with Rebellions.

👍 1. NPU: Surpassing GPU Limits in Price Competitiveness and Efficiency​

Innovation in infrastructure costs (TCO) is essential for the widespread adoption of industrial VLM services. Rebellions' NPU meets these demands with superior efficiency compared to general-purpose GPUs.

• Unrivaled Inference Performance: Rebellions’ ATOM NPU has proven up to 3x faster processing speeds in the vision domain compared to equivalent GPUs in global benchmarks like MLPerf.
• Superior Performance-per-Watt and Cost Savings: In a 24/7 operational environment, the NPU reduces power consumption by more than 50% compared to GPUs while maintaining high throughput (TPS). This directly leads to a reduction in the customer's operational cost burden.
• VLM Optimization: Latest large-scale model optimization technologies, such as FlashAttention and PagedAttention, are implemented at the hardware level, allowing heavy VLMs to run lightly and quickly.

EVA running on Rebellions NPU means customers can own cutting-edge Physical AI at the most economical cost.

👍 2. VLM Optimization: Extensive Model Testing and Technical Validation​

spectrabrain.ai is currently testing various state-of-the-art VLM models within the EVA platform in the Rebellions NPU environment.

We are going beyond simply replacing hardware; we are advancing our software stack to ensure that complex industrial scenarios are processed at optimal speeds on the NPU.

Through this process, we are finalizing the 'NPU-based VLM Service, EVA' at a level ready for immediate field deployment.

👍 3. From LG Electronics Deployment to Global Supply: A Strategic Roadmap​

The collaboration between spectrabrain.ai and Rebellions aims for substantial business expansion beyond a simple technical partnership.

1. Advanced VLM Optimization: We are in the validation stage to ensure optimal power efficiency and processing speed by testing various latest VLM models on Rebellions NPU.
2. Deployment at LG Electronics Production Sites: Based on validated VLM models and NPU optimization technology, we are prioritizing the introduction of NPU-based AI into major production processes and safety monitoring systems within LG Electronics.
3. External Supply of EVA+NPU Package: Leveraging successful references at LG Electronics, we plan to provide the EVA platform in an integrated solution package with Rebellions NPU for future external clients.

By adopting EVA, customers can enjoy a full-stack service that combines optimized hardware and a robust platform at a reasonable price, without the hassle of selecting complex hardware themselves.

👏 Conclusion: The Standard for Sustainable Industrial AI​

The combination of EVA and Rebellions NPU is a strategic choice to transform AI from a simple technology adoption into a service structure that operates continuously at a realistic cost.

Through this powerful collaboration spanning from hardware to the service platform, spectrabrain.ai will become a partner that accelerates AI transformation in industrial fields and fundamentally resolves the infrastructure burden for our customers.

The EVA v2.4 release reflects the requirements raised in real operational environments, significantly improving monitoring efficiency and user experience. This update focuses on Alarm Priority Sorting, Device Favorites, Expanded Language Support, and Enlarged View of Detection Result Images, delivering convenience that can be felt immediately in monitoring operations.

Alarm Priority Sorting – Never Miss Real-Time Responses Among Numerous Devices​

In a monitoring environment with numerous connected devices, the most important thing is immediate identification and response to alarm-triggered points. When a detection alarm occurs, EVA automatically moves the corresponding device to the top of the list, allowing you to quickly and easily identify the alarm-triggered device even in a complex list. This feature is designed to display the latest events at the top in order, even when multiple alarms occur simultaneously, so you can see the most critical screen at a glance without scrolling or searching. As a result, monitoring efficiency and response speed are greatly improved, and when combined with the Favorites feature, you can prioritize monitoring of key devices where alarms occur.

Device Favorites – Focused Monitoring of Key Points by Operator​

The more cameras you monitor, the more important it is to quickly check critical points. With this update, EVA allows users to register key devices they manage as favorites and filter them for instant access. This feature is especially useful in environments where device responsibility varies by operator. Each operator can manage their critical devices as a favorites group to ensure no important point is missed and maintain focused monitoring. Grouping priority monitoring cameras such as entrances, high-value equipment storage areas, and safety management zones will further enhance monitoring efficiency.

Expanded Language Support – EVA Accessible to Everyone​

EVA now supports both Korean and English. You can select your preferred language in the settings menu, and language changes can only be made by accounts with administrator or manager privileges. This update makes EVA easy to use even for users unfamiliar with AI by providing all screens and functions in Korean and simplifying technical terms. In addition, detection analysis results can be provided in the desired language to minimize communication errors, enabling quick adaptation for new users and consistent information sharing across teams.

