Build Production-Ready AI Agents and Multi-Agent Systems from JHU

My thoughts on the Agentic AI certification at Johns Hopkins University so far: I'm really happy with the content. I've already been applying everything I'm learning to my daily work, especially since I can now build and deploy agents designed around these core pillars: policy layer, tools and skills, memory and knowledge, guardrails, and observability. The knowledge in LangGraph has been particularly useful for understanding how to steer agent behavior in production at an enterprise scale. Based on what I've learned, I've already managed to build and launch a few agentic solutions into production, from prompt engineering and multi-agent systems all the way to agent evaluation and deployment using LangGraph.

Read More

This certificate has been awesome and fantastic for me. I was motivated to join the JHU Agentic AI program because I wanted to go beyond the general conversation around Agentic AI and Generative AI and develop a deeper, more structured understanding of how autonomous and multi-agent systems can be designed, orchestrated, evaluated, and applied responsibly in real-world contexts. Given my professional focus on digital transformation, data, analytics, and AI-enabled business innovation, I saw this program as an opportunity to strengthen both my technical perspective and my ability to translate AI capabilities into practical business value. My key learnings centered on understanding agentic AI as a system, not just as a model or a prompt. The program helped me better understand agent architectures, multi-agent collaboration, retrieval-augmented generation, tool use, orchestration, evaluation, safety, governance, and the importance of human oversight. One of my most important takeaways was that successful agentic AI solutions require more than autonomy; they require clear objectives, well-designed workflows, reliable evaluation mechanisms, guardrails, and measurable outcomes. The program has helped me significantly in my professional journey by giving me a stronger framework to design and discuss AI solutions with both technical and executive audiences. It has improved my ability to identify high-value use cases, assess feasibility and risk, and think more critically about how agentic systems can be deployed in enterprise environments. It has also reinforced my belief that AI should be applied not only as a productivity tool, but as a strategic capability that can transform operating models, decision-making, customer experience, and innovation. A memorable aspect of the program was the opportunity to connect concepts with hands-on projects and real-world scenarios. Working through practical assignments made the learning experience much more meaningful and helped me internalize how agentic AI systems behave, where they can create value, and where they need careful governance. Overall, the program was intellectually stimulating, highly relevant, and directly applicable to the work I do with organizations exploring the next stage of AI adoption. I am recommending this program to my colleagues, friends, and customers.

Read More

Happy to share—this was genuinely one of the more useful things I've done for myself professionally this year. At my day job at CSL Behring, I lead our automation and AI governance work, and I had already started building an AI assistant for my team on my own. I wanted real training to support what I'd been figuring out by trial and error, and I wanted to actually understand how these AI agents work under the hood. The course built up in a logical way—starting with how to talk to an AI model to get useful answers, then how to connect AI to your own documents and data so it can pull in real information instead of guessing, and finally how to get an AI to plan steps and take actions instead of just answering a question. The two hands-on projects were the best part. In the first, I built a tool that ranks companies as investments by combining real financial numbers with information pulled from their strategy documents. In the second, I built an AI agent that could research a stock on its own—pulling live data, doing the reasoning, and giving a recommendation. Actually building something and fixing it when it broke taught me way more than any lecture could have. It maps directly onto what I'm doing at work. Things I learned in the course—like how much the quality of what you feed the AI matters, and when adding more AI helpers actually makes something better versus just more complicated and expensive—are shaping real decisions I'm making right now on the assistant I'm building for my team. One memorable moment was hunting down a bug in my second project that turned out to be a single letter typed wrong. It was a good reminder that even with all this fancy AI stuff, it still comes down to old-fashioned attention to detail. Really glad I did this.

Read More

I would highly recommend this program to anyone looking to build expertise in Agentic AI, whether they are architects, engineers, data scientists, technology leaders, or AI practitioners. This is not just a theoretical course; it provides a balanced combination of academic depth, practical application, industry relevance, and hands-on learning. The program equips learners with the knowledge and confidence needed to design, evaluate, and deploy enterprise-grade Agentic AI solutions. If you are serious about understanding where AI is heading and want to develop the skills needed to lead the next generation of intelligent systems, this program is an excellent investment in your professional growth. Finally, I would like to thank the entire Johns Hopkins University, Great Learning, and Olympus Learning teams for their commitment, encouragement, support, and inspiration throughout this remarkable learning journey.

