Originally published at
[orquesta.live/blog/embedding-ai-workflows-orquesta-sdk] Embedding AI-powered workflows into existing web applications should be as seamless as possible. This philosophy guided us when building the Orquesta Embed SDK—a single script tag that brings robust AI capabilities directly to your app. Here's how we crafted this solution, with insights into architectural decisions, authentication flows, and real-time updates.
At the heart of our Embed SDK is a simple yet powerful premise: enable developers to integrate Orquesta's AI-driven operations without complex setup or infrastructure changes. The architectural design revolved around ease of use and performance.
The decision to encapsulate functionalities within a single script tag stemmed from a desire to reduce friction. Embedding Orquesta should feel natural, akin to adding an analytics tool or a customer chat widget. We designed the SDK to load asynchronously, ensuring it doesn't block the rendering of your web app.
A notable architectural choice was to employ microservices for handling different operations such as user authentication, real-time updates, and prompt submissions. This separation of concerns allows us to scale individual components independently based on demand and usage patterns.
Security is paramount, particularly when dealing with AI operations that might involve sensitive data or processes. Our architecture ensures that all interactions between your app and Orquesta are encrypted using AES-256. Moreover, because the Orquesta agent runs locally, no code or data ever leaves your infrastructure, maintaining complete privacy.
One of the critical components of embedding an SDK is seamless authentication. We opted for an OAuth 2.0-based flow to authenticate users. This allows for secure, token-based access to Orquesta's features and can easily integrate with existing identity providers, simplifying the experience for end users.
Our SDK initializes the OAuth process with a simple call, redirecting users to a login page if they aren't already authenticated. Once authenticated, the app receives a token granting it access to Orquesta's API.
Beyond just authentication, our SDK supports granular role-based permissions. Teams can define roles within the Orquesta dashboard, specifying what actions agents can perform. The SDK respects these permissions, ensuring that only authorized actions are executed within the embedded context.
To give users the responsiveness they need, we implemented real-time updates using WebSockets. This choice allows us to push updates to the web app instantly, providing feedback on AI operations as they occur. Monitoring the stream of outputs from AI agents becomes a dynamic and engaging experience, directly within the interface of your existing application.
One of the standout features within the Orquesta ecosystem is the Agent Grid. Embedded via our SDK, this component lets you monitor multiple AI agents simultaneously. Each agent's terminal can be viewed live, providing transparency and control over ongoing operations.
By embedding Orquesta, SaaS products can offer AI-powered workflows under their branding. The SDK supports customization options, allowing you to tailor the appearance and behavior to fit naturally within your product's UI.
This white-label capability extends the functionality of SaaS offerings, providing AI operation features without the need for significant in-house development.
Building the Orquesta Embed SDK involved balancing simplicity with powerful capabilities. From architectural decisions to real-time interactivity, each aspect was designed to empower developers to integrate AI operations effortlessly. For teams and organizations looking to enhance their workflows with AI, the Embed SDK provides a robust, secure, and flexible solution.
As we continue to evolve Orquesta, the commitment remains to provide tools that integrate seamlessly into the developer's workflow, making the power of AI accessible without compromising on ease of use or security.