Tableau – Analytics & Visualization Expert (AI L2) — Tableau Prep | LOD & Calculations | Dashboards | Tableau Pulse | Einstein Copilot | Server / Cloud

Duration: 56 Hours
Target Level: L2 (Intermediate)
Delivery Mode: Classroom / Online (ILT)
AI Platform: Tableau AI (Pulse / Einstein) + Azure OpenAI

Course Overview

This course equips Data Engineering & Analytics professionals with core Tableau analytics and visualization skills and the AI layer required for L2 proficiency. It is designed for practitioners who already build dashboards and want to master data preparation, advanced calculations, and governed deployment alongside modern Gen AI capabilities — specifically Tableau AI (Tableau Pulse, Einstein Copilot) and Azure OpenAI applied to analytics workflows.

The course follows a learn-by-doing philosophy. Every module includes hands-on labs and flexible case study scenarios that trainers can adapt to their domain context.

L2 Outcome Statement

• Connect, prepare and model data using Tableau Prep and data-source best practices
• Build advanced visual analytics with LOD expressions, parameters and sets
• Author complex calculations, table calculations and analytics-extension models
• Implement governance: permissions, row-level security and content management on Server / Cloud
• Integrate Tableau AI (Pulse / Einstein Copilot) and Azure OpenAI into analytics workflows
• Contribute to internal analytics accelerators and AI-assisted POCs

Prerequisites

• 1–2 years of hands-on experience in a Tableau / BI / analytics role
• Working knowledge of Tableau Desktop (worksheets, dashboards, data sources)
• Basic data modelling concepts (joins, relationships, granularity)
• Basic SQL proficiency
• Understanding of reporting and ETL/ELT concepts

Helpful but not mandatory: Exposure to Tableau Prep and calculated fields/LOD expressions · Any Gen AI/LLM concept · Python or R basics (for analytics extensions)

Course Structure at a Glance

Analytics & Visualization modules build the platform foundation. Gen AI modules apply Tableau AI and Azure OpenAI in an analytics context. Both tracks run in sequence and are equally mandatory.

Detailed Course Modules

Part A — Tableau Analytics & Visualization Foundation

Module 1: Data Connectivity, Modelling & Preparation | 8 hrs

Topics Covered: Connecting (live vs extract, data federation, custom SQL) · Tableau data model (logical vs physical layer) · Joins, unions, blends, relationships · Tableau Prep Builder (flows, cleaning, pivoting) · Extract optimization and Hyper performance · Incremental extract refresh

Hands-On Labs: Build a Tableau Prep flow (clean, pivot, join → published .hyper extract) · Model relationships vs joins on a multi-table source · Configure incremental extract refresh on a published data source

Case Study: Design a governed published data source and preparation flow for standardizing analytics across multiple teams.

Module 2: Visual Analytics & Dashboard Design | 8 hrs

Topics Covered: Visual best practices (chart selection, pre-attentive attributes, colour) · Marks, encodings, dual axes · Parameters, sets, groups, bins · Dashboard actions (filter, highlight, parameter, navigation, URL) · Layout and performance · Viz-in-tooltip, drill-down, dynamic zone visibility

Hands-On Labs: Build an interactive dashboard with parameter and set actions · Implement dynamic zone visibility and viz-in-tooltip · Optimize a slow dashboard using the Performance Recorder

Case Study: Design a multi-view executive operations dashboard with guided analytics and interactivity.

Module 3: Advanced Calculations & Analytics | 8 hrs

Topics Covered: Calculated fields (aggregate vs row-level) · LOD expressions (FIXED/INCLUDE/EXCLUDE) · Table calculations (addressing, partitioning) · Forecasting, trend lines, clustering · Analytics extensions (TabPy/R) · Calculation performance

Hands-On Labs: Solve a cohort/retention problem using LOD + table calculations · Build a forecast + clustering view · Call a Python model via TabPy from a calculated field

Case Study: Design LOD and analytics-extension driven views for customer segmentation and churn-indicator analytics.

Module 4: Governance, Security & Enterprise Deployment | 6 hrs

Topics Covered: Tableau Server vs Cloud (sites, projects, content hierarchy) · Permissions model · Row-level security (user filters, entitlement tables, virtual connections) · Certified data sources, Data Management & lineage · Content migration & version control · Admin Insights monitoring

Hands-On Labs: Implement RLS using an entitlement table and user functions · Configure project permissions and certify a data source · Promote content across Dev → Prod using Content Migration Tool/REST API

Case Study: Design permissions, RLS, and certified sources for a BFSI org enforcing governed self-service analytics for audit.

Part B — Gen AI for Analysts

Module 5: AI Foundations for Analytics – Azure OpenAI & Tableau AI | 6 hrs

Topics Covered: Tableau AI overview (Einstein Copilot, Tableau Pulse, Einstein Trust Layer) · Azure OpenAI vs OpenAI API · Model catalogue relevance to analytics · Prompt design for analytics use cases · Token/cost management · Responsible AI (grounding, bias, Trust Layer)

Hands-On Labs: Deploy a GPT-4o model in Azure OpenAI and call via REST · Write a prompt that generates a Tableau calculation from a natural-language request · Explore Tableau AI feature prerequisites and licensing

Case Study: Build a prompt reading data source metadata and generating a business glossary for auto-documentation.

Module 6: Tableau Pulse & Einstein Copilot for Analysts | 6 hrs

Topics Covered: Tableau Pulse (metrics layer, automated insights, digests) · Einstein Copilot (NL → viz, calculation assistance) · Prepping data sources/metrics for AI performance · Natural-language data exploration · Insight narratives and anomaly explanations · Governance and trust for AI-generated insights

Hands-On Labs: Define metrics in Tableau Pulse and review automated insights · Use Einstein Copilot to generate a calculation + viz from natural language · Curate metadata to improve AI insight quality

Case Study: Design a Pulse metrics layer and Copilot-ready data source for self-service NL analytics and metric monitoring.

Module 7: Embeddings, NL Q&A & RAG over Analytics Content | 8 hrs

Topics Covered: Embeddings (semantic vs keyword search) · Vector stores (Azure AI Search/pgvector) · Chunking strategies for dashboard specs and data dictionaries · RAG architecture · Surfacing RAG answers alongside Tableau (Extensions API) · Evaluating RAG (precision@k, faithfulness, citation tracking)

Hands-On Labs: Generate embeddings for a data-dictionary + dashboard-spec corpus · Build a RAG flow (docs → vector store → Azure OpenAI → grounded answer) · Surface the assistant via a Tableau dashboard extension

Case Study: Design a RAG system handling 500+ docs and metric definitions for an “Ask the analytics” assistant over Tableau content and glossary.

Module 8: AI-Augmented Analytics, Deployment & Monitoring | 6 hrs

Topics Covered: Surfacing LLM/AI outputs into dashboards (Extensions API, write-back) · AI-enriched fields feeding views · Embedding Copilot/RAG assistants (Tableau Embedding API) · Deployment and promotion · Monitoring (Admin Insights, usage, AI feature governance) · Cost and quota governance

Hands-On Labs: Surface AI-enriched fields into a dashboard · Promote the AI-assisted workbook Dev → Prod · Set up monitoring for usage, performance and AI features

Case Study: Productionize a governed data source + Pulse/Copilot + RAG + deployment as a capstone integrating all prior modules.

Tools & Environment

• Tableau Desktop
• Tableau Prep Builder
• Tableau Server / Cloud
• Tableau Pulse / Einstein
• TabPy / Rserve
• Azure OpenAI
• Azure AI Search
• VS Code + Python + Git