In "Building Agentic AI Systems", you will explore how to design and create intelligent and autonomous AI agents that can reason, plan, and adapt. This book dives deep into the principles and practices necessary to unlock the potential of generative AI and agentic systems. From foundation to implementation, you'll gain valuable insights into cutting-edge AI architectures and functionalities. What this Book will help me do Understand the foundational concepts of generative AI and the principles of agentic systems. Develop skills to design AI agents capable of self-reflection, tool utilization, and adaptable planning. Explore strategies for ensuring ethical transparency and safety in autonomous AI systems. Learn practical techniques to build effective multi-agent AI collaborations with real-world applications. Gain insights into designing AI systems with scalability, adaptability, and minimal human intervention. Author(s) Anjanava Biswas and Wrick Talukdar are experts in AI development with years of experience working on generative AI frameworks and autonomous systems. They specialize in creating innovative AI solutions and contributing to AI best practices in the industry. Their dedication to teaching and clarity in writing make technical concepts accessible to developers at all levels. Who is it for? This book is ideal for AI developers, machine learning engineers, and software architects seeking to advance their understanding of designing and implementing intelligent autonomous AI systems. Readers should have a foundational understanding of machine learning principles and basic programming experience, particularly in Python, to follow the book effectively. Understanding of generative AI or large language models is helpful but not required. If you're aiming to build or refine your skills in agent-based AI systems and how they adapt, this book is for you.

Today, I’m talking with Natalia Andreyeva from Infor about AI / ML product management and its application to supply chain software. Natalia is a Senior Director of Product Management for the Nexus AI / ML Solution Portfolio, and she walks us through what is new, and what is not, about designing AI capabilities in B2B software. We also got into why user experience is so critical in data-driven products, and the role of design in ensuring AI produces value. During our chat, Natalia hit on the importance of really nailing down customer needs through solid discovery and the role of product leaders in this non-technical work.

We also tackled some of the trickier aspects of designing for GenAI, digital assistants, the need to keep efforts strongly grounded in value creation for customers, and how even the best ML-based predictive analytics need to consider UX and the amount of evidence that customers need to believe the recommendations. During this episode, Natalia emphasizes a huge key to her work’s success: keeping customers and users in the loop throughout the product development lifecycle.

Highlights/ Skip to

What Natalia does as a Senior Director of Product Management for Infor Nexus (1:13) Who are the people using Infor Nexus Products and what do they accomplish when using them (2:51) Breaking down who makes up Natalia's team (4:05) What role does AI play in Natalia's work? (5:32) How do designers work with Natalia's team? (7:17) The problem that had Natalia rethink the discovery process when working with AI and machine learning applications (10:28) Why Natalia isn’t worried about competitors catching up to her team's design work (14:24) How Natalia works with Infor Nexus customers to help them understand the solutions her team is building (23:07) The biggest challenges Natalia faces with building GenAI and machine learning products (27:25) Natalia’s four steps to success in building AI products and capabilities (34:53) Where you can find more from Natalia (36:49)

