Agentic AI Design Patterns for GenAI and Predictive AI
With Thomas Erl
Liked by 146 users
Duration: 50m
Skill level: Advanced
Released: 10/16/2025
Course details
Description
What is this course about?
Predictive AI and generative AI provide clear business value, but each has its own limitations and risks. By leveraging the autonomous reasoning capabilities of agentic AI, we can now overcome many of those limitations and we can now mitigate many of the risks. This course covers a set of AI design patterns dedicated to how agentic AI can be effectively positioned and utilized as part of predictive AI and generative AI solutions. This can result in AI systems that are more autonomous, self-reliant, efficient, and accurate, as well as AI systems that are enhanced with regards to how both humans and applications can interact and integrate with them. This course, intended for AI/ML engineers and AI solution architects, aims to fill in the gaps between agentic AI and predictive/generative AI by showing how these technologies can be effectively used together.Note: This course was created by Thomas Erl. We are pleased to host this training in our library.
Instructor
Who teaches this course?
Thomas Erl, a LinkedIn Top Voice, bestselling author, and AI and Digital Technology Education Specialist at Arcitura. Thomas has authored or coauthored 15 books, and has published articles and interviews in publications like CEO World, The Wall Street Journal, and Forbes.Objectives
What will I be able to do by the end of this course?
- Identify and list key agentic AI design patterns utilized in enhancing predictive and generative models.
- Explain the role of autonomous self-RAG in improving generative AI content accuracy
- Describe how self-correction and decision-making logic contribute to information retrieval and content refinement.
- Implement agent-led parallelization by decomposing complex tasks into subtasks assigned to multiple AI systems.
- Analyze the effects of causal inference patterns in agentic AI design on predictive decision-making, focusing on identifying cause-and-effect relationships and mitigating risks in real-world applications.
- Assess the advantages and limitations of using the voting ensemble design pattern to enhance predictive accuracy in high-stakes decision-making scenarios and propose solutions to improve system reliability.
Audience
Who is this course for?
- AI engineers
- ML engineers
- Data scientists and engineers
- AI architects
- Research scientists
- Software developers
- Project managers in tech
- AI professionals
- Tech enthusiasts
Prerequisites
What do I need to know before taking this course?
- Basic agentic AI design and architecture concepts
- Basic predictive AI architecture foundational concepts
- Basic AI agent and system functions
- Intermediate understanding of generative AI
Skills you’ll gain
Earn a sharable certificate
Share what you’ve learned, and be a standout professional in your desired industry with a certificate showcasing your knowledge gained from the course.
-
Showcase on your LinkedIn profile under “Licenses and Certificate” section
-
Download or print out as PDF to share with others
-
Share as image online to demonstrate your skill
Meet the instructor
Learner reviews
-
Michael Posso
Michael Posso
VP Product Marketing Engineering – AI Platforms | AI Agents | Voice Interfaces | Enterprise CMS Systems
Contents
What’s included
- Learn on the go Access on tablet and phone
Similar courses
Download courses
Use your iOS or Android LinkedIn Learning app, and watch courses on your mobile device without an internet connection.