Enlarged View of Detection Result Images – Faster and More Accurate Situational Assessment​

In real-world monitoring environments, the quality of response depends heavily on how quickly and accurately detection result images can be reviewed after an alert is triggered. With EVA v2.4, the image enlargement experience—previously available only through external notifications such as Microsoft Teams or Slack—has been extended directly into EVA’s built-in chat interface. Detection result images delivered via the chat window can now be opened in a separate, enlarged view, allowing users to inspect high‑resolution images and freely zoom in with a single click. This eliminates the need to rely on small, embedded thumbnails within the chat area and enables immediate, clearer analysis of detection results on a larger screen. As a result, operators can closely examine critical detection elements—such as people, vehicles, and object locations—making it easier to distinguish false positives and significantly reducing the time required to decide on follow-up actions.

Support for Duplicate Camera RTSP Registration – Run Multiple Scenarios from a Single Camera​

In many real-world environments, a single camera feed often needs to support multiple detection scenarios simultaneously. For example, a parking lot camera may need to detect illegal parking, pedestrian safety risks, vehicle wrong-way driving, loitering, or intrusion — each as separate monitoring scenarios. To improve this flexibility, EVA now supports duplicate RTSP registration. You can register the same RTSP address to multiple virtual cameras, and configure different detection scenarios independently for each one. With this enhancement, you can monitor various situations in parallel using a single live video stream, while greatly improving scenario configuration flexibility without adding hardware or modifying the network setup.

Other Key Improvements​

This release also includes the following enhancements:

• Session logout time can be configured to match the installation environment.
• Improved repeated login requests when viewing detection images on mobile.
• Enhanced UI for device registration and expanded detection scenario area.
• Added device name editing feature.
• Detection alarm images can now be viewed in Slack.

EVA Listens to Your Feedback and Improves Faster​

This release was implemented based on customer feedback. The EVA team is committed to quickly improving inconveniences through short release cycles and continuously enhancing accuracy and responsiveness based on data collected from PoC and commercial environments. UI/UX improvements prioritize on-site usability, and we will continue to deliver features that reflect customer needs quickly. Your feedback is the driving force that makes EVA a better product.

Experience the Updated EVA v2.4 Now​

If you have any feature requests or improvement suggestions, please feel free to share them with us.

We held strategic discussions with Ringnet CEO Lee Jeong-min regarding the expansion of the EVA business.

As the domestic distributor of Cisco Meraki, Ringnet is a specialized partner with powerful network/security infrastructure and on-site implementation capabilities. Through collaboration with LG Electronics, Ringnet will play a crucial role in expanding EVA's Physical AI technology across various industries, including manufacturing, logistics, and the public sector.

During this meeting, we discussed in-depth strategies for nationwide and global expansion, building on the success of the "Meraki CCTV + EVA" integration PoC (Proof of Concept) verified at the LG Electronics Pyeongtaek Digital Park. Based on the success factors of the Pyeongtaek case, we explored ways to seamlessly integrate EVA into the Meraki ecosystem, making it easier for domestic manufacturing companies to adopt the solution and establishing a foundation for long-term global market expansion.

Regarding the direction of the partnership, we agreed to promote mutual growth through various business models, such as proposing an integrated package of "EVA + Meraki CCTV + Action Trigger" sensors, as well as standalone EVA sales structures. Ringnet plans to identify key targets within its existing customer base in manufacturing, distribution, logistics, and the public sector through consultation with its sales force, which will further accelerate EVA's market penetration.

Notably, at the Manufacturing Summit hosted by Cisco Korea on January 29, EVA will be featured and demonstrated as the main solution at the Ringnet booth. Moving beyond a simple CCTV exhibition, we are co-developing real-time demo scenarios designed to capture customer interest. These collaborative efforts are opening new possibilities for EVA to lead innovation in safety, security, and operations at domestic manufacturing sites by combining with Meraki's global cloud infrastructure.

We look forward to the exciting developments ahead.

While previous AI focused on providing general answers, our core mission is "Vertical AI."

• Researcher-led Vertical Foundation Models: Our AI researchers develop Foundation models equipped with specialized knowledge and reasoning capabilities optimized for specific industrial sectors.
• Commercializing Industry-Specific Services with EVA: These Vertical models are immediately integrated into spectrabrain.ai’s EVA. Through EVA’s natural language-based scenario settings and real-time field control technology, they are transformed into AI applications that work instantly on-site without the need for complex coding.

A Paradigm Shift in Industrial Safety for Construction and Manufacturing​

Our primary focus is "Industrial Safety," a domain where the highest levels of precision and reliability are mandatory.

