IA Generativa para Marketing y Ventas | UDEP

The Business Course is equivalent to 44 teaching hours*.

Module 1: Introduction to Generative AI

Introduction to AI, Machine Learning and Deep Learning.
Comparative analysis: discriminative vs generative models.
Fundamentals of tokenization and natural language processing.
Algorithmic biases and ethical considerations in business implementation.

Module 2: Leadership and Strategic Vision of AI in Business Management

ROI and KPIs specific to Genetic AI projects.
Organizational change management in the adoption of emerging technologies.
Case studies: successful implementations in the financial, retail, and logistics sectors.

Module 3: Prompt Techniques and their application in Marketing

Prompt Methodology for Marketing.
Advanced techniques: few-shot learning, chain-of-thought prompting.
Practical laboratory: development of prompts for content generation and audience segmentation.

Module 4: Prompt Techniques and Their Application in Sales

Specialized prompts for prospecting analysis and lead qualification.
Creation and optimization of commercial speeches with AI.
Conversational analysis and speech analytics for sales process optimization.

Module 5: Reasoning Models and In-Depth Research

Implementation of advanced reasoning models and techniques.
Intelligent web scraping and competitive analysis with in-depth research.
Synthesis of multi-source information and generation of strategic insights.

Module 6: Creating GPTs, Projects, and Artifacts for Marketing and Sales

Custom GPT architecture: technical configuration and optimization.
ChatGPT, Claude and Perplexity Projects: context management and memory systems.
Development of artifacts: templates, calculators, and interactive tools.

Module 7: AI Agents and Automation for Marketing and Sales

Design of multi-agent architectures for business processes.
Email marketing and social media automation.
Lead scoring prototype creation.
Tools: Make.com, Zapier, N8N for workflow automation.

Module 8: Artificial Intelligence for Data Analysis – Python and Google Collab

Use of generative models for data analysis.
Sentiment analysis and pattern recognition using Generative AI.
Exploration of generative models to perform predictive analysis, identifying future trends and consumer behavior patterns.
Using Python with Google Collab for data analysis – Applied Case with real data (dataset).

Module 9: Generative AI for Key Areas and Processes

Customer Experience: chatbots and sentiment analysis.
Human Resources: CV screening and interview speech analytics.
Practical cases by sector: banking, retail, manufacturing, services.

Module 10: From SEO to GEO: Generative Engine Optimization

GEO Framework: Content architecture for generative engines.
Content optimization for ChatGPT, Copilot, Claude, and Perplexity.
Emerging KPIs: appearance rate, quality of mentions, position in narratives

Module 11: Capstone Project

Problem definition and business case.
Comprehensive development of a Generative AI solution for a real business case.
Definition of KPIs, success metrics and implementation plan.

*One class hour is equivalent to 45 minutes.

The University of Piura reserves the right to postpone, reschedule, or cancel the program if the minimum number of participants is not met. Special sessions and exams may be scheduled outside of regular class hours, after prior notification to the students.

Faculty of Economic and Business Sciences

Generative AI for Marketing and Sales

Inicio

10August