Kickstart AI in Your Data Center with Cisco Validated Designs

Event: AI Field Day 5

Appearance: Cisco Presents at AI Field Day 5

Company: Cisco

Video Links:

Personnel: Siva Sivakumar, Tushar Patel

In this presentation, Cisco outlines its approach to helping enterprises deploy AI infrastructure efficiently and effectively through Cisco Validated Designs (CVDs). The speakers, Siva Sivakumar and Tushar Patel, emphasize the growing importance of AI across industries and the challenges enterprises face in integrating AI into their existing IT infrastructure. Cisco’s solution is to provide a full-stack approach that simplifies the deployment of AI workloads, from training to fine-tuning and inferencing, using a combination of Cisco UCS servers, Nexus networking, and partnerships with key vendors like NVIDIA, Red Hat, NetApp, and Pure Storage. The goal is to eliminate the guesswork for enterprises by offering pre-validated, optimized designs that ensure high performance and scalability.

Cisco’s AI-ready infrastructure is built on a foundation of its Nexus network fabric and UCS servers, which are optimized for AI workloads. The company has developed a modular design that allows GPUs to be cycled independently of compute resources, providing flexibility and efficiency. Cisco also collaborates with partners like NVIDIA to integrate AI-specific software stacks, such as NVIDIA NGC and NIM, into its solutions. These validated designs are tailored for various AI use cases, including large language models (LLMs), computer vision, and Retrieval-Augmented Generation (RAG). Cisco’s CVDs are comprehensive, covering everything from hardware setup to software tuning, and are designed to be easily reproducible, reducing the time and complexity for enterprises to get started with AI.

The presentation also highlights Cisco’s commitment to continuous improvement and customer support. Cisco works closely with its partners to ensure that its solutions are up-to-date with the latest AI technologies and best practices. The company also offers advisory services to help customers navigate the complexities of AI deployment, from selecting the right models to optimizing infrastructure for specific workloads. Cisco’s long-term vision is to become a trusted advisor for enterprises on their AI journey, providing not just hardware and software but also the expertise and tools needed to ensure successful AI implementations.


Demystifying Artificial Intelligence and Machine Learning Infrastructure for a Network Engineer with Cisco

Event: AI Field Day 5

Appearance: Cisco Presents at AI Field Day 5

Company: Cisco

Video Links:

Personnel: Paresh Gupta

Cisco’s presentation at AI Field Day 5, led by Paresh Gupta and Nicholas Davidson, focused on demystifying AI/ML infrastructure for network engineers, particularly in the context of building and managing GPU clusters for AI workloads. Paresh, a technical marketing leader, began by explaining the challenges of setting up a GPU cluster, emphasizing the importance of inter-GPU networking and how Cisco’s Nexus 9000 Series switches address these challenges. He highlighted the complexity of cabling and configuring such clusters, which can take weeks to set up, but with Cisco’s validated solutions, the process can be streamlined to just eight hours. Paresh also discussed the importance of non-blocking, non-over-subscribed network designs, such as the “Rails Optimized” design used by Nvidia and the “Fly” design by Intel, which ensure efficient communication between GPUs during distributed AI training tasks.

The presentation also delved into the technical aspects of inter-GPU communication, particularly the need for collective communication protocols like all-reduce and reduce-scatter, which allow GPUs to synchronize their states during parallel processing. Paresh explained how Cisco’s network designs, such as the use of dynamic load balancing and static pinning, help optimize the flow of data between GPUs, reducing congestion and improving performance. He also touched on the importance of creating a lossless network using priority-based flow control to avoid packet loss, which can significantly delay AI training jobs. Cisco’s Nexus Dashboard plays a crucial role in monitoring and detecting anomalies, such as packet loss or congestion, ensuring that the network operates efficiently.

Nicholas Davidson, a machine learning engineer at Cisco, then shared his experience of building a generative AI (GenAI) application using the on-premises GPU cluster managed by Paresh. He explained how the infrastructure allowed him to train models on Cisco’s private data, which could not be moved to the cloud due to security concerns. By leveraging the GPU cluster, Nicholas was able to reduce training times from days to hours, processing billions of tokens in a fraction of the time it would have taken using cloud-based resources. He also demonstrated how the AI model, integrated with Cisco’s Nexus Dashboard, could provide real-time insights and anomaly detection for network engineers, showcasing the practical benefits of having an on-prem AI/ML infrastructure.


