The independent daily for Salesforce admins, developers and architects

Curated by Abhinav (opens in a new tab)

Must-read

Six practices for taking Tableau MCP agents from prototype to production (opens in a new tab)

You will learn how to prepare a Tableau data model for agents, scope their tools and data, and build a test and monitoring harness before agents reach end users.

Why read this

The post draws on a regulated-industry customer deployment.

  1. Prepare the data model
  2. Define the agent's role
  3. Follow least privilege
  4. Load metadata into the prompt (optional)
  5. Pre-build queries for known questions
  6. Build evaluation and monitoring
Six practices for moving a Tableau MCP agent from prototype to production, in order

The post describes a large enterprise customer in a regulated industry that moved from Tableau dashboards to custom agents built on Tableau MCP. Off-the-shelf Tableau agents were too broad for the customer, who needed specialized workflows, agents that could act on results, embedding in a purpose-built application, and fine-grained control. Custom agents bring more need for testing, governance and monitoring, so the authors set out six practices.

The first is to prepare the data model. Business logic should live as close to the data as possible: calculated fields for fixed logic, Tableau Knowledge business preferences or field descriptions for logic shared across agents, and agent system instructions for logic specific to one agent. Teams should also remove duplicate fields, describe fields with units and caveats, name them in business terms, hide irrelevant fields and certify the data sources. The TDS Edit API, available in Tableau Cloud from October 2026 and Tableau Server 2026.3, lets teams add field descriptions in code.

The second is to define the agent’s role by answering what problem it solves, which domain it serves, what it can and cannot answer, and how it should respond. The answers shape its data, tools and system prompt. Tableau MCP now supports embedded data sources in 2026.3.

The third is to apply least privilege. The authors removed tools the agent did not need, starting with list-datasources, and pinned the agent to an approved data source ID. Tool scoping is set through environment variables on self-hosted deployments or site settings on hosted Tableau Cloud, and embedded data sources are scoped by project or tag.

The fourth, optional, practice is to load metadata into the system prompt at session start. This removed the get-datasource-metadata call and cut response time by almost 50 percent. The authors warn that this suits agents with one or two data sources and that stale metadata is a risk if schemas change often.

The fifth is to pre-build queries for frequent questions and expose them as custom tools, so the model only explains results. The authors advise against chasing perfect accuracy for open-ended questions, and suggest dashboards for figures that must be exact.

The sixth is an evaluation and monitoring framework: a question bank with correct answers, including refusals, run against each prompt, model and setting version, with LLM-as-a-judge grading for less deterministic answers, release-style versioning, production monitoring of latency, tokens and failures, and a regular review that adds new questions. The authors recommend an established agent observability platform, and they name LangSmith as an evaluation tool they used.

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

Worth reading?

Informatica adds governed enterprise data to Copilot, Foundry and Fabric (opens in a new tab)

You will learn what Informatica's Microsoft integrations now provide: Copilot access to business context, MCP-based governance for Foundry agents, and broader Fabric lineage scanning.

Why read this

You will also see the new U.S. East Coast Azure deployment option and what is generally available.

  1. Informatica governance and lineage data
  2. Headless MCP servers and scanners
  3. Microsoft Copilot, Foundry and Fabric
  4. Governed AI agents and analytics
How Informatica trusted data reaches Copilot, Foundry and Fabric agents

Informatica from Salesforce has expanded its collaboration with Microsoft, announced at Microsoft Ignite 2026. The integration brings Informatica’s enterprise data intelligence into Microsoft Copilot and Teams, giving business users access to business definitions, data quality, governance and lineage through natural-language experiences. The article presents this as a response to the gap between agents that can access data and agents that understand it and operate within access policies.

For AI developers, the integration with Microsoft Foundry extends Informatica Headless MCP servers, which reached general availability earlier, with new governance, identity and administrative capabilities. These let developers ground agents in authoritative definitions, quality indicators and lineage, apply access controls, and trace agent interactions with data management services. Informatica’s MCP services are also being expanded across Azure-based IDMC points of delivery worldwide.

For data engineers and analysts on Fabric, Informatica’s scanners now cover notebooks and data pipelines as well as data at rest. The enhanced scanners provide lineage across multistep pipeline orchestrations, support impact analysis, and are administered through a consolidated interface. The article also announces a new U.S. East Coast Azure point of delivery for customers with data residency or procurement requirements, and notes that Informatica purchases through Microsoft Marketplace can count toward a Microsoft Azure Consumption Commitment.

Availability is staggered: the Copilot integration is generally available, the Foundry MCP server integration is generally available with its expanded capabilities, the Fabric scanners are generally available for notebooks and pipelines, and the Azure U.S. East IDMC point of delivery is generally available. The piece is largely promotional, with customer and executive quotes, so the technical detail on the MCP governance features is thin.

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

Also told by Salesforce Time (opens in a new tab)

Worth reading?