{"id":10311,"date":"2025-09-17T11:59:28","date_gmt":"2025-09-17T03:59:28","guid":{"rendered":"https:\/\/www.salesforce.com\/?p=10311"},"modified":"2025-09-17T11:59:30","modified_gmt":"2025-09-17T03:59:30","slug":"is-your-data-ready-for-agents-5-ways-to-tell","status":"publish","type":"post","link":"https:\/\/www.salesforce.com\/ap\/blog\/is-your-data-ready-for-agents-5-ways-to-tell\/","title":{"rendered":"Is Your Data Ready for Agents? 5 Ways To Tell"},"content":{"rendered":"\n

Everyone loves a shiny new object, especially when that object is an AI agent. But before you plunge headfirst into an agent, let\u2019s ask an unsexy question: Where do you stand with your data readiness?  <\/p>\n\n\n\n

The truth is, your agent will be only as good as your data. Think of your data like the foundation of your house. It\u2019s what everything else is built on. Would you invest in a state-of-the-art kitchen if your foundation was crumbling or you had no foundation at all?\u00a0 Yet many companies rush to invest in agents without considering the state of their data.\u00a0Or they implement an\u00a0artificial intelligence<\/a>\u00a0(AI) agent only to find it doesn\u2019t work as well as they\u2019d like (again, see: data).\u00a0\u00a0<\/p>\n\n\n\n

A recent survey<\/a> shows that 90% of high-level data professionals believe company leaders are not paying enough attention to bad or inadequate data. Meanwhile, a report<\/a> by IT consulting firm Capgemini found that fewer than one in five companies has a high level of data readiness, with only 9% fully prepared for the data integration and interoperability required for AI. <\/p>\n\n\n\n

\u201cAn AI strategy without a data framework is just a wish list,\u201d said Kuber Sharma, director of product marketing for Tableau at Salesforce. \u201cAttempting to deploy AI agents without one leads to inconsistent results, security risks, and a lack of user trust.\u201d <\/p>\n\n\n\n

But how do you know if your data is good enough? Read on to see if your data is in shape for an AI agent \u2014 and where you are on the data maturity spectrum. <\/p>\n\n\n\n

What is good enough data?<\/h2>\n\n\n\n

Before assessing your readiness, it helps to understand what it means for your data to be \u201cgood enough.\u201d <\/p>\n\n\n\n

The simple definition: It means that your data is high quality and usable enough for the agent to do its job. But doesn\u2019t mean that your data needs to be perfect or that you need to clean all <\/em>of your data \u2014 only what the agent needs to execute its tasks. <\/p>\n\n\n\n

To do this, first identify the business problem you want an agent to solve. Then, identify the data the agent needs. If, for example, your agent will handle\u00a0customer service<\/a>, it probably needs data on your company\u2019s products, shipping information, and return policies. But it won\u2019t need your annual report or quarterly earnings readouts, or data about your workforce.\u00a0<\/p>\n\n\n\n

The data needs to be\u00a0organised\u00a0in a way that your agent can easily access and use. And you only need\u00a0enough good data<\/a>\u00a0to get the agent started. For example, if you want your agent to handle questions about products to start, make sure it has\u00a0well-organised\u00a0product data. As you expand its tasks to handle returns and exchanges, you can then clean up the data for those policies. Working with an agent is an ongoing process; you can modify and make improvements over time.<\/p>\n\n\n\n

Data readiness questions you need to ask<\/h2>\n\n\n\n

When Sharma talks to customers, he helps them assess data readiness by sharing this checklist of questions: <\/p>\n\n\n\n

1. Is your data unified and\u00a0harmonised?\u00a0<\/h3>\n\n\n\n

Put simply, is there one place where your agent can find all your data? Or is the data siloed and scattered across the company? \u201cIf your data is fragmented, the agent will deliver fragmented and inconsistent experiences,\u201d Sharma said. <\/p>\n\n\n\n

Your first order of business is to unify your data.\u00a0Data Cloud<\/a>, the Salesforce platform that gives agents instant access to all the data across your\u00a0organisation, can help. Data Cloud unifies data \u2014 whether it\u2019s stored in Sales Cloud, Service Cloud, Marketing Cloud, Commerce Cloud, or external systems like data warehouses and data lakes \u2014 into a single, coherent profile.\u00a0<\/p>\n\n\n\n

But your data also needs to be\u00a0\u201charmonised.\u201d In other words, it needs to be in a\u00a0standardised\u00a0format. The United States, for example, might be referred to as \u201cUSA\u201d in one place, but as the \u201cU.S.\u201d or \u201cUnited States\u201d in others. When you\u00a0standardised\u00a0formats across all your data, it becomes easier for your agent to understand and use.\u00a0<\/p>\n\n\n\n