Read More

I recently completed Certificate Program in Agentic AI to gain knowledge and understanding of agents and prompt engineering. I believe this course helps me better understand what it means to implement agents in an environment, maintain implementation as the product scales, and stay ethically mindful so that user information and usage of these agents are protected. Having support from the Program Manager was greatly appreciated. All the mentors involved in weekly mentored learning sessions and coursework were very knowledgeable in this complex subject.

Read More

It became clear around the middle of 2025 that Agentic AI had reached a level of maturity where it was becoming viable for impactful, real-world use cases. However, moving from an impressive proof of concept to a reliable production system remained complex, risk-heavy, and required deeper expertise. That gap is what motivated me to upskill in Agentic AI. As with my previous Great Learning course, the quality of lecturers, video content, and faculty has been excellent. However, I found the live mentor sessions to be more execution-focused, with a stronger emphasis on “how” rather than “why.” I would have preferred a more theoretical focus on agent systems and evaluation, with less reliance on building by example. Due to frequent work travel and a demanding schedule, I have not been able to engage with the course in as much depth as I would have liked, including optional readings and independent experimentation. Balancing this alongside professional commitments has been the most challenging aspect. Despite this, the program has reinforced how significantly my role and industry will evolve in the coming years. While many colleagues may understand Generative AI, fewer are able to build and operate effectively in an Agentic AI environment, and this has given me a clear step ahead in capability and perspective. We are currently working on defining and building AI employees to augment our workforce and improve operational efficiency. The focus is not on replacing people, but on filling gaps in processes where human capacity is limited. One example is proactive monitoring and review of production systems and KPIs. In complex web platforms, while we already have metric-based alerting, holistic system health is often only assessed during monthly reviews. With Agentic systems, we are moving toward daily or near real-time system intelligence. My advice to professionals is simple: you do not truly understand the potential until you experience Agentic AI firsthand. When it clicks and you start observing emergent behavior beyond what was explicitly designed, the true transformative power of this technology becomes clear.

Read More

I made a deliberate decision to upskill in Agentic AI as it was an upcoming area when I started this program last year. My learning experience was very good. The quality of videos, curriculum, and assignments provided end-to-end coverage. The rigor was well paced and gave enough time to complete assignments. The hardest part was understanding multi-agent systems and patterns like coordinators, state handling, and how state moves between agents. The last assignment helped clarify these concepts. Managing time was sometimes difficult, but short videos helped me learn in small breaks. Yes, the program gave me a far deeper understanding of how to design agentic systems and what considerations are needed. My advice to professionals is to go for it.

Read More

Recently completed the Certificate Program in Agentic AI. The pace of innovation in this space is incredible, but what stood out most is how quickly agentic patterns are moving from theory to real-world application. For me, this was not about the certificate, but about sharpening how I think about human-in-the-loop workflows, real-time decision support, and building AI capability rather than just deploying tools. I am excited to continue exploring this, especially in Pharma R&D, where the opportunity to improve how decisions are made is significant. I also found Great Learning to be a strong learning platform, with well-structured courses and supportive staff.