Quotes from Today’s Episode

“I always launch discovery with customers, in the presence of the UX specialist [our designer]. We do the interviews together, and [regardless of who is facilitating] the goal is to understand the pain points of our customers by listening to how they do their jobs today. We do a series of these interviews and we distill them into the customer needs; the problems we need to really address for the customers. And then we start thinking about how to [address these needs]. Data products are a particular challenge because it’s not always that you can easily create a UX that would allow users to realize the value they’re searching for from the solution. And even if we can deliver it, consuming that is typically a challenge, too. So, this is where [design becomes really important]. [...] What I found through the years of experience is that it’s very difficult to explain to people around you what it is that you’re building when you’re dealing with a data-driven product. Is it a dashboard? Is it a workboard? They understand the word data, but that’s not what we are creating. We are creating the actual experience for the outcome that data will deliver to them indirectly, right? So, that’s typically how we work.” - Natalia Andreyeva (7:47) “[When doing discovery for products without AI], we already have ideas for what we want to get out. We know that there is a space in the market for those solutions to come to life. We just have to understand where. For AI-driven products, it’s not only about [the user’s] understanding of the problem or the design, it is also about understanding if the data exists and if it’s feasible to build the solution to address [the user’s] problem. [Data] feasibility is an extremely important piece because it will drive the UX as well.” - Natalia Andreyeva (10:50) “When [the team] discussed the problem, it sounded like a simple calculation that needed to be created [for users]. In reality, it was an entire process of thinking of multiple people in the chain [of command] to understand whether or not a medical product was safe to be consumed. That’s the outcome we needed to produce, and when we finally did, we actually celebrated with our customers and with our designers. It was one of the most difficult things that we had to design. So why did this problem actually get solved, and why we were the ones who solved it? It’s because we took the time to understand the current user experience through [our customer] interviews. We connected the dots and translated it all into a visual solution. We would never be able to do that without the proper UX and design in that place for the data.” - Natalia Andreyeva (13:16) “Everybody is pressured to come up with a strategy [for AI] or explain how AI is being incorporated into their solutions and platform, but it is still essential for all of my peers in product management to focus on the value [we’re] creating for customers. You cannot bypass discovery. Discovery is the essential portion where you have to spend time with your customers, champions, advisors, and their leads, but especially users who are doing this [supply chain] job every single day—so we understand where the pain point really is for them, we solve that pain, and we solve it with our design team as a partner, so that solution can surface value. ” - Natalia Andreyeva (22:08) “GenAI is a new field and new technology. It’s evolving quickly, and nobody really knows how to properly adapt or drive the adoption of AI solutions. The speed of innovation [in the AI field] is a challenge for everybody. People who work on the frontlines (i.e. product, engineering teams), have to stay way ahead of the market. Meanwhile, customers who are going to be using these [AI] solutions are not going to trust the [initial] outcomes. It’s going to take some time for people to become comfortable with them. But it doesn’t mean that your solution is bad or didn’t find the market fit. It’s just not time for your [solution] yet. Educating our users on the value of the solution is also part of that challenge, and [designers] have to be very careful that solutions are accessible. Users do not adopt intimidating solutions.” - Natalia Andreyeva (27:41) “First, discovery—where we search for the problems. From my experience, [discovery] works better if you’re very structured. I always provide [a customer] with an outline of what needs to happen so it’s not a secret. Then, do the prototyping phase and keep the customer engaged so they can see the quick outcomes of those prototypes. This is where you also have to really include the feasibility of the data if you’re building an AI solution, right? [Prototyping] can be short or long, but you need to keep the customer engaged throughout that phase so they see quick outcomes. Keep on validating this conceptually, you know, on the napkin, in Figma, it doesn’t really matter; you have to keep on keeping them engaged. Then, once you validate it works and the customer likes it, then build. Don’t really go into the deep development work until you know [all of this!] When you do build, create a beta solution. It only has to work so much to prove the value. Then, run the pilot, and if it’s successful, build the MVP, then launch. It’s simple, but it is a lot of work, and you have to keep your customers really engaged through all of those phases. If something doesn’t work [along the way], try to pivot early enough so you still have a viable product at the end.” - Natalia Andreyeva (34:53)

Links

Natalia's LinkedIn

Unlock your team's full potential with the power of Google Cloud training for partners. Explore the learning portfolio designed for partner practicioners including role-based learning paths, certification programs, skill badges, and more. Plus, we'll highlight the latest from the generative AI portfolio. Boost capabilities and drive customer success without compromising productivity!

Unlock the power of generative AI with retrieval augmented generation (RAG) on Google Cloud. In this session, we’ll navigate key architectural decisions to deploy and run RAG apps: from model and app hosting to data ingestion and vector store choice. We’ll cover reference architecture options – from an easy-to-deploy approach with Vertex AI RAG Engine, to a fully managed solution on Vertex AI, to a flexible DIY topology with Google Kubernetes Engine and open source tools – and compare trade-offs between operational simplicity and granular control.

Discover how some of the world’s most innovative companies modernized and transformed their applications with the power of Firestore, Firebase, and cutting-edge generative AI. Learn how they leveraged the latest technologies, such as edge computing and AI, to enhance customer experiences at every stage of the customer journey. Explore their innovative architecture and gain insights into building modern, engaging applications that deliver exceptional customer experiences.

Experience the power of AlloyDB Omni, a cutting-edge PostgreSQL-compatible database designed for multicloud and hybrid cloud environments. This session explores how AlloyDB Omni accelerates the development of modern applications, enabling generative AI experiences, efficient vector search, real-time operational analytics, and scalable transactional performance. We’ll also showcase how to run your applications on multiple clouds using Aiven’s seamless managed service, and how to supercharge hybrid cloud deployments with cloud-ready partners.

Are you a site reliability engineer (SRE) for an organization running generative AI workloads? If gen AI is transforming your workloads, are your SRE skills keeping pace? This session is a must for SREs facing the unique challenges of gen AI. Learn to adapt the four golden signals – tackling latency in multistage pipelines, user satisfaction in nondeterministic systems, and new error types like hallucinations. Discover how Google Cloud Observability and Firebase Genkit AI monitoring can help you master gen AI SRE.

Time to make generative AI a reality for your application. This session is all about how to build high-performance gen AI applications fast with Cloud SQL for MySQL and PostgreSQL. Learn about Google Cloud’s innovative full-stack solutions that make gen AI app development, deployment, and operations simple and easy – even when deploying high-performance, production-grade applications. We’ll highlight best practices for getting started with Vertex AI, Cloud Run, Google Kubernetes Engine, and Cloud SQL, so that you can focus on gen AI application development from the get-go.