Navigating the AI Landscape Insights Innovations and Infrastructure Advancements with Cisco

Event: AI Field Day 5

Appearance: Cisco Presents at AI Field Day 5

Company: Cisco

Video Links:

Personnel: Jake Katz

Whether you’re an AI enthusiast, data center manager, or technology strategist, this session offers valuable insights and practical knowledge to help you navigate the evolving AI landscape. Join us to learn about an overview of the AI market and the shift from InfiniBand to Ethernet in AI data centers. This session covers learnings from hyperscaler implementations and the evolving continuum of customer needs, from a la carte and build-your-own systems to turnkey solutions. Discover how Cisco is advancing AI infrastructure with innovations like the Cisco Nexus Hyperfabric AI in collaboration with NVIDIA. Learn how these advancements are making AI more accessible and scalable for businesses of all sizes.

Jake Katz, Vice President of AI/ML Product Management at Cisco, provided a comprehensive overview of the current AI landscape, emphasizing the transition from InfiniBand to Ethernet in AI data centers. He highlighted the significant role of hyperscalers in driving AI innovations, particularly in the development of large language models and GPU clusters. Katz noted that while hyperscalers are at the forefront of AI advancements, there remains a vast potential for enterprise adoption, which is still in its early stages. He discussed the increasing bandwidth demands driven by AI workloads, predicting a shift towards 800 gigabit data centers in the near future, and underscored the importance of power and cooling solutions as AI technologies evolve.

Katz introduced Cisco’s Nexus Hyperfabric, a cloud-based management system designed to simplify the deployment and management of AI clusters. This solution, developed in partnership with NVIDIA, aims to provide a plug-and-play experience for enterprises looking to harness AI capabilities without the complexity typically associated with such deployments. The Hyperfabric solution integrates high-performance Ethernet with a full hardware and software stack, allowing customers to manage their AI infrastructure efficiently. Katz emphasized that Cisco’s approach is tailored to meet the diverse needs of customers across the AI continuum, from hyperscalers to Fortune 5,000 enterprises, ensuring that organizations can effectively navigate their AI journeys with the right tools and infrastructure in place.


Deploying AI Agents with Ease Integrail Studio’s Cloud and On Prem Solutions

Event: AI Field Day 5

Appearance: Integrail Presents at AI Field Day 5

Company: Integrail

Video Links:

Personnel: Anton Antich

Learn how to deploy AI agents effortlessly with Anton Antich, Co-founder and CEO of Integrail. Watch as Anton demonstrates the deployment process for AI agents created in Integrail Studio, whether to the cloud or on-premises. Discover best practices for quality assurance and how to seamlessly integrate these agents into your existing applications, making AI adoption easy and efficient.

During the presentation, Anton highlighted the simplicity of deploying AI agents with just a single button click, allowing users to transition from local environments to cloud or staging environments seamlessly. He emphasized the accessibility of deployed agents via API, enabling users to create sophisticated user interfaces without needing extensive coding knowledge. Additionally, Anton introduced benchmarking tools that allow users to compare different models and assess their performance through custom questionnaires, ensuring that the agents meet specific accuracy and cost-efficiency requirements.

Anton also discussed the monitoring capabilities of Integrail Studio, which provide insights into agent performance, execution times, and costs. He shared the roadmap for future developments, including enhanced integrations with popular CRMs, the introduction of a code execution node for generating and testing code, and the creation of autonomous agents capable of coordinating complex tasks. The presentation concluded with an invitation for attendees to experiment with the platform and provide feedback, as Integrail Studio continues to evolve and improve.


Ultimate AI Learning Agents with Integrail

Event: AI Field Day 5

Appearance: Integrail Presents at AI Field Day 5

Company: Integrail

Video Links:

Personnel: Anton Antich

Anton Antich, Co-founder and CEO of Integrail, presents learning agents—advanced AI that continuously evolves by learning from its environment and user interactions. Watch as Anton demonstrates how these agents can acquire new skills, adapt to changing scenarios, and improve decision-making. Discover the power of learning agents in handling dynamic customer interactions, personalized marketing, and more complex business operations.

