Category

Data Management

Several data breaches affecting a wide range of companies that use Salesforce have been reported in recent weeks. These incidents have impacted organizations across various sectors, including technology, retail, and insurance. The exposed data has varied by victim but has commonly included customer contact information, internal business records, and even sensitive data like API tokens and credentials.

Sercante clients can be assured that our systems have not been impacted by these recent attacks, however we want to make sure that Salesforce customers are aware of these incidents and are equipped to safeguard their instances.

How the Breaches Occurred

The recent breaches are not due to a vulnerability within the Salesforce Core platform itself. Instead, threat actors have used sophisticated social engineering and supply chain attacks to gain unauthorized access. 

One common method has been targeted voice phishing (vishing) campaigns. In these attacks, bad actors impersonated legitimate employees or IT support staff to trick victims into downloading a malicious replica of Data Loader and granting access to their Salesforce environments.

In a recent and widespread campaign, attackers leveraged compromised OAuth tokens for a third-party application, Salesloft Drift. By exploiting the integration between the app and Salesforce, the threat actors were able to export large volumes of data and credentials from numerous corporate Salesforce instances in what is called a “supply-chain attack”. . The attackers were able to steal “digital keys,” or authentication tokens, from the Drift app. They then used these stolen keys to access and steal data and credentials like passwords, API keys, and access tokens for other services that could be used to compromise other systems integrated with Salesforce.  

This highlights a critical risk: while the core platform may be secure, its connections to third-party apps can introduce vulnerabilities.

Risk to Salesforce Customers

The primary risk to Salesforce customers lies in the potential for stolen data to be used for further attacks. Customer contact information and other details can be weaponized in targeted and highly convincing phishing and social engineering campaigns to gain access to other corporate systems. The exposure of sensitive information like API tokens and credentials poses a significant threat, as it can be used to compromise connected systems, such as other cloud platforms or internal networks.

UPDATE: If you are a Drift customer – Salesloft has announced plans to shut down its Drift chatbot following their recent security breaches. This no doubt presents a challenge to your website engagement strategy.  The Sercante team is well-versed in the various conversational platforms that integrate seamlessly with Salesforce and can help you navigate this transition.

Recommended Actions for Protection

While Salesforce has taken steps to restrict the use of “uninstalled connected apps”, customers should take steps to protect themselves from similar threats:

  • Reauthenticate Drift Connections: Salesloft Drift customers will need to reauthenticate their Salesforce integration with Drift. It’s also advised that any and all authentication tokens stored in or connected to the Drift platform should be considered potentially compromised and update them immediately. 
  • Rotate all credentials and keys: Immediately change any passwords, API keys, and other access tokens that were stored in your Salesforce instance
  • Investigate your Salesforce account: Look for any unusual activity in your Salesforce login history, audit trails, and API access logs from early to mid-August 2025. Look for suspicious logins or data access patterns, particularly from the user account associated with the Drift integration.
  • Audit Third-Party Apps: Audit your connected apps to make sure they are secure, and make sure that all third-party apps connected to your Salesforce account have only the minimum permissions they need to do their job and revoke access for any app that is no longer in use.
  • Secure APIs and Integrations: When configuring new integrations, restrict API access by defining trusted IP ranges and ensuring that connected apps have the most restrictive scope possible.
  • Apply the Principle of Least Privilege: Limit user permissions to only what is necessary for their job role. Restrict administrative access and minimize the use of permissions like “Modify All Data.”
  • Be on high alert for phishing: Warn your employees to be extra cautious about any unexpected or unusual emails, phone calls, or messages. The attackers may use the stolen contact information to try and trick people into giving up more sensitive data.
  • Rinse & Repeat: Security isn’t a set it and forget it function. It takes constant and consistent vigilance to protect your systems and data. 

While the core Salesforce platform is secure, recent data breaches are a reminder that a company’s security is only as strong as its weakest link, which is often a third-party app or a human being. To stay safe, you have to be proactive. By using strong security practices, enforcing strict access rules, and training your team, you can drastically improve your defenses. Ultimately, keeping your data safe is a team effort—you, Salesforce, and all of your employees have a role to play.

If you’d like a guide to help you navigate how to optimize data protection in your organization with Salesforce, reach out to the Sercante team. Our experts can be your guide for impactful next steps.

Student retention is one of the most pressing challenges in higher education—and it’s not just about keeping enrollment numbers up. It’s about making sure students feel supported, connected, and confident in their ability to succeed, and engaging them before it’s too late.

