Summary Fresh from Tableau Conference 2026, Fi and Sarah sit down with Kirk and Candi Munroe - co-founders of Paint with Data, a Tableau consultancy and Salesforce partner based in Canada - to unpack what's actually coming for Tableau and what it means for the people making decisions about their data teams. Kirk brings 25 years in business analytics, a newly minted Tableau Visionary title, as well as a Tableau Ambassador and a book on data modelling in Tableau. Candi is a Visual Analytics specialist, four-time Tableau User Group Ambassador, and heads up the Canada Tableau User Group. Between them, they've seen every era of Tableau - and they're genuinely excited about this one. The conversation covers Tableau Solve and its write-back and forecasting potential, the Viz layers that will let you layer multiple data sources on a single chart axis, composable data sources and why they're the missing piece in Tableau's semantic layer story, agentic analytics and what it actually takes to make natural language querying work in practice, Tableau MCP - including a cautionary tale about a CPM field that cost 58 cents a query - and what the Devs on Stage roadmap means for the data leaders who need to decide what comes next for their teams. Takeaways Tableau Solve productionises record-level triage and forecasting - and write-back is finally coming, with Kirk calling it "way, way, way overdue" Chart Layers will allow multiple data sources to sit on the same XY axis without any joining, opening up time series comparisons and complex formatting that previously required workarounds Tableau Server is getting genuine love - including LLM features - signalling that Tableau sees it as a long-term platform, not a migration waiting to happen Composable data sources let analysts extend a published data source on the fly without touching the original, and because everything is relationship-based, nothing already built gets broken Well-governed, well-commented data sources are now a prerequisite for agentic analytics - without them, the AI will guess wrong and cost you money (Kirk's CPM example is a must-hear) Tableau MCP is already live, easy to set up in Claude Desktop in under three minutes, and keeps row-level security intact - but you need your own personal access token, not a service account AI-assisted field descriptions get you 90-95% of the way there - the blank box problem is real, and the AI solves it The Tableau Desktop Authoring API is in its third release, and style guide automation - padding, corner rounding, colour palette - is close Headless BI and Slack-first data experiences are coming, and they matter most for the people who will never naturally log into Tableau Data leaders should position themselves as connective glue across departments - spotting correlations between silos that no single team can see Chapters 00:00 Introduction to Tableau Conference 2026 Highlights 01:52 Meet the Experts: Kirk and Candi 03:32 Exciting Announcements from TC26 05:40 Tableau Solve: Enhancements and Features 07:52 The Importance of Write-Back Functionality 09:31 Map and Chart Layers: A New Era in Visualization 11:51 Tableau Server vs. Tableau Cloud: The Future 13:19 Tab Move: Streamlining the Transition to Cloud 15:05 Accessibility Features in Tableau 15:18 Composable Data Sources: Unlocking New Potential 20:47 Optimizing Data Integration in Tableau 22:17 The Future of Composable Data Sources 24:22 Leveraging AI for Data Management 26:30 The Role of AI in Data Exploration 26:31 Understanding Agentic Analytics 29:52 Implementing Tableau MCP Effectively 34:24 Designing for Consistency in Data Visualization 36:54 Evolving Data Governance and Ethics 38:31 Exploring New Features in Tableau 39:08 The Future of Data Integration and Collaboration 48:26 Building a Data-Driven Organization 50:41 The Role of Data Leaders as Consultants Links Kirk Munroe on LinkedIn: https://www.linkedin.com/in/kirkmunroe/ Candi Munroe on LinkedIn: https://www.linkedin.com/in/candimunroe/ Paint with Data: https://paintwithdata.com Paint with Data Blog: https://www.paintwithdata.com/blog Data Modeling with Tableau by Kirk Munroe: https://www.amazon.com/Data-Modeling-Tableau-practical-building/dp/1803248025 Kirk Munroe on the Flerlage Twins blog: https://www.flerlagetwins.com/2023/01/data-.html TC26 Devs on Stage: https://www.salesforce.com/plus/experience/tableau_conference_2026/series/tableau_conference_2026_highlights/episode/episode-s1e25 Watch TC26 on demand: https://www.salesforce.com/plus/experience/tableau_conference_2026 Fi Crocker on LinkedIn: https://www.linkedin.com/in/ficrocker/ Sarah Burnett on LinkedIn: https://www.linkedin.com/in/sezbee/ Keywords Tableau Conference 2026, TC26, Tableau Solve, composable data sources, agentic analytics, Tableau MCP, Viz layers, chart layers, write-back Tableau, Tableau Visionary, data governance, Tableau Cloud, Tableau Server, AI in Tableau, semantic layer Tableau, data leadership, data leaders, Paint with Data, Kirk Munroe, Candi Munroe, Tableau data modelling, headless BI, Slack analytics, Tableau Desktop Authoring API, row-level security, Tableau prep, published data sources, Dub Dub Data, unDUBBED podcast