One thing, three names. In these docs we call your assistant a Digital Twin. You will also see it called an Instance — on the Instance Settings panel, in the admin Instances list, and in your web address (
your-instance.praxislxp.com) — and an Institution, which is what our software calls it behind the scenes (in API fields such as institution). All three mean exactly the same thing: one assistant, with its own knowledge, voice, members and settings. Which name you see depends on the screen you are on, not on what the thing is. An Account is different — it is the organisation that owns one or more Digital Twins.Integration Capabilities at a Glance
This section is for the person connecting Pria to something else — an LMS, a website, a voice product, or your own code. Each path below says who it is for and links to its setup guide.Supported Integration Paths
LMS Plug-and-Play with LTI
Seamlessly connect Pria to leading platforms like Moodle, Canvas, D2L (Brightspace), and Blackboard Learn via the industry-standard Learning Tools Interoperability (LTI) protocol. This ensures consistent user experiences, easy provisioning, and scalable rollouts across schools and organizations.Deep Canvas Integration
For organizations using Canvas, Pria enables a premium, branded experience with Custom Theme integrations—unlocking UI customization, direct navigation, and native workflows for optimal engagement.Universal Web SDK Integration
Extend Pria into any web or mobile application using the robust Web SDK. Leverage flexible components, secure authentication, and event hooks to power personalized learning journeys or embed AI assistants with minimal engineering overhead.AI Middleware & Model Context Protocol (MCP) Server
Pria can also act as an MCP server. Model Context Protocol is an open standard that lets an AI application borrow tools from another system. Pria offers asearch-instance-rag tool, which searches the documents uploaded to a Digital Twin and returns the passages that match a plain-language question — so a coding assistant or agent you run elsewhere can consult your twin’s knowledge without you copying the documents into it. The Praxis AI Middleware is the layer that makes this possible: it sits between your systems and the AI models and handles sign-in, retrieval, tools and conversation state.
Voice & Avatar Providers
Give your Digital Twin a voice — or a face. Pria’s Convo Mode supports OpenAI Realtime, OpenAI GPT-Live (listens and speaks at the same time while your twin’s own model answers), Gemini Live (30 voices, live transcription, ephemeral token security), xAI Grok voice, ElevenLabs Conversational AI (connect an agent to Pria’s Chat Completions API as a Custom LLM, with embeddable voice widgets), Cartesia expressive voices, and the Anam talking avatar. Compare them all in Voice & Realtime Providers.Sign-in
People reach Pria with an email and password, social login (Google, Microsoft, Apple, GitHub, Facebook), your organization’s single sign-on, or a launch from their LMS. See Authentication Overview.Avatar Embed Widget
Put your Digital Twin’s talking avatar directly on an external website with a single script tag (or React component). Visitors converse with the avatar anonymously — no Pria login — while your Twin’s knowledge and instructions drive every answer. See Avatar Embed Widget.The choice is yours
Chat Completions
Best Use Case:
Connect any OpenAI SDK app to a Digital Twin in minutes — minimal setup, full compatibility.
Connect any OpenAI SDK app to a Digital Twin in minutes — minimal setup, full compatibility.
Web App
Best Use Case:
Rapidly add AI-powered learning, support bots, or AI assistants to your own platform—no LMS required.
Rapidly add AI-powered learning, support bots, or AI assistants to your own platform—no LMS required.
MCP Server
Best Use Case:
Integrate Pria’s context-aware AI into custom LLM stacks, workflow engines, or analytic tools.
Integrate Pria’s context-aware AI into custom LLM stacks, workflow engines, or analytic tools.
Canvas
Best Use Case:
Deliver a unified, branded learning experience, automate class operations, or deploy digital twins natively in Canvas.
Deliver a unified, branded learning experience, automate class operations, or deploy digital twins natively in Canvas.
D2L
Best Use Case:
Empower instructors and students with AI-driven feedback and smart assistance within your Brightspace environment.
Empower instructors and students with AI-driven feedback and smart assistance within your Brightspace environment.
Moodle
Best Use Case:
Bring course-aware AI assistance into Moodle classrooms with a standard LTI Advantage tool.
Bring course-aware AI assistance into Moodle classrooms with a standard LTI Advantage tool.
Blackboard
Best Use Case:
Deploy digital twins across Blackboard Learn courses via LTI Advantage.
Deploy digital twins across Blackboard Learn courses via LTI Advantage.
ElevenLabs
Best Use Case:
Give your Digital Twin a voice — deploy real-time voice widgets powered by ElevenLabs and your Twin’s knowledge.
Give your Digital Twin a voice — deploy real-time voice widgets powered by ElevenLabs and your Twin’s knowledge.
Gemini Live
Best Use Case:
Native Google multimodal audio for real-time voice conversations with tool calling support.
Native Google multimodal audio for real-time voice conversations with tool calling support.
Avatar Embed Widget
Best Use Case:
Put your Twin’s talking avatar on any external website — anonymous visitors converse with it instantly.
Put your Twin’s talking avatar on any external website — anonymous visitors converse with it instantly.
Javascript APIs
Best Use Case:
Programmatically control Pria, trigger specific actions, or enrich your own UIs with targeted AI features.
Programmatically control Pria, trigger specific actions, or enrich your own UIs with targeted AI features.
Tip: Every integration path is fully documented — with code samples, diagrams, and accessibility guidance — to ensure a smooth rollout regardless of technical skill level.