Almost a quarter, 22.3%, of first-time, full-time undergraduate freshmen drop out within the first 12 months, while 39% don’t complete their degree within eight years (Education Data Initiative). 

Which is why it is imperative for institutions to be taking action to improve student retention. One of the ways they can is by maximizing the technology they have and tapping into the latest solutions available to gain a better view of their students’ journeys and take action to engage when it matters most.

In Sercante’s latest demo, we explored how Salesforce’s connected tech stack—featuring Data Cloud, Marketing Cloud Advanced, and Agentforce can empower institutions to identify and support at-risk students before they fall through the cracks.

In the demo, we followed the journey of Jason Smith, a sophomore whose profile revealed a 77% attrition risk. What followed is a case study in how smarter tech, working harder behind the scenes, can drive real results for both teams and students.

Unifying Student Data for Smarter Insights

Everything begins with data. Using Salesforce Data Cloud, we created a Unified Student Profile by integrating key data sources across systems: academic performance, course engagement, attendance patterns, and more.

This holistic view powered a propensity model that flagged Jason’s risk level at 77%. Instead of relying on gut instinct or outdated reports, the team now had real-time, actionable insight—and a clear signal that it was time to act.

A screenshot of Jason Smith's student profile showing the attrition risk at 77%.

From Insight to Action with Marketing Cloud Advanced

That’s where Marketing Cloud Advanced comes in. Once a student is identified as at-risk, every minute matters. This tool enabled us to build automated, personalized communication journeys, so students like Jason could receive the right message at the right time.

Jason’s message came from Sercante University: a friendly, timely nudge to connect with an advisor. And because it was based on real-time data from his unified profile, it felt relevant, not random.

A Seamless Path to Support with Agentforce

The magic moment? When Jason clicked the link and landed on a scheduling page powered by Agentforce.

Here’s where tech meets empathy. Agentforce’s AI assistant recognized Jason’s concerns about unavailable classes and provided instant, personalized guidance—helping him book an appointment with an advisor in just three clicks or less.

No back-and-forth emails. No waiting. No frustration. Just a frictionless experience that made Jason feel seen, supported, and empowered to move forward.

A Multi-Cloud Solution that Improves Student Retention

What made this work wasn’t just the data or automation—it was how these tools worked together to create a better experience for both students and staff.

  • For teams: The heavy lifting was handled behind the scenes. With Data Cloud pulling real-time insights, MC Advanced automating outreach, and Agentforce handling the scheduling, advisors could spend less time triaging and more time supporting.
  • For students: It felt easy, human, and personalized. Jason didn’t need to fight for support—it found him, right when he needed it. He got help fast, with minimal effort and instant gratification.

This Agentforce, Data Cloud, and Marketing Cloud Advanced, multi-cloud solution, is an example of when teams use the power of data and AI to engage their students when it matters most, before it’s too late. Intercepting more students like Jason can help institutions improve student retention while creating real connections that last to drive growth for the institution and in Jason’s educational journey.

Final Takeaway

When schools bring together data, automation, and AI, they unlock a more connected, proactive, and student-centered approach to retention.

  • Students feel seen, supported, and confident in what to do next
  • Teams get relief from manual processes and can focus on what matters most
  • Institutions see better outcomes—without burning out their staff

It’s not just about reducing attrition—it’s about building trust, creating moments that matter, and delivering an experience that helps every student thrive.

Want to see the full journey? Watch the demo here

Looking to implement something similar at your institution? Reach out to the Sercante team.

Product Note: Marketing Cloud Growth and Advanced are editions of Marketing Cloud Next and have also been referred to as Agentforce Marketing.

Marketing Cloud Growth/Advanced (aka Next Gen Marketing Cloud) is built to leverage the power of Data Cloud, giving marketers key benefits like unified customer profiles, enhanced segmentation, cross-object personalization, and calculated insights. However, these capabilities come with a cost in the form of Data Cloud credit consumption. In this post, we’ll review several tips to help you maximize the benefits of Data Cloud without breaking the bank.

Introduction to Data Cloud Credits

Before we start talking about conserving credits, let’s take a look at what they are and what actions use them.

What Are Data Cloud Credits?

Salesforce defines Data Cloud Credits as “digital currency that you use to pay for Data Cloud services.” These credits are consumption-based, meaning you only pay for what you use. Use a little, pay a little. Use a lot, pay a lot. 

Credit use is calculated by multiplying the number of units consumed for each usage type by the corresponding multiplier from the rate card. Usage types include Data Services, Data Storage, Einstein Requests, and Segment Activations. Usage can be monitored in the Digital Wallet included in your Salesforce org.