In the presentation, Anton explains that learning agents in Integrail’s platform can update their memory and acquire new skills, much like humans. The agents have a sophisticated architecture that includes sensors, actuators, a brain, skills, short-term memory, and long-term memory. The memory can be updated automatically, allowing the agent to become more knowledgeable over time. Expanding skills is currently semi-manual, but the platform is working towards making this process fully automatic. Anton demonstrates a feature called branching, which allows the agent to make decisions based on user input, implementing an if-then-else functionality. This branching capability is crucial for creating complex agents that can handle various tasks and user interactions.

Anton also showcases a more sophisticated agent designed for strategic marketing. This agent can read a website, analyze its content, and generate an initial marketing strategy document. Users can interact with the agent to iteratively update and refine the document, adding new features or generating Google Ads examples. The agent uses a combination of techniques, including branching, summarization, and memory updates, to provide a collaborative work environment. This example illustrates the potential of learning agents to assist in complex business operations, making them a valuable tool for corporate work. The presentation concludes with a look at the future of Integrail’s learning agents, emphasizing the potential for fully automatic skill acquisition and the new opportunities it will bring.


Enhancing AI Capabilities with Memory and State Agents in Integrail Studio

Event: AI Field Day 5

Appearance: Integrail Presents at AI Field Day 5

Company: Integrail

Video Links:

Personnel: Anton Antich

Anton Antich, Co-founder and CEO of Integrail, demonstrates how state agents use memory to improve decision-making and handle more complex workflows. These agents differ from reflex agents by retaining information between interactions, allowing for more personalized responses and adaptable strategies. Watch the demos to learn how state agents are applied in customer service, marketing, and IT management, showcasing the powerful capabilities of Agentic AI.

In the presentation, Antich explains the architecture of state agents, emphasizing the importance of updating short-term memory while excluding long-term memory updates. He demonstrates the limitations of reflex agents, which lack context and history, by showing how they fail to maintain a coherent conversation about Ernest Hemingway. To address this, he introduces a chat history node that allows agents to retain and utilize previous interactions, thereby creating a more context-aware and responsive agent. This enhancement is crucial for applications requiring a deeper understanding of user interactions, such as customer service and IT management.

Antich further illustrates the capabilities of state agents through a “Questionary Builder” demo, which showcases how these agents can handle more complex tasks by updating short-term memory between interactions. The agent is designed to gather specific user information, such as name, date of birth, and hobbies, and updates its session memory accordingly. This approach not only makes the agents more efficient by reducing the need to analyze extensive chat histories but also enables them to achieve more complex goals. By integrating memory and state, Integrail’s agents can manage multi-step processes and adapt to user needs more effectively, demonstrating the potential for advanced applications in various fields.


Understanding Reflex Agents in Integrail Studio

Event: AI Field Day 5

Appearance: Integrail Presents at AI Field Day 5

Company: Integrail

Video Links:

Personnel: Anton Antich

In this presentation, Anton Antich, Co-founder and CEO of Integrail, introduces the concept of reflex agents and demonstrates their creation using Integrail Studio. Reflex agents are designed to perform simple tasks efficiently by adhering to basic condition-action rules, making them suitable for straightforward processes in various fields such as sales, marketing, and HR. Antich emphasizes that these agents can interact with external systems, enabling them to execute tasks like web searches and email responses without the need for complex decision-making or memory capabilities.

Antich provides a detailed walkthrough of how reflex agents can be utilized in practical scenarios, such as conducting web searches to gather information before responding to user queries. He explains the process of formulating effective search queries from user prompts and highlights the importance of converting raw HTML into readable formats for further processing. By integrating both Google search and vector memory, these agents can access a wealth of information, allowing them to provide accurate and contextually relevant responses. Antich also discusses the potential for customization, enabling users to connect their own APIs and tailor the agents to meet specific organizational needs.

The presentation further explores the capabilities of reflex agents in automating transactional processes, such as customer support and email management. Antich demonstrates how these agents can read emails, generate draft responses, and utilize internal knowledge bases to enhance their effectiveness. He addresses concerns regarding data security and sovereignty, explaining the options for cloud and on-premise deployments. Overall, the session illustrates how reflex agents can streamline operations and improve efficiency across various business functions by leveraging AI technology in a user-friendly manner.


