Writing personalized content manually for every audience segment is neither efficient nor scalable. This module introduces AI prompts as a systematic solution, showing how prompt templates with variables and placeholders can generate customized outputs across multiple audience types from a single structure. Learners move from prompt design through to execution, running scripts that produce AI-generated variations and saving outputs for A/B testing. The module also addresses how to evaluate AI outputs critically before putting them to use in a live campaign. By the end of this module, you will be able to write and run a prompt template that generates personalized content variations and assess those outputs for campaign suitability.

Marketing teams that rely on manual outreach and one-size-fits-all email sequences leave significant conversion potential unrealized. This module examines how AI-enhanced automation reshapes the lead nurturing process — from initial contact to purchase-ready handoff — by enabling personalized, behavior-triggered communication at scale. Drawing on a real-world case study of Spotify's AI-driven email performance and a hands-on HubSpot walkthrough, learners move from concept to configuration. The focus is on building workflows that reflect actual buyer behavior, not just filling a five-step template. By the end of this module, you will be able to design and configure a multi-email automation workflow in HubSpot that applies AI-enhanced logic to improve lead conversion outcomes.

Acquisition metrics tell you how many customers you're winning; CLV tells you whether those wins are worth the investment. This module focuses on understanding, calculating, and applying Customer Lifetime Value as a strategic decision-making tool — not as an abstract formula, but as a lens for evaluating acquisition channels, prioritizing retention efforts, and allocating marketing resources more precisely. Using Netflix's CLV-driven retention approach as a case study, learners work through the core formula, segment-level analysis across paid and organic cohorts, and the communication skills needed to present CLV findings to stakeholders. By the end of this module, you will be able to calculate CLV for distinct customer segments, interpret what the results mean for retention strategy, and present data-driven recommendations with clarity and confidence.

Effective marketing campaigns depend on reliable CRM data. This module introduces the three core dimensions of CRM data health: completeness, accuracy, and recency and shows how weak data quality creates workflow failures, broken personalization, unreliable reporting, and poor campaign targeting. By the end of this module, learners will be able to diagnose common CRM data problems, assess their impact on campaign performance, and conduct a structured data health audit in HubSpot.

Identifying CRM data problems is only valuable if teams can fix them systematically. This module focuses on the core CRM cleaning techniques used in marketing operations: deduplication, standardization, and enrichment. Learners explore how to sequence cleanup activities efficiently, apply bulk updates in HubSpot, and document cleanup decisions to support repeatable processes. By the end of this module, learners will be able to execute a structured CRM cleanup that improves campaign readiness and data reliability.

A one-time cleanup does not prevent future data decay. This module introduces the workflow logic patterns that keep CRM data accurate over time, including property update triggers, lifecycle stage progression rules, duplicate monitoring, and re-enrollment conditions. Learners examine how automated maintenance workflows reduce recurring manual cleanup and sustain long-term campaign readiness. By the end of this module, learners will be able to design CRM maintenance workflows in HubSpot that continuously support data quality and operational efficiency.

AI tools can surface market research at a speed and scale no human team could match. But volume of output is not the same as quality of insight. This module focuses on developing the judgment to tell the difference. You will explore how AI tools generate trend data, competitor positioning, and audience sentiment, and learn a practical framework for evaluating whether any given output is reliable and relevant enough to shape a campaign. By the end of this module, you will be able to confidently assess AI-generated market research before it influences your strategy.

Having reliable AI-generated insights is only useful if you have a process for turning them into campaign strategy. Many marketing teams use AI research tools reactively, opening a platform and seeing what comes up rather than building research around the questions a campaign actually needs answered. This module introduces a structured approach to AI-assisted research that starts with clear research questions, matches tools to question types, and synthesizes findings into a campaign-ready summary. By the end of this module, you will be able to run a structured AI research session from brief to output and produce findings that translate directly into campaign strategy.

Not every AI tool that promises to transform your marketing workflow actually will. Choosing the right tool for your tech stack requires more than a compelling vendor demo. It requires a structured evaluation process that tests each tool against the criteria that matter most in your specific environment: capability, compliance, integration, reliability, and cost. This module gives you a practical framework for making AI tool adoption decisions that are defensible, sustainable, and aligned with your actual workflow needs. By the end of this module, you will be able to evaluate AI tools systematically and produce a clear, criteria-based recommendation for any marketing use case.

Generating an email draft with ChatGPT takes seconds. Determining whether that draft is worth sending requires a different skill entirely. This module focuses on building the critical judgment needed to evaluate AI-generated email content before it reaches an audience. Learners explore structured prompting techniques that shape better output from the start, and apply a four-point red-teaming framework to assess subject line specificity, body copy relevance, CTA clarity, and AI language hallmarks. By the end of this module, you will be able to apply a systematic evaluation process to any ChatGPT email draft, identify specific weaknesses, and produce targeted revision recommendations that close the gap between AI output and audience-ready copy.

Most marketers who use ChatGPT for email copy spend more time editing the output than a well-structured prompt would have required. The difference between drafts that need heavy revision and drafts that are nearly ready to send is not the tool—it is the brief. This module introduces a five-element prompt architecture for email sequences and a chained refinement approach that allows marketers to improve specific elements without starting over. Learners practice building structured sequence prompts, generating multi-email drafts, and applying targeted follow-up prompts to address tone, specificity, and CTA quality. By the end of this module, you will be able to draft a complete email sequence using structured prompt architecture and refine the output efficiently using targeted iteration.

Individual prompting skill produces good drafts. A documented workflow produces consistent quality across an entire team. This module addresses the gap that emerges when multiple team members use ChatGPT without a shared system—brand voice shifts, output quality varies, and early efficiency gains erode. Learners design a reusable ChatGPT content workflow built around five components: prompt templates with clearly marked variable fields, an output evaluation rubric with specific pass conditions, brand voice guardrails, review checkpoints, and version control practices. By the end of this module, you will be able to build and document a ChatGPT email workflow that any team member can follow to produce consistent, on-brand content without relying on individual prompting instinct.

Deploying AI for personalized marketing outreach is only as effective as the operational foundation beneath it. Incomplete CRM records, poorly calibrated lead scoring, and vague prompts don't just limit AI performance — they automate the wrong decisions at scale. This project module places learners in the role of a Marketing Operations Lead preparing a SaaS startup to launch a feature campaign, with the task of building the three-part infrastructure that makes personalized nurturing possible: a targeted CRM cleanup plan, a lead scoring model that integrates AI-driven behavioral signals, and a reusable master prompt engineered to generate relevant outreach for high-value prospects. Each deliverable builds directly on the last, requiring learners to think in systems rather than isolated tasks. By the end of this module, you will be able to identify and prioritize CRM data gaps, design a balanced lead scoring framework that incorporates AI-generated intent signals, and construct a structured prompt that enables consistent, personalized outreach at scale.