The key takeaway is that credits are a valuable resource, and every action comes with a related cost. The goal is not to scare marketers or discourage credit usage. It’s to encourage smart, intentional use to ensure that each credit delivers value.

Here are some great resources if you would like to learn more about these topics.

Tips for Optimizing Your Data Cloud Credit Usage

Tip #1 – Apply Filters to Data Streams

Identity resolution rules are one of the largest consumers of Data Cloud credits. They use Data Service credits to create the unified individual records required for Marketing Cloud Growth/Advanced. This process is essential and must be activated. But it can be optimized.

Save Credits with Filters 

Identity resolution rules link data from multiple data sources into unified individual records. Credit consumption is based on the total number of records that Data Cloud reviews when unifying the records. Credits can be conserved by applying filters to the data streams to limit the number of records being used in the identity resolution process.

Example:

If your lead data stream contains 1M records and your contact data stream includes 500K records, 1.5M records will be used in the creation of the unified individual records. Data filters can be applied to limit the number of records used in the identity resolution process by focusing on only records that should be included in your marketing activities.

Applying Data Filters 

Data filters can be applied in two ways:

  1. When Ingesting: By adding a filter to the data streams
  2. After Ingestion: By applying a filter to the data lake object (DLO) in the data space (Marketing Cloud uses the default data space)


The filters will impact the system processes like unification, segmentation, and CI, but will not impact the total number in the data stream.

Example:
There are 6,088 total records in the lead data stream (and let’s say that 2,500 are from the USA). If you apply a filter for Country = USA, the total record count in the data stream stays the same (6,088), but only the 2,500 records from the USA will be used in system processes (including identity resolution).  This reduces the data being evaluated to only leads in the USA and will reduce credit consumption.

A screenshot of recently viewed data streams in Data Cloud.
A screenshot in Data Cloud showing how to edit the filter in a data stream to only include records whose country equals USA.


The great thing about filters is that they help save credits across multiple areas. They reduce credit usage in identity resolution and also limit the number of records evaluated in processes like segmentation and calculated insights. This saves you even more.

Tip #2 – Audit Refresh Schedules

Credits are consumed when data is refreshed in Data Cloud. This includes data streams, data graphs, calculated insights, identity resolution rules, and segments. 

Data Streams
Data streams based on Salesforce data refresh every 15 minutes by default and upsert with new or changed records. Manual updates can also be triggered if needed. Data ingested from other sources can be scheduled to run hourly or daily, so it’s worth taking a look at their schedules.

If you find the data is being refreshed hourly, consider the frequency that the data is actually updating (in the data source being ingested) and the “freshness” that’s needed in your marketing activities. Hourly refreshes make sense for data that changes frequently and is used in time-sensitive communications. In other cases, daily refreshes might meet your business needs and they would save credits.

Data Graphs
Data graphs are used for personalization and dynamic content, and refresh daily by default. The refresh interval can be updated by navigating to the data graph in Data Cloud and selecting the “Schedule” option from the dropdown (under the ▼icon).

More frequent refresh intervals mean “fresher” data, but will use more credits. I recommend sticking with the daily refresh option and adjusting based on your needs. Remember, manual refreshes can also be triggered if needed.

A screenshot of the Refresh Interval drop down setting to set your Data Graph's refresh schedule.

Identity Resolution
Identity Resolution rules run daily and the schedule can’t be changed. The rules will run once every 24 hours and the time of day might vary based on your org and the amount of data being processed. Manual refreshes can be triggered by navigating to the rule and clicking the “Run Ruleset” button.

The only real optimization for identity resolution is limiting the number of records processed (by applying filters) as discussed in the first tip.

Segments
Segment refresh schedules are the primary way that marketing teams can reduce Data Cloud credit consumption. When creating a segment, the Standard Publish option offers the following refresh schedules:

  • Don’t refresh
  • 12 hours
  • 24 hours


I recommend choosing “Don’t refresh” unless there’s a defined need to refresh more frequently. This ensures segments aren’t needlessly refreshing—and burning credits unnecessarily.

Make sure your segments are still up to date before sending emails by selecting the “Immediately before running this flow” refresh option in your segment-triggered flow. This guarantees your email targets the most current segment population, without incurring extra credit usage from scheduled refreshes.

A screenshot showing toggling on "Immediately before running this flow" for the setting for "When do you want to republish this segment?"

Tip #3 – Be Selective

Data storage is another factor to consider when evaluating credit consumption. When ingesting data into Data Cloud, start with a minimalist mindset. Ask yourself the following questions when deciding which fields to include:

  • Is this field needed for identity resolution?
  • Is this field needed to support marketing efforts (ex. dynamic content, personalization, segmentation)?
  • Is this field used in calculated insights?

