# Predictive AI: scoring, frequency, send time and bots

*Marketing Cloud Next Consultant Study Guide · Agentforce & AI Innovation · Last updated November 6, 2026 · https://www.certifyforce.com/study-guide/marketing-cloud-next-consultant/agentforce-and-ai-innovation/predictive-ai-scoring-frequency-send-time-and-bots*

How to pick Engagement Scoring, Engagement Frequency, Send Time Optimization or Metrics Guard from a requirement, with each feature's edition, setup and data needs, and how the Einstein Decision element uses scores in a flow.

- Certification: Salesforce Marketing Cloud Next Consultant
- Exam section: Agentforce & AI Innovation
- Study guide: https://www.certifyforce.com/study-guide/marketing-cloud-next-consultant

**Official exam objective:**

> Given a scenario, determine which predictive AI feature to use.

## What the exam expects

- Choose among Send Time Optimization, Metrics Guard, Engagement Scoring and Engagement Frequency from a business requirement.
- State which features each edition includes.
- Plan each feature's Setup path, identity resolution ruleset and global model decision.
- Explain why a contact has no score, and what a model is not intended to do.
- Configure Einstein Decision models, paths and data graph requirements.
- Distinguish the real-time and batch versions of Metrics Guard.

**Key terms.** *Predictive AI*: features that provide insights to inform the content and timing of marketing activities. *Global model*: a model trained on anonymized, aggregated data across customers. *Model card*: the page stating a model's intended use, data and limits. *Data graph*: the related data objects a flow can read. *Einstein Decision*: the flow element that routes people by engagement level.

## Key facts

| Fact | Detail | Source |
|---|---|---|
| Growth predictive features | Send Time Optimization and Metrics Guard | [AI data usage](https://help.salesforce.com/s/articleView?id=mktg.mktg_einstein_data_usage.htm&type=5&language=en_US) |
| Advanced-only predictive features | Engagement Scoring and Engagement Frequency | [Enable AI](https://help.salesforce.com/s/articleView?id=mktg.mktg_admin_setup_einstein.htm&type=5&language=en_US) |
| STO ruleset | Individual as primary object, among the first two rulesets created | [Enable AI](https://help.salesforce.com/s/articleView?id=mktg.mktg_admin_setup_einstein.htm&type=5&language=en_US) |
| STO history and channel | Past 90 days; email only | [STO card](https://help.salesforce.com/s/articleView?id=mktg.mktg_einstein_model_card_esto.htm&type=5&language=en_US) |
| Scoring minimum | One email send for a contact to have scores | [Scoring card](https://help.salesforce.com/s/articleView?id=mktg.mktg_einstein_model_card_ees.htm&type=5&language=en_US) |
| Frequency minimums | 10 subscribers; five variants over 28 days | [Frequency card](https://help.salesforce.com/s/articleView?id=mktg.mktg_einstein_model_card_eef.htm&type=5&language=en_US) |
| Refresh | Scoring and Frequency update weekly; the cadence varies by one to several days | [Scoring card](https://help.salesforce.com/s/articleView?id=mktg.mktg_einstein_model_card_ees.htm&type=5&language=en_US), [Frequency card](https://help.salesforce.com/s/articleView?id=mktg.mktg_einstein_model_card_eef.htm&type=5&language=en_US) |
| Metrics Guard batch service | Scores every Engagement+ event in the Email Engagement DMO | [Metrics Guard card](https://help.salesforce.com/s/articleView?id=mktg.mktg_einstein_model_card_emg.htm&type=5&language=en_US) |
| Einstein Decision primary DMO | Unified Individual | [Einstein Decision](https://help.salesforce.com/s/articleView?id=platform.flow_ref_elements_mktg_einstein_decision.htm&type=5&language=en_US) |

## Check yourself

- Why shouldn't a team expect Send Time Optimization results straight after enabling it?
- Why is it risky to withhold messages because of a low predicted engagement score?
- Which data do these model cards say the histories exclude?

## Sources

- [Enable AI Features in Marketing Cloud Next](https://help.salesforce.com/s/articleView?id=mktg.mktg_admin_setup_einstein.htm&type=5&language=en_US)
- [AI Data Usage in Marketing Cloud Next](https://help.salesforce.com/s/articleView?id=mktg.mktg_einstein_data_usage.htm&type=5&language=en_US)
- [Einstein Decision Marketing Flow Element](https://help.salesforce.com/s/articleView?id=platform.flow_ref_elements_mktg_einstein_decision.htm&type=5&language=en_US)
- [Model Card: Einstein Send Time Optimization](https://help.salesforce.com/s/articleView?id=mktg.mktg_einstein_model_card_esto.htm&type=5&language=en_US)
- [Model Card: Einstein Metrics Guard](https://help.salesforce.com/s/articleView?id=mktg.mktg_einstein_model_card_emg.htm&type=5&language=en_US)
- [Model Card: Einstein Engagement Scoring](https://help.salesforce.com/s/articleView?id=mktg.mktg_einstein_model_card_ees.htm&type=5&language=en_US)
- [Model Card: Einstein Engagement Frequency](https://help.salesforce.com/s/articleView?id=mktg.mktg_einstein_model_card_eef.htm&type=5&language=en_US)
- [Feature Availability by Marketing Cloud Next Edition](https://help.salesforce.com/s/articleView?id=mktg.mktg_editions.htm&type=5&language=en_US)
- [Explore AI in Marketing Cloud Next](https://help.salesforce.com/s/articleView?id=mktg.mktg_einstein_learning_map.htm&type=5&language=en_US)

## About the full unit

The "Core concepts", "Exam traps" and "Worked scenario" sections of this unit, its 9 linked practice questions, and unlimited timed mock exams are included with the Marketing Cloud Next Consultant pack (USD $19): https://www.certifyforce.com/practice-exams