Read More

Over more than two decades in enterprise technology and digital platforms, I have seen several waves of transformation. In recent years, it became clear that AI is evolving beyond predictive models into systems that can reason, plan, and participate in real operational workflows. In many architecture and strategy discussions, AI agents coordinating tools and enterprise data started becoming increasingly relevant. I wanted to better understand how these systems can be designed, governed, and responsibly deployed at enterprise scale, which motivated me to pursue deeper learning in Agentic AI. The program has been rigorous, well-structured, and highly relevant for professionals working in enterprise technology leadership roles. The faculty bring strong academic depth while connecting concepts to practical industry scenarios. The curriculum progresses from foundational agent concepts to orchestration, evaluation, and deployment considerations, while mentoring sessions and project work make the learning highly applied and valuable from an enterprise architecture perspective. Agentic AI is a rapidly evolving field that spans reasoning frameworks, orchestration, evaluation, and enterprise deployment considerations. The program reflects that breadth and depth, which makes it intellectually engaging. Alongside my professional responsibilities, I dedicate focused time to explore the concepts and projects because understanding how intelligent systems will shape future enterprise platforms is an important investment. Yes, the program has broadened my perspective on how AI systems may evolve within enterprise environments. Beyond conversational interfaces, agent-based systems can coordinate tools, analyze information, and support complex operational workflows. In large digital platforms, this opens opportunities for AI-assisted decision support, knowledge synthesis, and intelligent automation while still requiring strong governance and human oversight. One of the most valuable learnings has been understanding agent architecture patterns and reasoning workflows. Through the coursework, I explored multi-agent systems that simulate structured decision processes such as document analysis and risk evaluation. These concepts are useful when thinking about how AI-enabled workflows can be integrated into enterprise platforms while maintaining traceability, governance, and responsible use. In my professional work, this perspective also helps shape how intelligent capabilities can complement digital platforms and improve customer and operational experiences. For professionals exploring this space, it is important to start with a strong understanding of how agents reason, plan, interact with tools, and are evaluated. The technology is evolving quickly, but the real value comes from applying it thoughtfully within real organizational environments. Programs that combine academic rigor with hands-on experimentation provide a strong foundation for this journey.

Read More

What motivated me to upskill in Agentic AI actually started during a course I was taking at MIT on Large Language Models. In one of the sessions, the professor split us into groups and gave us an assignment focused on Agentic AI. That experience completely opened my eyes to what agents are capable of and how much real work they can take on. Over the next three days, our team built an agent integrated with WhatsApp that could make hotel reservations for a major hotel chain. Watching that system come to life was a turning point for me. I realized right then that I wanted to fully immerse myself in Agentic AI and learn everything I could, rather than rely on secondhand opinions or external noise. I explored a few different programs, but ultimately chose Johns Hopkins University and Great Learning because it felt like the right place to go deeper, build real skills, and push myself forward in this space. The experience with Great Learning has been nothing short of exceptional. The support staff is truly outstanding and genuinely committed to learner success. The curriculum is one of the strongest available for Agentic AI, with a level of depth, structure, and real-world relevance that stood out compared to other programs. A key differentiator is that the professors bring applied professional experience into the learning—they do not just teach theory but connect it directly to real-world scenarios and challenges. Learning from both mentors and professors added significant value, especially given the practical insights and industry exposure shared throughout the sessions. The hardest part of the course was making the initial sacrifice of time—giving up some weekends or Friday nights to study. Once a consistent rhythm was established, it became much more manageable. Creating a structured schedule helped a lot, breaking down content into manageable daily goals and staying a week ahead of live sessions, which made the experience organized and sustainable. The program has expanded my perspective on software development and workflow design, especially in how agentic systems handle complexity with traceability, observability, and human-in-the-loop design. Frameworks like LangGraph demonstrate how structured workflows can support highly regulated industries, including healthcare, where compliance and reliability are critical. The potential of tools like LangChain and related frameworks is evolving quickly and reshaping how such systems are built. In my professional work in healthcare, I have been using LangGraph to build a multi-agent system currently under development, supported by Claude and Cursor. The course helped significantly, especially in introducing SmolAgents for rapid prototyping. This has allowed me to test ideas quickly before moving into full system design. A key takeaway has been the importance of governance in agentic systems, particularly in regulated environments where safeguarding personal health information and ensuring compliance is critical. For professionals considering Agentic AI, my advice is simple: just start. You do not need to be a software developer to benefit from it. Understanding these systems fundamentally changes how you think about problems and possibilities, and with how quickly the field is evolving, it is one of the most valuable areas to explore right now.

Read More