If the answer to these questions is “no,” hold off on ingesting the field to reduce unnecessary data storage. If a new use case arises later, the field can always be added to the data stream.

How to add a field to an existing data stream 

  1. Confirm the Data Cloud Salesforce Connector has read access to the field.
    • Permission Sets > Data Cloud Salesforce Connector > Object Settings
      • Navigate to the object that contains the field and verify the “Read Access” box is checked
  2. In Data Cloud, select the Data Streams tab and the data stream related to the object where the field is located.
  3. Click the “Add Source Fields” button from the selected data stream.
  4. Select the field (or fields) from the table and save.
  5. Click the “Review” button in the Data Mapping section and map the fields from the data lake object to the data model object (you might need to create new custom fields).

Make the Most of Your Credits 

Data Cloud credits are a valuable resource and should be managed accordingly. With a little bit of planning and some regular audits, you can make the most of your credits and take full advantage of the AI, calculated insights, personalization, and segmentation capabilities of Marketing Cloud Growth/Advanced.

If you have questions about Data Cloud or Marketing Cloud Growth/Advanced reach out to the Sercante team or leave us a comment. 

Product Note: Marketing Cloud Growth and Advanced are editions of Marketing Cloud Next and have also been referred to as Agentforce Marketing.

Marketing Cloud Growth and Advanced Edition (aka Marketing Cloud on Core or just Marketing Cloud) offers incredible capabilities to marketers in so many areas. From AI powered segmentation, scheduling and sending SMS in a nurture campaign, and unprecedented abilities to tailor your marketing content to the audience viewing it, Marketing Cloud Growth and Advanced Edition can help marketing teams large and small automate their marketing efforts. All of these amazing capabilities rely on the power of one key feature of Data Cloud – the Data Graph

Data Graphs allow you to combine and transform data from multiple Data Cloud Data Model Objects (DMOs) into a single view. This read-only Data Graph can then be used in a variety of ways through API, automations, and Salesforce applications, like Marketing Cloud. In fact, a Data Graph is a requirement for using personalization (and some automations) within Marketing Cloud – the objects and fields you select when creating this graph are the same objects and fields that you’ll have access to when adding personalization to your marketing content or powering your automations. 

Your Data Graph needs to have a specific shape to successfully send your emails. If you have Marketing Cloud Advanced Edition, you’ll also need to ensure that Einstein Engagement Scoring and Einstein Engagement Frequency features have been enabled before building. This blog will help you understand the steps needed to take to create and edit your Data Graph for Marketing Cloud.

Things to Consider Before Building a Data Graph

Once upon a time editing a data graph wasn’t possible, which meant gathering all of the information you’d need to reference in your marketing efforts before building your first graph. Now it’s entirely possible to edit your data graph, but I’d still highly recommend you gather your requirements ahead of time, so let’s think about what you’ll need.

What fields do you need for personalization?

Personalized marketing content is the name of the game, so the first thing to consider is what fields you’ll want to reference in any personalized marketing content. This should include things like First Name, Last Name, Title, and Account but you should also consider what custom fields you may want to reference, like the name of a product or webinar they’ve attended.

Are there any fields you’ll need for segmentation?

The segmentation capabilities in Marketing Cloud rely on the fields that are included in your data graph, so next up it’s time to think about how you’re planning on segmenting your prospects for email, SMS, and/or WhatsApp sends and automations. Common things to include could be industry, region, and address data. Make note of the fields and the object that those fields are on. For example, if you want to pull in industry, that field is likely on the Account Object. Keep in mind that anything you include here must have some relationship to the individual included in the segment. 

What will you need for your automations?

The last thing you’ll need to consider is any information you might need for your flows. What information will you be basing your automation decisions on? Things to consider include campaign membership or status, email engagement, and geographical information.

Have Advanced edition? Turn on Einstein Features (if applicable)

Marketing Cloud Advanced Edition includes Einstein Engagement Scoring and Einstein Engagement Frequency. Be sure to enable these features before building your data graph! 

Confirm the fields are in Data Cloud

Now that you have your field requirements determined, the next step is to make sure all these fields are mapped to your Data Streams. These field mappings take the new information ingested in the data stream and map it to the appropriate fields and objects in the Data Model Object (DMO) to create or update the appropriate records. Head to the Data Streams tab in Data Cloud and confirm all the fields you listed earlier are mapped to the appropriate DMOs. Check out this help article for some data mapping best practices.