Introduction to AI Agents with Integrail

Event: AI Field Day 5

Appearance: Integrail Presents at AI Field Day 5

Company: Integrail

Video Links:

Personnel: Anton Antich

Anton Antich, Co-founder and CEO of Integrail, presented an introduction to AI agents using Integrail Studio, showcasing the various types of agents that can be created to automate workflows across different business functions. The presentation began with a basic understanding of AI agents, drawing parallels between human cognitive functions and the capabilities of these agents. Anton explained how agents can perceive input, process information, and produce output, akin to human behavior. He emphasized the importance of memory, both long-term and short-term, in enhancing the functionality of these agents, and introduced concepts such as Retrieval Augmented Generation (RAG) and Vector Memory, which are crucial for improving the accuracy and relevance of responses generated by AI.

Throughout the session, Anton demonstrated the creation of different agents, starting with a simple reflex agent and progressing to more complex stateful and learning agents. He illustrated how these agents can be designed to perform specific tasks, such as automating social media content creation with an Instagram Maker, and how they can work together to streamline processes in customer support, marketing, and IT. The presentation highlighted the potential of Agentic AI to transform business operations by enabling users to build customized agents that leverage their unique data and workflows. Anton also discussed the significance of integrating various AI models and techniques to enhance the capabilities of these agents, allowing for a more sophisticated and tailored approach to automation.

In addition to the technical aspects, Anton shared his vision for the future of AI agents, emphasizing the need for creativity and experimentation in building these tools. He introduced the concept of a collaborative ecosystem where users can share their agent creations, fostering a community of innovation. The presentation concluded with a call to action for individuals and organizations to explore the possibilities of AI agents, encouraging them to leverage Integrail’s platform to develop their own solutions. By combining the power of AI with user creativity, Anton believes that the potential applications of these agents are limitless, paving the way for a new era of intelligent automation.


Agentic AI with Integrail Studio

Event: AI Field Day 5

Appearance: Integrail Presents at AI Field Day 5

Company: Integrail

Video Links:

Personnel: Anton Antich, Tom Leyden

In this presentation, Anton Antich, Co-founder and CEO of Integrail, introduces Integrail Studio, a no-code platform designed for creating Agentic AI applications that streamline business workflows. The platform allows users to deploy multiple AI agents, each specialized in specific tasks, enabling them to collaborate effectively. This approach makes advanced AI technology accessible to individuals without a technical background, allowing businesses to automate complex operations and enhance productivity. Antich emphasizes the vision behind Agentic AI, which aims to provide pragmatic solutions that can help users focus on more creative aspects of their work while delegating repetitive tasks to AI.

The presentation delves into the evolution of AI, highlighting significant milestones such as the development of deep neural networks and large language models. Antich discusses the current landscape, where skepticism and enthusiasm coexist regarding AI’s potential. He argues that the truth lies in the middle, advocating for the use of specialized AI agents that can work together to solve complex problems. This pragmatic approach, termed Agentic AI, allows for the creation of agents that are not only controllable but also capable of addressing a wide range of tasks, thus making AI more practical and beneficial for everyday use.

Throughout the session, Antich provides insights into the architecture of Integrail Studio, which integrates various AI models and external business applications. He explains the platform’s no-code visual editor, benchmarking tools, and deployment capabilities, all designed to facilitate the creation and management of AI agents. The presentation also emphasizes the importance of automating repetitive tasks, encouraging users to leverage AI to enhance efficiency in their workflows. As the official launch of the platform approaches, Antich invites attendees to explore the early preview version, showcasing the potential of Agentic AI to transform business operations.


Taking the Keysight AI Data Center Test Platform for a Test Drive

Event: AI Field Day 5

Appearance: Keysight Presents at AI Field Day 5

Company: Keysight Technologies

Video Links:

Personnel: Ankur Sheth

This demonstration of the AI Data Center Test Platform shows how network events impact completion times. The first demo showcases the effects of congestion on completion times and how poor fabric utilization impacts performance. You’ll also see how the AI Data Center Test Platform can show how increasing parallelism of data transfer helps improve utilization and completion times.

In the presentation by Keysight Technologies at AI Field Day 5, Ankur Sheth, Director of AI Test R&D, demonstrated the AI Data Center Test Platform, focusing on how network events impact completion times. The setup involved emulating a server with eight GPUs connected to a two-tier fabric network, using the Arise 1 box to simulate the GPUs and network interface cards (NICs). The demonstration aimed to show the effects of network congestion on performance and how increasing the parallelism of data transfer can improve fabric utilization and completion times. The first scenario examined the impact of congestion on the network, revealing poor performance due to misconfigured congestion control settings.

Sheth explained the configuration and results of running an All Reduce Collective operation, which is commonly used during the backward pass of a training job. The initial test showed that the network’s poor configuration led to low utilization and high latency, with only 25% of the theoretical throughput achieved. Detailed flow completion times and cumulative distribution functions (CDFs) highlighted significant discrepancies in data transfer times, indicating a problem in the network configuration. After adjusting the network settings, particularly the Priority Flow Control (PFC) settings, the performance improved dramatically, achieving 95% utilization and significantly reducing completion times.

In a second experiment, Sheth demonstrated the impact of using different algorithms and increasing the number of Q-Pairs, which are connections used in the RDMA over Converged Ethernet (RoCE) protocol. The halving-doubling algorithm initially showed average performance with significant tail latencies. By increasing the Q-Pairs from one to eight, the network’s performance improved, with more parallel and consistent data transfer times. This change allowed the network to better load balance the traffic, resulting in more efficient utilization. The presentation concluded with a demonstration of how the platform’s metrics and data can be integrated into automated test cases and analyzed using tools like Jupyter notebooks, providing valuable insights for network designers and engineers.


Keysight AI Data Center Test Platform Architecture and Capabilities

Event: AI Field Day 5

Appearance: Keysight Presents at AI Field Day 5

Company: Keysight Technologies

Video Links:

Personnel: Alex Bortok, Ankur Sheth

Keysight’s AI Data Center Test Platform is designed to emulate AI workloads, enabling users to benchmark and validate the performance of AI infrastructure in both pre-deployment labs and production AI clusters. The platform allows AI operators and equipment vendors to enhance the efficiency of AI model training over Ethernet networks by experimenting with various workload parameters and network designs. Notably, the platform provides comprehensive insights into the performance of communications and RDMA transports without the need for GPUs, making it a cost-effective solution for testing and optimization.

During the presentation, Alex Bortok and Ankur Sheth discussed the critical role of network performance in AI training, emphasizing that a significant portion of GPU time is spent on data communication rather than computation. They highlighted the importance of co-tuning the software stack and network components to achieve optimal performance, particularly as AI workloads grow in complexity and size. The speakers also explained the challenges associated with traditional benchmarking methods, which often fail to correlate performance metrics across different components of the AI infrastructure. The AI Data Center Test Platform addresses these challenges by providing a controlled environment for emulating workloads and generating real traffic, allowing for more accurate performance assessments.

The architecture of the platform is built on Keysight’s Aries 1 series of traffic generators, which can produce Rocky traffic at line rates. The platform’s software stack is API-driven, enabling users to conduct collective benchmarks and analyze results effectively. The presenters outlined the various testing capabilities offered by the platform, including load balancing, congestion control, and topology experimentation, all aimed at reducing the time required for AI model training. By providing deeper insights and repeatable testing conditions, Keysight’s AI Data Center Test Platform positions itself as a valuable tool for optimizing AI infrastructure and accelerating the deployment of AI models.


Test Tomorrow’s AI Networks Today with Keysight

Event: AI Field Day 5

Appearance: Keysight Presents at AI Field Day 5

Company: Keysight Technologies

Video Links:

Personnel: Ankur Sheth

AI deployment is growing rapidly and the race to train and deliver new AI models quickly and efficiently is a top priority. The Keysight AI Data Center Test Platform is designed to accelerate innovation in AI network fabric validation and optimization, enabling you to test today’s AI networks with confidence. This presentation introduces Keysight, the challenges our customers face and why realistic emulation and testing of AI workloads is critical.

In the presentation by Ankur Sheth from Keysight Technologies, the focus is on the rapid growth of AI deployment and the critical need for effective testing of AI network infrastructures. Keysight, with its rich history stemming from Hewlett Packard, has established itself as a leader in test and measurement solutions across various technology sectors. The company has evolved through acquisitions and innovations, positioning itself to address the unique challenges posed by the increasing complexity of AI networks. As AI technologies proliferate, particularly in hyperscale environments, the demand for robust testing solutions becomes paramount to ensure that the underlying infrastructure can support the high bandwidth, low latency, and reliability required for optimal performance.

Sheth highlights the significant role that network failures play in the inefficiencies of AI training jobs, noting that 20% of failures can be attributed to network issues. With GPUs being the most expensive resources in AI infrastructures, it is crucial to minimize their idle time caused by data transfer delays. The challenges of testing at scale are compounded by the high costs and limited availability of GPUs, making it impractical to create large test environments. As a result, the need for realistic emulation and testing of AI workloads is emphasized, as it allows operators to identify and resolve potential network issues before deploying their systems in production.

To address these challenges, Keysight introduces its AI Data Center Test Platform, which combines advanced hardware and software solutions tailored for testing AI network fabrics. This platform enables testing without the need for physical GPUs, thereby alleviating some of the cost and resource constraints faced by operators. The presentation sets the stage for a deeper exploration of the specific tools and methodologies that Keysight offers, such as the ARIES-1 platform of traffic generators, which are designed to facilitate effective testing and validation of AI networks. By providing these innovative solutions, Keysight aims to empower its customers to accelerate their AI initiatives and ensure the reliability of their network infrastructures.


What is an AI PC with Stephen Foskett

Event: AppDev Field Day 1

Appearance: Ignite AppDev Field Day 1

Company: Ignite, The Futurum Group

Video Links:

Personnel: Stephen Foskett

Stephen Foskett’s Ignite Talk at AppDev Field Day explores the concept of AI PCs, highlighting the integration of AI hardware and software in personal computers. He explains that while AI hardware like tensor cores and neural processing units have been present in devices for years, the true potential of AI PCs lies in their ability to perform AI-accelerated tasks locally. This could revolutionize user experiences and spark a new wave of PC purchases. Foskett discusses the necessary hardware components, such as high-performance CPUs, NPUs, GPUs, ample memory, and connectivity, and emphasizes the importance of software integration, citing Apple’s and Microsoft’s efforts in this area. He also addresses potential privacy concerns and the industry’s hope that AI PCs will drive a super cycle of buying, particularly in the business sector. However, he notes that the widespread use of mobile devices, which already incorporate similar AI technologies, could limit the impact of AI PCs in the consumer market.


Application Developers are Part of a Bigger Picture with Jack Poller

Event: AppDev Field Day 1

Appearance: Ignite AppDev Field Day 1

Company: Ignite

Video Links:

Personnel: Jack Poller

In his Ignite talk at AppDev Field Day, Jack Poller, an analyst and founder of Paradigm Technica, emphasizes the importance of recognizing that application developers are part of a larger ecosystem. Poller points out that the nature of the tech industry often leads developers to focus narrowly on their specific tasks, such as designing, deploying, and maintaining applications. However, he argues that it’s crucial to look beyond these immediate responsibilities and understand the broader context in which their work exists. Using the example of an XKCD comic, Poller illustrates how every piece of technology relies on numerous other elements, many of which are developed independently in the open-source community. He also highlights the interdependence between different facets of technology, such as internet performance monitoring by Catchpoint, and how they collectively impact the user experience. Poller encourages developers to broaden their perspective, recognize their role within the bigger picture, and appreciate their contribution to the wider tech community.


The DevOps Loop is Not How Software Gets Built with Mitch Ashley

Event: AppDev Field Day 1

Appearance: Ignite AppDev Field Day 1

Company: Ignite, Techstrong

Video Links:

Personnel: Mitch Ashley

In his Ignite talk at AppDev Field Day, Mitch Ashley challenges the conventional depiction of the DevOps loop as a circular, continuous process, arguing that it inaccurately represents how software development actually occurs. He reminisces about his early career experiences with the waterfall model, where extensive planning preceded any coding, leading to numerous issues upon implementation. Ashley explains that the shift to Agile methodologies, which introduced shorter cycles and incremental releases, was a significant improvement but still not the final answer. He describes DevOps as a more distributed, multiverse-like process where development is fragmented across teams and tasks, integrating continuous integration and deployment practices that allow for frequent, smaller updates. This approach better aligns with the dynamic requirements of modern software development, enabling quicker adaptations to changing needs and more efficient handling of potential issues. Ashley emphasizes the importance of viewing DevOps as a platform rather than a mere collection of tools, advocating for a holistic approach that integrates various disciplines seamlessly across the development lifecycle.


