Core Concepts

Qubitz is organized around six core capabilities. Together they cover the full lifecycle from AI strategy discovery through to production deployment and ongoing management.

Use Case Tool

The AI-powered discovery engine. Accessed via AI Assessment in the top navigation bar, it opens a chat-based intake with a Business Requirements panel. Describe the company in the chat - the platform auto-researches it and fills the panel through natural conversation.

Click Initiate assessment to choose a route:

• Yes - full AI Readiness (~12 min) - adaptive Q&A across 6 categories (Organization & Strategy, Tech Infrastructure, Data Readiness, Team & Skills, Compliance, AI Initiatives), then use cases plus 6 scored PDF reports
• No - use cases only (~8 min) - use cases generated directly, no extra reports

Results land on the Jamming Board - a collaborative workspace where your team rates use cases with star ratings and threaded comments. Sentiment analysis on comments feeds into ranking automatically. The top-ranked use case gets a Best Fit badge. Additional artifacts (Executive Presentation, AWS Architecture Diagram) can be generated on demand from the Artifacts panel.

Business email is required. Personal email domains (Gmail, Yahoo, Hotmail, and others) are not accepted at signup, invite flows, or the Use Case Tool form.

Control Hub

The AI-powered agent design, test, and deployment engine. Takes your identified use case and automatically designs a custom multi-agent system tailored to solve it.

Five tabs:

• Agentic Workflows - The Workflow Architect generates multi-step workflow plans for your use case. Each workflow has a name, description, and ordered step list. Limits: 30 workflows per project, 300 KB total, 24 KB per workflow. Remaining capacity is shown before you hit the cap.
• Agentic System - The Workflow Architect generates a multi-agent architecture (3-7 agents) with roles, models, tools, memory, and system prompts. Edit any agent inline or refine via the chat panel. Deployment to AgentCore fires automatically once the spec is ready - no manual Approve step.
• Data - Upload knowledge base documents, connect structured datasets, configure MCP integrations, and build a domain property knowledge graph (GraphRAG) via the AI-powered graph builder and Cytoscape.js canvas.
• Test Bed - Live chat connected to your AgentCore runtime with a real-time Agent Activity Tree and structured evaluation across up to 8 metrics (Response Quality, Task Completion, Tool Usage, Safety).
• Deploy - Full-stack app generation (code streams in real-time → auto-builds via GitHub + Amplify), API endpoint and key management, Developer Guide generation, and Business Case analysis (cost estimates, AWS architecture diagram).

Post-deployment, the Application Management dashboard gives you ongoing control: agent configuration, observability, FinOps, compliance, identity, App Refiner, and custom domains.

GraphRAG

A domain knowledge graph builder inside the Control Hub Data tab. GraphRAG lets you define and visualize the conceptual structure of your problem domain before and after agent deployment.

• Nodes represent domain entities (concepts, processes, products, regulations)
• Edges represent relationships between nodes
• Evidence anchors every node and edge to a source document

The graph is visualized interactively via Cytoscape.js and stored as versioned JSON in S3. The GraphRagAgent supports build (initial graph construction) and edit (incremental updates) actions via SSE streaming. Agents with GraphRAG available query it at runtime to answer precise relationship questions - complementing unstructured RAG with structured domain reasoning.

Blueprints

Pre-built, production-ready agent systems for high-value enterprise use cases. Each blueprint is a fully designed multi-agent application that Qubitz customizes to your company during a short setup wizard - no design work required.

17 blueprints across five categories:

Horizontal (any industry)

• Customer Support - omnichannel AI support agent (web chat, Slack, WhatsApp, voice) with human escalation
• Intelligent Document Processor - classify, extract, validate, review, and report on any document type
• AI Screening - automated voice-based candidate interviews with structured assessments

Healthcare & Life Sciences

• Clinical Documentation & Care Coordination
• Clinical Trial Operations & Patient Recruitment
• Consumer Diagnostics AI Analysis & Report Engine
• Patient Access, Referral & Care Navigation
• Pharmacovigilance & Safety Case Management
• Regulatory Submission & Medical Affairs Workflow

Financial Services & Insurance

• Financial Crime Investigation & Case Management
• Lending Case Processor
• Regulatory-Compliant Contact Centre Agent

Media & Entertainment

• Advertising Planning & Campaign Operations
• Content Supply Chain & Distribution

Manufacturing & Automotive

• Predictive Maintenance Planner
• Quality Investigation and CAPA
• Supply Shortage and Exception Response

See the Blueprints page for full detail on each blueprint.

AI Assessment

The AI readiness assessment route available at the Initiate assessment step in the Use Case Tool. Choosing Yes at the route selection dialog launches an adaptive Q&A of approximately 8-16 questions across 6 categories: Organization & Strategy, Tech Infrastructure, Data Readiness, Team & Skills, Compliance, and AI Initiatives. On completion, 6 scored reports are generated in parallel alongside your use cases: Revised Priority Use Cases, Platform Decision, Gap Mitigation Plan, AWS Fit Feasibility Report, ROI Modeling Report, and Well-Architected Framework Review.

Application Management

The post-deployment operations layer. Once your application is deployed, Application Management provides ten dedicated tabs: