User Personas
The MATIH Platform is designed to serve six primary personas, each representing a distinct role in a modern data organization. Every persona has a dedicated workbench application tailored to their workflow, and all personas share access to the conversational AI interface as their primary interaction model.
Persona Overview
| Persona | Primary Workbench | Core Activity | Key Platform Capabilities |
|---|---|---|---|
| Data Engineer | Data Workbench (3002) | Build and maintain data pipelines | Pipeline orchestration, data quality, catalog management |
| BI Developer | BI Workbench (3000) | Create dashboards and reports | Dashboard builder, semantic layer, scheduled reports |
| ML Engineer | ML Workbench (3001) | Train and deploy ML models | Experiment tracking, model registry, distributed training |
| Agentic User | Agentic Workbench (3003) | Ask questions in natural language | Conversational analytics, text-to-SQL, AI agents |
| Platform Admin | Control Plane UI (3004) | Manage tenants and infrastructure | Tenant provisioning, monitoring, configuration |
| Executive | BI Workbench (3000) | Consume insights and KPIs | Pre-built dashboards, natural language queries, alerts |
The Conversational Interface
While each persona has a specialized workbench, the conversational AI interface is accessible from every workbench. This means that any user can ask a natural language question and receive a data-driven answer, regardless of their technical proficiency.
Any Workbench
|
v
Conversational AI Panel
|
+-- "What was revenue last quarter?"
+-- "Show me the top 10 customers by spend"
+-- "Create a chart comparing Q1 vs Q2 sales"
+-- "Why did the pipeline fail last night?"
|
v
AI Agent Orchestrator --> SQL Generation --> Query Execution --> VisualizationThe conversational interface adapts its behavior based on the persona. A Data Engineer asking about pipeline failures receives technical diagnostics, while an Executive asking about revenue trends receives a summary with a chart.
Persona-Workbench Mapping
Each workbench is a standalone React/TypeScript/Vite application designed for a specific persona's workflow:
| Workbench | Port | Primary Persona | Secondary Personas |
|---|---|---|---|
| BI Workbench | 3000 | BI Developer | Executive, Agentic User |
| ML Workbench | 3001 | ML Engineer | Data Engineer |
| Data Workbench | 3002 | Data Engineer | BI Developer |
| Agentic Workbench | 3003 | Agentic User | All personas |
| Control Plane UI | 3004 | Platform Admin | -- |
| Data Plane UI | 3005 | Platform Admin | Data Engineer |
Cross-Persona Collaboration
The platform enables collaboration across persona boundaries through shared artifacts:
| Artifact | Created By | Used By |
|---|---|---|
| Dashboards | BI Developer | Executive, Agentic User |
| Semantic models | BI Developer | AI Service, ML Engineer |
| Data pipelines | Data Engineer | BI Developer, ML Engineer |
| ML models | ML Engineer | BI Developer (predictions in dashboards) |
| Data quality rules | Data Engineer | Governance, BI Developer |
| Saved queries | Any persona | All personas |
Reading Guide
Each persona page in this section follows a consistent structure:
- Role description -- Who this persona is and what they do
- Day-in-the-life workflow -- A typical workday using the platform
- Key capabilities -- The platform features most relevant to this persona
- Workbench overview -- The primary UI and its key screens
- Related chapters -- Where to find implementation details
Select your persona from the list below to see your tailored guide: