The independent daily for Salesforce admins, developers and architects

Curated by Abhinav (opens in a new tab)

Tableau Data Apps bring governed agentic analytics to vibe-coded apps (opens in a new tab)

You will learn what a Tableau Data App is, where it can be built and published, and how it inherits Tableau's security, semantics and refresh model.

Why read this

The piece is a product overview in beta, so the detail on setup is thin.

  1. Connect your agent via MCP
  2. Prompt your intent
  3. Preview, iterate and verify
  4. Publish and share
The four steps to get a Tableau Data App from prompt to shared link

Tableau Data Apps, now in beta, are custom interactive analytical web apps hosted and powered by the Tableau platform. They separate the visual front end from the query engine, so builders can use AI agents to produce apps quickly while the apps still draw on Tableau’s semantics, connectivity and governance. The article argues that visualization was never the hard part, and that without an analytics platform agent-built apps risk guessing at business definitions, running slow and costly query loops, and leaking credentials or data.

Apps can be built in Tableau Studio or with any third-party agent connected through the Tableau MCP server or Tableau Next MCP server. Apps built in Tableau Studio publish to Tableau Cloud or Server, while apps built with third-party agents can publish to Tableau Cloud, Server or Tableau Next. Inside Tableau Cloud and Server, apps sit in workbooks and query Published or Embedded Data Sources, and in Tableau Next they sit in workspaces and use Tableau Semantics.

Data freshness comes from live connections or scheduled extract refreshes, and federated queries let apps reach heterogeneous sources without copying data. Database credentials stay in Tableau, and object-level and row-level security apply to every user. The getting-started steps are to connect an agent, prompt the intent, preview and verify the logic, then publish and share.

Read the original at Salesforce Blog (opens in a new tab)

Worth reading?

Recommended

Setting up proactive Intelligence in Tableau Next with Slack and MCP (opens in a new tab)

You will learn the setup path for Tableau Next's three proactive features: autonomous insights, data alerts and intelligence briefs.

Why read this

You will also see how admins scope agents and users, and how alerts are created and managed through Slackbot.

  1. Set up Tableau Agent in Tableau Next
  2. Connect Slack to Salesforce
  3. Enable Tableau Next MCP server for Slackbot
The one-time admin setup that connects Tableau Next to Slack and MCP

Proactive Intelligence in Tableau Next has Tableau Agent monitor business data in the background and push prioritized insights to Slack, Salesforce or any MCP-compatible client. The article describes three capabilities that work together: autonomous insights, which explore data for risks nobody thought to ask about; data alerts, which notify on conditions such as a commit drop or a large deal slipping; and intelligence briefs, which run scheduled or on-demand reviews of core KPIs. All three draw on the governed semantic model so calculations follow the organisation’s definitions.

Setup is a one-time admin task. Prerequisites are Tableau Next in Enterprise, Performance or Unlimited edition, at least one AI-ready semantic data model, and Slack with the Salesforce app and Slackbot connected to MCP. The admin sets up a Tableau Agent, connects Slack to Salesforce, and enables the Tableau Next MCP server for Slackbot. For autonomous insights, the admin turns on the feature under Administration settings, scopes the agent to semantic models, creates an Agentforce Studio skill that supplies business context without scripting output, grants the AI Skill User Permission Set, and assigns an agent to each user, since no one receives insights until that step is done.

Alerts can be created in plain language through Slackbot, or through built-in metric alert types such as period-over-period change, unusual change, goal and threshold. Alerts check daily or weekly and notify only when the condition is met. The article recommends a phased rollout: start with one key alert, pilot autonomous insights with a small group of leaders, then automate one recurring review with an intelligence brief.

Read the original at Salesforce Blog (opens in a new tab)

Worth reading?