• Safety-Specific Models: We are building dedicated models that possess a deep understanding of the unique risk factors found in construction and manufacturing environments.
• Intelligent Monitoring Solutions: By combining EVA’s vision capabilities—which "understand" rather than just "see"—we plan to supply next-generation safety solutions to major manufacturing and construction firms. These solutions go beyond simple intrusion detection to proactively predict and respond to risky worker behavior.

Leap forward as a Key Player in the EXAONE Ecosystem​

This collaboration aligns with the LG EXAONE Alliance, South Korea’s premier hyperscale AI ecosystem.

Core Agentic AI Platform: Within the EXAONE ecosystem, which currently features 23 leading partners, EVA serves as the core Agentic AI platform connecting the physical world with AI. Global GTM (Go-To-Market): Leveraging the powerful synergy of the EXAONE ecosystem, we will accelerate our global market entry and secure strong market competitiveness alongside partners from various domains.

Together with our AI researchers, we are standing at the center of innovation—a journey where technology crosses the threshold of the lab to prove its value in the most demanding industrial fields of our lives.

A university campus is an ocean of data. Thousands of people move, live, and interact every day. Until now, cameras in this space existed only for “security” and “surveillance.” Countless recorded video data created no value and were discarded over time.

We asked a question: "Instead of simply discarding this vast data, can we use it as an 'asset' to make the campus smarter?"

From this question, the Postech Living Lab project based on EVA (Evolved Vision Agent) began.

Phase 1. The First Step Toward a Safer Campus (The Foundation)​

Our first mission was clear: create an environment where Postech students and staff can live with peace of mind. We initially deployed the EVA solution to enhance the campus security system.

• Monitoring without blind spots: Detecting risk factors in key campus areas
• Intelligent accident prevention: Immediate alert system for abnormal behaviors such as falls or intrusions

At this stage, EVA has proven its fast and accurate video analysis capabilities, successfully serving as the reliable “eyes” that protect the campus.

Phase 2. Evolution into a Data-Driven Research Platform (The Expansion)​

Now we move beyond physical safety toward intellectual innovation. EVA expands from a simple security tool into a core platform that transforms the campus into a massive “AI Living Lab.”

1. Turning Discarded Data into Assets (Data as an Asset)​

EVA breathes life into collected video data.

• Automated processing: Analyze raw video data at the collection stage and convert it into research-ready datasets (including anonymization for privacy protection).
• Contextual integration: Go beyond “a person walked by” to combine spatiotemporal metadata such as “library focus level during exam period.” This builds a repository of high-quality data assets with strong research value.

2. Students Become Creators, Not Consumers (Student as a Creator)​

The main actors of the Living Lab are students. Traditionally, students were mere consumers of school-provided services. But on the EVA platform, things change.

• Real-world AI practice: Train AI models using real campus data—not textbook examples—based on where you walk and live.
• Service development leadership: “Is the cafeteria line too long?” Students can use EVA data to develop and deploy a “cafeteria congestion prediction service.” Through hackathons and idea competitions, students define problems and create solutions, growing into true Creators.

Future. A Virtuous Cycle Where Daily Life Becomes Research​

The future we envision for Postech is a Virtuous Cycle. Data accumulated through EVA becomes material for better AI models, which in turn return as services that improve campus convenience and safety.

• Smart cafeteria: Enjoy meals without waiting during peak hours
• Energy optimization: Automatic HVAC control based on classroom usage patterns
• Safety research: AI that detects lab hazards before anyone else

EVA will make Postech not only the safest place but also fertile ground for the most innovative AI talent. Starting from safety management and evolving into R&D innovation, EVA will lead this journey together with Postech.

Research achievements with Postech can be found in the blog below:

- Performance Enhancement through Instruction Tuning Based on User Feedback Data​

- From Image to Language, From Language to Reasoning: Boosting VLM Performance with Camera Context​

The EVA v2.3 release is not just about adding new features—it’s an update designed to eliminate inefficiencies in large-scale camera operations, improve detection accuracy, and dramatically enhance the user experience. EVA is now smarter, more intuitive, and more powerful than ever.

Say Goodbye to Repetitive Tasks! Common & Custom Detection Scenarios​

One of the biggest challenges in managing large-scale camera operations is the inefficiency of registering the same detection scenario across dozens or even hundreds of cameras. For example, if you manage 100 cameras, you previously had to register the same scenario 100 times—a time-consuming and labor-intensive process.

EVA v2.3 solves this problem by introducing the Common Scenario feature. Now, administrators only need to define a Common Scenario once in the EVA settings menu. Connected cameras can automatically apply this scenario, and if needed, you can add Custom Scenarios for individual cameras. Furthermore, EVA allows both Common and Custom Scenarios to be applied simultaneously, greatly improving operational flexibility.