Be sure the Data Cloud Connector can View All fields

One of Salesforce’s core tenets is trust, and that extends across all layers of the Salesforce ecosystem. This means that the connector between Data Cloud and Sales Cloud has minimum access to information in your Salesforce system. Make sure all the fields you’re including in your data graph are visible to Data Cloud by going to the Data Cloud Salesforce Connector Permission Set and updating the object settings to include the View All and Read permissions for every object you’ve listed. This ensures that all objects and fields are able to be ingested into Data Cloud.

Building the Standard Data Graph for Marketing Cloud 

We have a step by step blog on building a data graph for personalization, but as a quick refresher, here are the steps you’ll need to take and things to keep in mind. 

  1. Go to Salesforce Setup > Marketing Cloud > Assisted Setup > Reporting and Optimization > Customer Engagement
  2. Click on “Go to Data Graphs”
  3. Create a new data graph from scratch
  4. Use the default data space
  5. Select the Unified Individual as your Primary Data Model Object
  6. Ensure your data graph has the following shape:
  • Unified Individual (Primary Data Model Object)
    • Unified Link Individual
      • Individual
        • Contact Point Email
        • Contact Point Phone
  1. Make sure all the objects and fields on your lists are included in the data graph
    1. The following fields must be selected during the Data Graph setup:
      1. Individual ID from ‘Individual’
      2. Email Address from ‘Contact Point Email’
      3. Telephone Number from ‘Contact Point Phone’

But what if you have Advanced?

If you’re using Marketing Cloud Advanced Edition, be sure to include the Email Engagement Score (Unified Individual > Unified Link Individual > Contact Point Email) and Email Engagement Frequency (Contact Point Email & Contact Point Phone). 

Add in SMS 

By now, your data graph should look something like this, give or take the Email Engagement Score, Email Engagement Frequency, and SMS options. To include SMS in your Data Graph, be sure to include the Contact Point Phone and the Message Engagement options, as shown below.

Message Engagement gives you lots of options for monitoring how your SMS marketing is doing. Use this to monitor engagement with your SMS messages, the messages you’re sending, links, subscription information and more!

Bringing in Custom Fields and Objects

Okay, so we’ve covered adding in all the standard objects and fields you’ll need for your standard personalization and automation needs, but what about the custom objects that you may have in your organization? These may be objects from integrations, or ones you’ve created to help manage campaigns or customer orders. 

To bring this information into your Data Graph for use in your marketing, you’ll need to ensure that there’s a connection to the Individual in some manner. What does that mean? An easy example is an Opportunity – Opportunities are connected to the Individual via their Account in Salesforce. Select the top level item in your Data Graph, then use the + option to drill down to the object you’re looking for. Once you’ve gotten your object added on the graph, use the right side of the screen to select the fields you want to include in the graph.

Deploy Your Data Graph

Now that you’ve built your graph, the next step is to save and build, then deploy your graph. Click on Save and Build then choose your refresh interval. Keep in mind that every refresh will consume credits! The right refresh interval will depend on how you’re planning on using the Data Graph, but typically the daily refresh rate works well for marketing needs.

Head Back to Setup to Deploy Your Graph

From Salesforce Setup, type Reporting and Optimization in the Quick Find box and navigate to the Customer Engagement option. In the Configure Basic Personalization section, use the drop down menu to select the Data Graph you just created.

If prompted, confirm that you want to update your data graph by clicking the Update button.

Get Personalizing with Your Data Graph!

Now that you’ve built and deployed your Data Graph, you’re able to use the information in your personalization and automation efforts across Marketing Cloud. This powerful tool combines information from across your Salesforce organization into a single place of reference for Marketing Cloud to use that will update automatically on a planned schedule.

Autonomous AI is transforming the way organizations operate, and Salesforce’s Agentforce is at the forefront of this revolution. The product was made generally available by Salesforce in October 2024. Whether you want to streamline case management, enhance lead nurturing, or delight customers, Agentforce empowers businesses to accomplish more with fewer resources. In this post, we’ll share five practical tips to help you successfully implement and use Agentforce. 

Feeling anxious about diving all in with Agentforce? Contact the Sercante team for an Agentforce readiness assessment. That way, you can be sure you’re getting set up for success before you implement Agentforce in your org.

Understanding Agentforce

Before diving into the tips, let’s take a closer look at what Agentforce is.

Agentforce enables autonomous AI agents to perform tasks without human intervention, acting as digital workers within Salesforce or external customer channels. These agents enhance productivity by automating routine tasks and assisting with complex ones. With tools like Agent Builder, you can customize agents using pre-built topics and actions or create entirely new ones tailored to your organization’s needs.

Agentforce integrates seamlessly across the Salesforce platform, leveraging Data Cloud for reasoning and learning. Out-of-the-box agents include Service Agents for case deflection, with more capabilities to be released in December 2024, such as SDR and sales coaching agents.

Unleashing the Power of Agentforce: Five Steps to Get Started

Follow these five steps to get started on the right foot when you dive into Agentforce.

Tip 1: Identify Use Cases

Start by identifying where Agentforce can deliver the most value in your organization. Ask yourself:

  • How are you using your CRM today?
  • What are the current pain points in your processes?
  • Are there routine tasks that could be automated to free up team capacity?
  • Are there new processes you’ve avoided due to resource constraints?

Examples of use cases include automating FAQ responses for service teams, generating campaign briefs for marketing, or assisting sales reps with lead prioritization and moving deals faster.

Then for each use case, think about what would be needed to transition to an agent:

  • What job should they do?
  • What actions will they need to take?
  • What actions should they NOT take?  (This is just as if not more important to make sure you have defined the lane where an agent should operate within that use case)

Your responses to those questions are going to help you to understand the level of effort involved in use case. This in turn is going to help you to prioritize based on the level of effort and potential value

Tip 2: Define Success Metrics

To gauge the success of your Agentforce implementation, establish clear goals and KPIs. 

Questions you can ask:

  • What does success mean? How will we know we have addressed our problem? 
  • What metrics are we tracking today that we want to see improvement on?
  • Are there additional metrics that will let us know we are seeing success?

For example:

  • Reducing average case handling time by 20%
  • Improving lead response times
  • Increasing campaign ROI by automating content creation

Ensure you have baseline data for comparison and that the necessary measurement tools are in place to help you track success.

Tip 3: Assess Your Data

Your AI agents are only as good as the data they access. For the use cases identified, evaluate your data readiness:

  • What data do need? 
  • Where is it located? Is it in your CRM, Data Cloud, or other external systems?
  • Is it accessible from your CRM? If it’s stored in an external system, do you have APIs in place to get that information?
  • Is the data clean, accurate, and up-to-date?
    • Follow this blog post for tips on how to keep your imported Pardot prospect data clean.
  • Do you have a single view of the customer across systems?
  • Lastly, are knowledge bases and metadata structured for easy access? 
    • Agents need knowledge to inform how they will operate and answer questions. This is all of the background configurations your agents actions will rely on — flows, prompts, and Apex for example — they need to also be clearly identifiable and accessible. 
    • When you add actions to your topics, it uses the descriptions to help fuel the instructions. The naming conventions of your resources will also make it easier to determine what the inputs and outputs need to be.

Data and metadata are the backbone of AI performance, so this is an important area to pay attention to.

Tip 4: Start Small

After completing the previous steps, you may have more than one great use case to start with. Here’s where you ask yourself: What are the quick wins that we can get started on that can move the needle and that we can expand on as we mature?

It’s really easy to get caught up on how this can solve ALL the things. There are many challenges to starting a complex process all at once. If a lot of effort is required to get the data in place or to get the actions set up, it will be more difficult to roll out, not to mention making it potentially disruptive and prone to issues 

Avoid the temptation to tackle complex processes right away. Instead, focus on a simple, high-impact use case to pilot Agentforce. There are many out-of-the-box topics and actions that make getting started easier. For example, automating a single FAQ response or generating summaries for sales reps.

Starting small helps build confidence, momentum, and organizational buy-in, and it also reduces the risk of missteps.

Tip 5: Nail Down Clear Instructions

When designing agents, clarity is key. Use the Agent Builder to create and test well-defined topics and actions:

  • Topics – Include precise instructions for classifying user requests, setting guardrails, and outlining scope.
  • Actions – Clearly define what the agent should do, including required inputs and expected outputs.

Salesforce Agentforce Topic Instruction Best Practices

Instructions are the foundation for grounding how agents perform. They set the guardrails for how the agent should behave and give the agent the context it needs to do its job. 