Maximize your Gen AI inference performance on GKE. This session dives into the latest Kubernetes and GKE advancements, revealing how to achieve significant cost savings, reduced latency, and increased throughput. Discover new inference features on GKE for optimizing load balancing, scaling, accelerator selection, and overall usability. Plus, hear directly from Snap Inc. about their journey re-architecting their inference platform for the demands of Gen AI.

The wealth gap remains a persistent challenge, but generative AI offers new tools to address this complex issue. In this fireside chat, Kevin Cohee, CEO of OneUnited Bank, will share his vision for leveraging GenAI to create economic opportunity for underserved communities. Learn how OneUnited Bank's partnership with Google Cloud is driving personalized financial education and wealth management solutions, paving the way for a more equitable future.

Organizations with strict data residency requirements often struggle to leverage AI and the latest in cloud innovations on-premises. Learn how to architect gen AI optimized applications for success using LLMs, cloud infrastructure, and data on-premises without compromising on data sovereignty, security, or latency in this technical deep dive session.

Simplify blockchain development with generative AI on Google Cloud. In this interactive session, you’ll learn how Gemini AI helps generate queries for BigQuery blockchain datasets and analyzes real-time blockchain data. See how Blockscope is using Gemini to conduct forensic analysis of blockchain data. Live demos will show you how to supercharge your Web3 projects, whether you're a blockchain veteran or just starting out.

Despite the robustness of a retailer's order management system, external factors can disrupt both employee and customer experiences. Cognizant tackled the Must-Arrive-By-Date (MABD) challenge, crucial for ensuring timely shipments. Their OMS Gen AI solution features an intelligent assistant that predicts PO delays and recommends actions to guarantee on-time arrivals. This innovation delights store associates and customers alike, ensuring shelves remain stocked even under extreme weather conditions.

This Session is hosted by a Google Cloud Next Sponsor.
Visit your registration profile at g.co/cloudnext to opt out of sharing your contact information with the sponsor hosting this session.

Don't let Gen AI pitfalls derail your enterprise's success. We explore common challenges that hinder implementation, including prioritization paralysis, the seductive "proof-of-concept" trap, managing unpredictable outputs and model hallucinations, and keeping pace with rapid innovation. We highlight strategies to mitigate these risks, emphasizing the crucial role of your unique data in achieving competitive advantage. Increase your chances of achieving meaningful gen AI success by learning how to navigate these obstacles.

This Session is hosted by a Google Cloud Next Sponsor.
Visit your registration profile at g.co/cloudnext to opt out of sharing your contact information with the sponsor hosting this session.

We invite you to explore how Cognizant's Generative AI-powered solution transforms contract negotiations. This advanced technology reduces contract review time from 92 minutes to just 26 seconds, achieving a 10% increase in accuracy. It possesses a distinctive ability to identify and risk-score non-standard contract language, equipping negotiators with a contextual understanding of risk levels. This solution facilitates data-driven decision-making, mitigates financial risks, and provides a proactive approach to contract management.

This Session is hosted by a Google Cloud Next Sponsor.
Visit your registration profile at g.co/cloudnext to opt out of sharing your contact information with the sponsor hosting this session.

Definity and Quantiphi share the transformative journey of AI-driven Mainframe Modernization. By building a future-proof platform on Google Cloud for their legacy infrastructure and using Quantiphi’s GenAI-based developer productivity accelerator called 'Codeaira', Definity is unlocking a new wave of innovation in the insurance industry.  This session will address the value of AI-driven digital transformation in tackling the insurance sector's business and technical challenges while improving efficiency, customer engagement, and analytics.

This Session is hosted by a Google Cloud Next Sponsor.
Visit your registration profile at g.co/cloudnext to opt out of sharing your contact information with the sponsor hosting this session.

Discover how to integrate AI and Gen AI capabilities to unblock data quality issues, streamline the deployment processes of a data platform, and empower data teams to accelerate the development of customized data products. By automating data product and pipeline creation, infrastructure deployment, data quality, and PII controls, you can reduce engineering efforts by 30-40% and develop products three times faster. Learn how this approach has helped clients create data products faster and more cost-efficiently across various industries.

This Session is hosted by a Google Cloud Next Sponsor.
Visit your registration profile at g.co/cloudnext to opt out of sharing your contact information with the sponsor hosting this session.

The next generation of intelligent business applications is here and powered by generative AI. In this session, you will learn about Spanner's latest graph capabilities and how GraphRAG can help you deliver richer contextual generative AI applications. Discover how to leverage a consolidated data platform to create smarter, more intuitive applications and drive business innovation.

In today’s fast-paced market, data is key to innovation. This session explores how Apigee, combined with Google Distributed Cloud, enables organizations to unlock the value of their data, regardless of its location. Learn how to operationalize data across legacy systems, the cloud, and edge environments to build cutting-edge solutions like generative AI and advanced analytics. Discover how Apigee simplifies data accessibility and interoperability, accelerating your time to market and maximizing the potential of your data assets.