It's been a non-stop few months, and we're excited to show off what we've been working on! Here are the latest product highlights:

Framework for building applications

When it comes to AI applications, they need to be secure, customizable, and easy to use. And our new framework for building applications ensures just that. Our plugin system consists of a published library of UI components, allowing developers to extend the platform's functionality with custom AI apps. This UI library ensures you can build and scale custom applications faster.

We’ve also created an Apps Portal - a landing page for authenticated users to access any number of Vertesia, third-party, or custom AI apps. 

And speaking of Vertesia apps, we’ve just launched our: 

AI Assistant App 

Our enterprise AI Assistant app is a solution for individuals, teams, and/or the entire organization to securely interact with AI agents via a user friendly chat interface. The agents have knowledge and context to autonomously complete business-specific tasks.

And the possibilities for the Assistant App are endless. Some examples include:

1. Reviewing contracts and policies

2. Analyzing customer data and sentiment

3. Creating product documentation and knowledge base content

4. Analyzing and generating images

5. Forecasting trends and demand

Just to name a few!

To learn more and see a quick video, please visit our AI Assistant App webpage.

Enhanced provisioning capabilities

We’ve added support for managing users as groups, simplifying permission management and user access to Vertesia projects and applications.

We’ve also added SCIM 2.0 support, which means users and groups can now be externally provisioned through identity and access management services like Microsoft Entra and Okta, centralizing and simplifying user and group management for large organizations.

Additional tooling options for AI agents 

We introduced support for tool plugins, allowing developers to create and expose custom tools for agents. This expands the capabilities of the agent workflow system and enables integration with external services and resources.

And we’ve added an MCP (model context protocol) client to access tools hosted on remote MCP tool servers. This enables AI agents access to a virtually unlimited number of MCP tools offered by third-party software vendors (like GitHub, for example).

Additional Product Features

We have also rolled out several other impactful enhancements:

Experience

• Granular permissions can now be assigned to users and groups on collections and their contents, providing greater flexibility and control over managing user access in Vertesia projects.
• Hybrid Search - which combines similarity (vector) and full-text searches into a single interface, adding flexibility to the search and improving search results for users and AI agents.

Enterprise ready

• Added Azure AI Foundry as an inference provider, including support for model families from OpenAI, Grok, Deepseek, Mistral, and Microsoft. This replaces the now deprecated support for the older Azure OpenAI.
• Dynamic rate limiting - Introduced a new rate-limiting mechanism that considers both the environment and the specific model being used. This enhancement optimizes execution of AI workloads based on the available capacity of models. 

What’s coming?

A new app - Review Center

The Review Center App is a comprehensive solution fit for a broad range of use cases focused on document review. This app provides a unified workspace for organizing documents, creating and managing checklists, and interacting with AI-powered agents. It significantly improves the speed of document review, and can process 1,000+ documents at once, while providing accurate results and recommendations. 

The Review Center App is currently in beta. Please reach out for a demo and more information. 

To wrap up

We are continuously adding new product features and capabilities to the Vertesia platform. Be sure to follow us on LinkedIn and subscribe to our blog to hear about the latest updates as they are announced!