Here are a few best practices for writing Agentforce topic instructions:

  • Start simple
    • Start with the main use case first to ensure the agent is performing as expected. Then, add in more detail to address edge cases. Be sure to test existing instructions for any conflict. You don’t want to confuse the agent! 
  • Use plain language
    • Use concise natural language to describe what your action does. Keep it to 1-3 sentences, and it can include the goal of the action, any use cases, and the objects or records it uses or modifies. 
    • In general, the more relevant detail you include in your instructions, the easier it is for the agent to differentiate between actions. Also, be sure to vary the words you use. For example, use a mix of “Get,” “Find,” “Retrieve,” or “Identify” for actions that will query records.
  • Avoid industry or company jargon
    • Write like you are instructing someone who doesn’t know your business. Even terms like ‘qualified lead’ could mean something different from one organization to another. Give context where necessary, and reference clear criteria using the data it will have access to. 
    • For example, instead of vague terms like “qualify lead,” specify conditions such as “lead status equals MQL.” 
    • The agent isn’t not going to know your business processes either, so be explicit about the sequence of instructions or any conditions a conversation must meet for an agent to apply an action.
  • Think of all the paths
    • You want to go through every possible permutation to determine the actions required. For example: a customer reaches out because they didn’t receive their order. 
    • First think about the order status ( Order Shipped, Delayed, Not Found, Processing). If the status is Shipped then there could be different tracking statuses (In Transit or Delivered for example). If the order is showing as Delivered, was it delivered to the customer’s correct address? Was it stolen? …and so on.
  • Remember the Guardrails
    • Keep the Agent in its lane by providing clear instructions on what the agent should not do to prevent unwanted responses. In cases where the agent is customer-facing, be sure to also give clear direction on when an interaction should be routed to a human.

Test these instructions thoroughly in the Agent Builder’s testing environment to ensure your agents behave as expected.

Ready to Explore Agentforce?

Agentforce offers an exciting opportunity to enhance productivity and streamline operations. By identifying the right use cases, preparing your data, and starting with manageable projects, you can set your organization up for success.

Want to learn more? Check out Salesforce’s Agentforce Trailhead and virtual workshops to get hands-on experience. Need expert guidance? Contact the Sercante team for an Agentforce readiness assessment.

Product Note: Marketing Cloud Growth and Advanced are editions of Marketing Cloud Next and have also been referred to as Agentforce Marketing.

Like many people in the Salesforce ecosystem, you may be intrigued by the announcement of Marketing Cloud Growth Edition — especially since access to the platform is available to current Marketing Cloud Account Engagement (Pardot) users on the “Growth Edition” tier. However, a key differentiator between the platforms is that Growth Edition gives marketers access to Data Cloud credits.

In this post, we’ll explain how Account Engagement users can tap into those Data Cloud credits through Growth Edition, the differences between both platforms’ billing models, and strategies for marketers to follow while using Data Cloud credits.

Understanding the Consumption-Based Billing Model

Whether you’re a marketer, an operations manager, an admin, or something in between, there’s a lot to look forward to as functionality moves into Salesforce core. For example, consider the flexibility of segmentation with Data Cloud and leveraging Einstein AI to supercharge your campaigns. 

As you start to explore this toolset and feature set, however, there is an important mindset shift in the structure of the product to be aware of.

Like Data Cloud, Marketing Cloud Growth Edition is a consumption-based toolset. That means your team’s feature usage within the platform determines how many credits are used and what your organization will pay each billing cycle.

Back up a second — Account Engagement has usage limits, too?

Yes, Account Engagement has certain feature limits. If you’re an admin, you’re probably familiar with navigating to the usage tab and checking your mailable prospect database or how many repeating engagement studios you have in play (if you’re not, check out our blog post on monitoring your mailable database). 

How does the Account Engagement billing model differ from Growth Edition’s?

Outside of total mailable database count and feature limits based on your edition, segmentation and email sending are generally open season for users. Dynamic lists can be run and emails can be sent to your heart’s content. 

The Einstein toolsets available in the more premium editions of the platform also generally run for the whole database and have no specific consumption considerations.

In comparison, Marketing Cloud Growth Edition is structured so there are credits for many of the core actions taken. This aligns with the structure of Data Cloud, which serves as the segmentation engine for Growth campaigns. 

Marketing Cloud Growth Edition Standard Credits

For new setups of Growth Edition, these are the standard credits provisioned:

  • 10K Marketing Unified Profiles
  • 240K Data Cloud Credits
  • 10K Segment and Activation Credits
  • 1TB Data Cloud Storage
  • 180K Emails/year
  • 20K Einstein Co-Create Requests for email content generation

These numbers may depend on your edition and specific agreement with Salesforce, and all of these areas can be extended with additional credits

Other business segments may have Data Cloud

Also worth considering — Data Cloud is not solely a marketing tool, and Data Cloud may already be in use by other divisions of your organization. But don’t fret, that’s a good thing!

A key benefit of the toolset and moving to Growth is gaining the ability to align customer experience processes across all departments.

Is there an easy way to monitor my consumption-based credits?