2. Have you resolved identities and is the information up to date?  <\/h3>\n\n\n\n

Even after all your data is unified, you may still have multiple entries for each individual customer. Maria Gonzalez, for example, could have several different profiles: one with the name of M. Gonzalez, another under her full name, and a third in which she\u2019s identified by her email address only. <\/p>\n\n\n\n

If you want data to be ready for an agent, these duplicate records need to be merged to create a single profile for each customer. Salesforce has a tool called\u00a0Identity Resolution<\/a>\u00a0that can perform this task.\u00a0<\/p>\n\n\n\n

You also want to make sure everything\u2019s up to date. Is Maria Gonzalez\u2019s email correct? Do you know which products she\u2019s using now? Your data team may need to check this manually. But clean, updated data helps your agent perform well. Old, incorrect data can lead to frustrating experiences for customers and unreliable outcomes like hallucinations. <\/p>\n\n\n\n

3. Do you have clear data governance policies in place and is your data secure? <\/h3>\n\n\n\n

Customer trust is key to deploying an AI agent successfully. And to create trust, your agent needs clear rules. You should be in compliance with local regulations, such as the\u00a0CCPA<\/a>\u00a0(California\u2019s data protection law) or the\u00a0GDPR<\/a>\u00a0(the European Union\u2019s regulations). You also need a\u00a0data governance framework<\/a>, or a clear policy for data quality, security, and access.<\/p>\n\n\n\n

An important part of this framework is making sure your data is secure. That\u2019s one of the advantages of Data Cloud, which is secured by Salesforce\u2019s\u00a0Einstein Trust Layer<\/a>; it automatically masks sensitive data and blocks information from being stored by external LLMs.\u00a0<\/p>\n\n\n\n

You also want your agent to only have access to the data it needs to do its job. An agent that\u2019s scheduling appointments in a\u00a0clinical setting, for example, should not have access to private or sensitive information about a patient\u2019s health.\u00a0\u00a0<\/p>\n\n\n\n

4. Can you activate your data in real time? <\/h3>\n\n\n\n

This is probably the most action-based of all Sharma\u2019s questions. In simplest terms, it means, is your data ready for immediate use in workflows? Can you use it to power real-time action? <\/p>\n\n\n\n

The only way to answer is to experiment. After you\u2019ve set up your agent, feed it some data and see if it can take the action you want. For example, if you have a customer service agent, see if it can access your data about returns and issue a shipping label. <\/p>\n\n\n\n

You may also want your agent to proactively make recommendations to customers. Sharma pointed to a few large, successful companies that do this well. \u201cWhen I order a matcha latte at Starbucks on my phone, I immediately get a message, \u2018Have you tried the matcha cookie as well?\u2019\u2019\u2019 he said. \u201cOr when you order shoes on Amazon, they usually follow up with a \u2018You forgot socks, dude.\u2019\u201d If you want your agent to do the same, load it with the data it needs and see if it prompts customers with recommendations. <\/p>\n\n\n\n

5. Have you established a feedback loop? <\/h3>\n\n\n\n

As much as you might want to \u201cset and forget\u201d your agent, well \u2026 you can\u2019t.  Agents need humans in the loop to make sure they\u2019re doing their job. Ask yourself: What systems do you have in place to test your agent? How can you monitor your agent\u2019s performance and make changes if necessary? <\/p>\n\n\n\n

Salesforce\u2019s\u00a0Agentforce Command\u00a0Centre<\/a>\u00a0can help with this. It\u2019s a first-of-its kind\u00a0observability tool<\/a>\u00a0designed to evaluate AI agent activity and help you figure out where you need to make improvements. But no matter which tool you use, you need some type of system in place to check if your agent has the data it needs and is accessing it correctly.\u00a0<\/p>\n\n\n\n

Salesforce\u2019s AI Readiness Assessment<\/a> tool can also give you a good idea of whether you\u2019re ready for an agent. <\/p>\n\n\n\n

\n\t
\n\n\t\t
\n\t\t\t

Download Essential Data Sources Worksheet<\/h2>\n\t\t\t\t\t\t\t

For each data source your agents will need, score its readiness from 1 (needs significant improvement) to 3 (well established). Identify an action to prepare this data for implementing AI agents, and assign an accountability owner.<\/p>\n\t\t\t\n\t\t\t\n\t\t\t\t\t\t\t

\n\t\t\t\t\tDownload<\/a>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\n\t\t
\n\t\t\t\t\t<\/div>\n\t<\/div>\n\n\t\t\t
<\/div>\n\t\n\t\t\t\n\t\t\"\"\n\n\t\t\n\t\t\t\t\t\"\"\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\t\t\t\"\"\n\t\t\n\t<\/div>\n\n\n\n

Where are you on the data maturity spectrum?<\/h2>\n\n\n\n

At the same time you\u2019re going through the checklist, you can see where you are on the data maturity spectrum with this list suggested by Sharma. Here\u2019s each stage of readiness on the road to deploying an agent:<\/p>\n\n\n\n

Crawl<\/h2>\n\n\n\n