What benefits does this bring to EVA users?​

• Significantly reduces registration time and repetitive tasks in large-scale operations.
• Updates to Common Scenarios are automatically reflected across all cameras, maximizing management efficiency.
• Administrators can focus on strategic operations and safety enhancements instead of repetitive work.

Define Your Own Zones for More Precise Detection​

EVA v2.3 introduces a new Detection Zone Setting feature. This feature moves beyond the traditional approach of detecting across the entire screen, allowing users to freely define specific zones and apply customized scenarios to those zones. Users can draw rectangular areas on the camera stream, name them, and set detection scenarios for each. For example, you can easily implement a scenario like “Send an alert when someone enters Zone A.” But this feature isn’t limited to safety management. It can be used in various industrial environments—detecting defective products on a specific section of a production line, monitoring work status in a warehouse zone, or analyzing customer behavior around a particular display in retail stores. Now, administrators can go beyond monitoring the entire screen and focus on critical areas based on operational goals for precise detection. EVA supports scenarios that enhance safety, productivity, quality control, and customer behavior analysis.

What benefits does this bring to EVA users?​

• Enables customized detection tailored to operational goals by defining specific zones.
• Reduces unnecessary alerts and ensures accurate event responses.
• Expands coverage and application range through diverse scenarios.

More Intuitive and Powerful Image Guided Detection​

We’ve taken the Image Guided Detection feature to the next level. This feature allows users to specify images for detection. Previously, the process of selecting images, setting areas, deleting, and managing them was complex and difficult to use. In this update, we’ve made image selection, labeling, registration, editing, and deletion far more intuitive. Now, users can easily register desired images and implement customized detection with minimal effort. This feature is extremely useful for detecting defective products in manufacturing processes, but its applications go much further. For example, checking specific packaging conditions in a warehouse, monitoring product display arrangements in retail stores, or tracking the location of specific equipment on construction sites. In situations where data is scarce or existing models cannot cover certain cases, Image Guided Detection becomes a powerful alternative.

What benefits does this bring to EVA users?​

• Solves data scarcity issues, enabling customized detection.
• Simplifies management processes, greatly improving user experience.
• Enhances accuracy and reliability across diverse industrial environments.

EVA continues to evolve. We will keep delivering smarter and more powerful features to support your operations.

The synergy between Meraki’s highly scalable, cloud-native video infrastructure and EVA’s lightweight yet high-precision AI vision engine offers significant potential across multiple industries. By combining Meraki’s centralized management and secure architecture with EVA’s advanced scenario detection capabilities, organizations can elevate an existing camera network into a powerful real-time intelligence platform—without additional hardware deployment.

During our discussion, we aligned on establishing an EVA demo environment at Cisco’s headquarters and initiating joint PoCs leveraging video data from Meraki cameras installed in public sectors such as schools and airports. These efforts aim to validate various safety, operational, and risk-detection use cases that can unlock new service models.

This collaboration represents a compelling opportunity to merge cloud-first infrastructure with cutting-edge AI. Exciting developments lie ahead.

KOCOM expressed strong interest in EVA’s economic efficiency and scalability, and both sides agreed to pursue a joint Proof of Concept (PoC) along with continued discussions to refine potential business models.

The session also provided valuable insight into how advanced AI technology can drive innovation in smart buildings and home IoT solutions, highlighting promising opportunities within the residential market.

Building on this momentum, both companies will continue strengthening their collaboration to deliver next-generation AI-powered smart living experiences. More exciting developments lie ahead.

📍 November 14, 2025 (Fri), LG Digital Park Learning Center

At the "2025 Second Half Enterprise Safety & Health Leaders Workshop" held at the LG Digital Park Learning Center, we had the meaningful opportunity to introduce the EVA solution. The one-hour session focused on "AI-based Intelligent Safety CCTV" and presented EVA’s innovative safety management capabilities along with a roadmap for enterprise-wide deployment.

During the workshop, spectrabrain.ai EVA highlighted ease of operation and cost efficiency as its core values. Leveraging multimodal LLM-based technology, EVA demonstrated real-time detection of worker safety status through simultaneous analysis of video and text data, coupled with instant alert functionality. This approach represents a key strength that sets EVA apart from conventional high-cost AI systems.

Following the session, an active Q&A took place, during which participants reaffirmed EVA’s potential to deliver tangible value in the safety and health domain across the following dimensions:

• Ease of Operations: Easy deployment and operation at worksites
• Cost Efficiency: Remarkable economic advantage over existing solutions
• Scalability: Continuous expansion through ongoing updates to both the solution and foundation models

During the workshop, EVA was proposed as a company-wide safety management solution. Through its adoption, we envision the establishment of an intelligent safety management system not only at LG Digital Park but across all LG workplaces, ensuring enhanced accident prevention and operational efficiency.