Innovate with AI – Build Chat GPT-like Apps with Calvin Hendryx-Parker

Event: AppDev Field Day 1

Appearance: Ignite AppDev Field Day 1

Company: Ignite

Video Links:

Personnel: Calvin Hendryx-Parker

In his Ignite talk at AppDev Field Day, Calvin Hendryx-Parker, CTO and co-founder of Six Feet Up, describes the process he uses to built AI applications, particularly focusing on data quality and management. He discusses the use of retrieval augmented generation for enhancing chatbot functionalities, emphasizing how poor data quality often hampers AI effectiveness. Calvin showcases a live code demonstration where he extracts and utilizes data from a poorly structured conference website to create a chatbot capable of providing specific, accurate information about the event. He explains the integration of various AI tools, including OpenAI’s Embeddings API and a VectorDB, to handle and improve data interaction for AI applications, highlighting the importance of structured data in AI efficiency and reliability.


DevRel’n For Dollars with Josh Atwell

Event: AppDev Field Day 1

Appearance: Ignite AppDev Field Day 1

Company: Ignite

Video Links:

Personnel: Josh Atwell

In his Ignite talk at AppDev Field Day, Josh Atwell, a seasoned DevRel leader, delved into the intricate value of developer relations (DevRel) in enhancing business outcomes. Atwell highlighted common misconceptions about DevRel, emphasizing that beyond the visible activities like speaking at conferences and engaging with the community, DevRel plays a crucial role in driving product awareness, adoption, and customer success. He stressed the importance of aligning DevRel efforts with key performance indicators (KPIs) and objectives and key results (OKRs) to demonstrate tangible business value. Atwell also discussed strategies for reducing friction for developers, fostering trust as peers within the developer community, and ensuring that DevRel initiatives support broader marketing and sales goals, ultimately contributing to sustained product growth and customer retention.


DevOps on the Menu with Chrystina Nguyen

Event: AppDev Field Day 1

Appearance: Ignite AppDev Field Day 1

Company: Ignite

Video Links:

Personnel: Chrystina Nguyen

In her Ignite talk at AppDev Field Day, Chrystina Nguyen shared her unique perspective on DevOps, drawing parallels between her extensive experience in the restaurant industry and the principles of DevOps in technology. She highlighted the similarities in teamwork and process optimization between running a successful restaurant and implementing DevOps practices. Chrystina emphasized that DevOps is applicable in various aspects of life, not just in technical fields, illustrating this with examples like grocery shopping and restaurant operations. She used her personal journey from the hospitality industry to tech as an inspiring example of career reinvention and adapting DevOps principles across different sectors, underscoring the universal relevance of effective communication and collaboration in achieving successful outcomes.


GKE Autopilot with Michael Levan

Event: AppDev Field Day 1

Appearance: Ignite AppDev Field Day 1

Company: Ignite

Video Links:

Personnel: Michael Levan

In his Ignite Talk at AppDev Field Day, Michael Levan discussed GKE Autopilot, which he refers to as “serverless Kubernetes” due to its management of both the control plane and worker nodes, unlike standard GKE where only the control plane is managed. He highlighted that while Autopilot simplifies the setup process, reducing the complexity and amount of code required, it also limits customization options, tying users to the configurations and services provided by GCP. Levan emphasized that while Autopilot can be cost-effective and efficient for those who want to avoid the intricacies of Kubernetes management, it may not be suitable for users who need full control over their Kubernetes environment, such as choosing specific CNIs, CSIs, or CRIs.


The Evolution of the CI CD Pipeline – Bridging the Gap from Heritage to Modern Apps with Paul Nashawaty

Event: AppDev Field Day 1

Appearance: Ignite AppDev Field Day 1

Company: Ignite, The Futurum Group

Video Links:

Personnel: Paul Nashawaty

In his Ignite presentation, Paul Nashawaty discussed the evolution of the CI/CD pipeline, emphasizing the need to balance the allure of new, cutting-edge technologies with the imperative to modernize heritage applications. He highlighted the challenges organizations face in this modernization process, particularly the integration of DevSecOps across various environments and the importance of the software development lifecycle (SDLC). Nashawaty stressed the significance of not overlooking older systems that need to evolve alongside new innovations. He also addressed the broader challenges in the market, such as skill gaps and the role of service delivery partners in implementing new technologies. Throughout his talk, Nashawaty advocated for reducing complexity and maintaining a comprehensive approach that includes both new developments and existing legacy systems to ensure a holistic progression in technology deployment.


« Previous Page
Next Page »