Glad you asked! Yes, Salesforce released a feature called Digital Wallet to help admins keep track of consumption-based tools.

The Consumption Card tab can be accessed by users with appropriate permissions and provides an overview page to monitor credit usage.

This page also includes access to insights that help you understand how usage is trending over time and where you might need to plan for expansion.

How do I go about strategically using these? What is a “credit” worth, anyways?

Different considerations are at play for different consumption metrics within Marketing Cloud Growth.  Email send credits and Einstein Co-Create credits are relatively straightforward — the total number of emails launched and uses of AI copy generation for the content, respectively. 

Where complexity lies is the data harmonization and segmentation process in Data Cloud and credits needed there — calculated based on rows in your database used and processed for different actions.

You can see a more detailed breakdown of the calculations here

Data Cloud Credit Usage Examples for Growth Edition Marketers 

In practice, these areas are likely where a marketer will consume Data Cloud credits.

Data Harmonization and Unified Individuals

  • Target Audience: As opposed to “prospects” within Account Engagement, users create segments in Data Cloud for Marketing Cloud Growth Edition campaigns via Unified Individual profiles.

    Instead of 1:1 syncing with a lead or contact, these unified profiles can link multiple data sources to create a 360-degree view of the customer, with data from Salesforce and external data sources. 
  • Identity Resolution: To make sure these unified profiles are accurate to your map of data, identity resolution rules are created in Data Cloud to join datasets by the relationships you define.

    The harmonization process this executes does utilize Data Cloud credits, so data complexity here can affect the requirements for this process. Learn more about the process in this Trailhead!
  • Growth Edition also includes a set of features for incorporating consent per channel into this profile, determining whether the individual can be sent communications and helping you maintain privacy and compliance for your audience.

Pulling and Refreshing Segments

  • Segment Creation: When you create a new segment or modify an existing one, Data Cloud Credits are used to execute the data queries that define the segment criteria. This process involves filtering and aggregating large volumes of data to isolate specific audiences.
  • Segment Refresh: To keep your segments up-to-date, you’ll need to refresh them regularly. Each time you perform a refresh, credits are consumed as the system reprocesses the data to ensure the segment reflects the most current information.

Using Einstein’s AI Capabilities 

Note: this refers to Einstein Features within Data Cloud, not Einstein Co-Create content generation within Marketing Cloud Growth. You can get more on the specific rate consumption for AI models with Data Cloud here.

  • Predictive Scoring: Einstein AI can analyze historical data and predict future behaviors. Utilizing predictive models or scoring capabilities consumes Data Cloud Credits based on the complexity and volume of data processed.
  • Recommendation Engines: Whether you want to personalize content or recommend products, Einstein’s recommendation engines leverage AI to analyze user behavior and preferences. This process also requires Data Cloud Credits, reflecting the computational resources needed for these advanced features.
  • Automated Insights: Einstein provides actionable insights and analytics by examining trends and patterns within your data. Accessing these insights involves credit consumption, especially when dealing with extensive datasets or detailed analyses.

How to make the most of your Data Cloud credits

To make sure you’re using Data Cloud as efficiently as possible, keep the following considerations in mind.

  • Efficient Querying: Optimize your segment queries to be as efficient as possible. Reducing the complexity of queries or breaking them into smaller, more manageable tasks can help conserve credits.
  • Scheduled Refreshes: Instead of frequent manual refreshes, schedule them during off-peak times or based on data needs. This reduces unnecessary credit usage while ensuring segments remain accurate.
  • Strategic AI Usage: Use Einstein’s AI capabilities strategically. Prioritize features that deliver the most value for your marketing goals and ensure that the credit expenditure aligns with your objectives.
  • AI Models Management: Regularly review and refine AI models to maintain their accuracy and relevance. Properly trained models can yield better insights, maximizing the return on your credit investment.

Take advantage of the consumption-based model to understand what you’ll need as you scale

Hopefully, this gave you a good introduction to the concepts needed to monitor and understand credit usage as you consider using Marketing Cloud Growth Edition and Data Cloud alongside Account Engagement.

 Don’t let this scare you off — while there are new concepts to learn, the toolset opens possibilities for marketers ready to use data to create the best possible customer experience and segmentation. 

As the “Growth” name implies, it sets your business up for cost-efficiency in the short term and scalability in the long term. As you continue to scale and incorporate new data sources and channels, there’s a more defined method to ingest this data, improve your personalization, and predict the impact to your costs over time. 

As you explore more, please check out our FAQ article on Marketing Cloud Growth or send us a message if you have any other questions.

No more posts to show