Jonathan Lalou's Blog

Posts Tagged ‘AWSReInvent2025’

Lecturer

Santiago Giraldo serves as Senior Director of Product Marketing for Artificial Intelligence at Snowflake. With over 15 years of experience in data and AI technology, Santiago specializes in bridging business needs with advanced technical solutions, focusing on generative AI and enterprise data platforms. He holds a background from Parsons School of Design – The New School and is based in the Denver Metropolitan Area.

Brian Neumann is Senior Vice President of Engineering at Decile, an e-commerce analytics platform. Brian leads engineering efforts to develop innovative data solutions for brands, emphasizing multi-tenant architectures and AI integration to enhance customer insights.

Abstract

This presentation explores the transformative potential of Snowflake Intelligence, a generative AI-powered feature set designed to enable natural language interactions with enterprise data. Santiago introduces the core principles of Snowflake Intelligence, addressing longstanding challenges in data accessibility and decision-making velocity. Brian then details Decile’s implementation, showcasing how the platform powers Luma, a custom AI analyst that democratizes e-commerce insights across organizational roles. The discussion highlights architectural strategies, trust mechanisms, and practical outcomes, illustrating how agentic AI can shift enterprises from reactive reporting to proactive, reasoned action.

Bridging the Gap Between Business and Data Teams

Enterprises often grapple with disparities in how business users and data teams interact with information. Business stakeholders require timely, actionable insights to drive decisions, yet data teams frequently dedicate substantial effort to producing static reports or dashboards. By the time these deliverables reach decision-makers, opportunities may have diminished, as insights arrive too late for effective intervention.

Snowflake Intelligence addresses this divide by empowering users—from executives to frontline employees—to pose complex questions in natural language and receive reasoned responses. Unlike traditional tools limited to surface-level queries (e.g., “What were sales last week?”), this innovation facilitates deeper inquiry, such as identifying underlying causes or forecasting future trends. It integrates data from disparate sources, including databases, customer platforms like Salesforce, and third-party enrichments, all within a secure, governed environment.

A key advantage lies in its enterprise readiness: features are native to the Snowflake platform, ensuring robust governance, security, and data quality. This approach fosters a “reasoning partner” dynamic, where AI not only retrieves data but also provides explanatory context, enabling high-confidence decisions in real time.

Core Principles and Capabilities of Snowflake Intelligence

Snowflake Intelligence rests on three foundational pillars: deep analysis, trust, and enterprise-grade security.

Deep analysis extends beyond descriptive reporting to prescriptive and predictive reasoning. Users can explore questions like “What headwinds threaten upcoming sales?” or “How can retention be improved?” by leveraging multimodal data—structured and unstructured—across the organization. Features such as research mode enable forward-looking investigations, drawing from comprehensive knowledge sources.

Trust is paramount in generative AI adoption, where hallucinations or opaque reasoning erode confidence. Snowflake mitigates this through verified answers, full traceability to original sources, and transparent explanations. Responses include reformulated queries, step-by-step reasoning, and direct links to underlying SQL, allowing verification down to individual data points.

Enterprise readiness ensures all operations occur within Snowflake’s governed ecosystem. Dynamic discovery provides clear explanations of results, while integrations with marketplace data and enterprise tools unify insights. This holistic design transforms data utilization, placing organizational knowledge at users’ fingertips for instantaneous, reliable exploration.

Decile’s Journey: From Traditional Analytics to AI-Driven Insights

Decile operates as an e-commerce analytics platform, serving over 100 leading brands by aggregating data from sources like Shopify, Magento, marketing channels, and enrichment providers such as Acxiom. The platform creates dedicated Snowflake data warehouses per client, overlaid with application experiences for lifecycle reporting and customer segmentation.

Initially, Decile’s dashboards aimed to surpass native platform reporting by stitching disparate data for richer views. However, brand variability—ranging from retail integrations to diverse product analytics—complicated dashboard flexibility. This led to increased complexity for non-technical users, who grew reliant on customer success teams, effectively positioning Decile as an outsourced data function.

Recognizing this barrier, Decile sought to empower clients directly through an AI analyst. Early prototyping with various frameworks revealed significant hurdles: building vector stores for semantic understanding, ensuring SQL accuracy, providing visualizations, and establishing evaluation mechanisms. These challenges posed substantial investment risks for a startup.

Snowflake Intelligence emerged as an ideal solution, leveraging existing governed warehouses and dbt semantic models. Implementation involved extending dbt documentation with metadata (aliases, synonyms, sample values) to inform semantic views—YAML-defined structures describing dimensions, measures, relationships, and natural language descriptions.

Cortex Search services enhanced fuzzy matching for free-form queries, while verified queries predefined complex calculations (e.g., retention cohorts). A custom library automated provisioning of semantic views, search services, and agents via deployment pipelines.

Implementation Outcomes and Future Directions at Decile

Rapid deployment enabled pilot testing through Snowflake’s UI, gathering feedback to refine models. API access facilitated seamless integration into Decile’s application, branding the experience as Luma—a conversational AI analyst.

Users reported substantial time savings, with marketers and executives conducting analyses previously requiring extensive report stitching. Visible thinking steps—detailing semantic mappings and reasoning—built confidence, reducing perceived black-box risks. Support queries dropped 75% among adopters, as users self-served segments for activation.

Luma’s impact extends to operational efficiency: quicker market entry, reduced custom report demands, and empowered segmentation (e.g., identifying repeat purchasers for subscriptions).

Looking ahead, Decile plans per-brand instruction customization to capture nuances (e.g., subscription vendors, wholesale handling). Aspirations include user-contributed context for vertical-specific analyses and scheduled alerting for anomalies, emulating a proactive human analyst.

Implications for Enterprise AI Adoption

This collaboration exemplifies how Snowflake Intelligence lowers barriers to agentic AI in specialized domains. By providing turnkey frameworks—semantic views, APIs, and observability—platforms like Decile accelerate innovation without prohibitive development overhead.

Broader implications include democratized data access, reducing silos and delays while upholding trust through traceability. For e-commerce, this translates to agile responses to market dynamics, personalized strategies, and sustained growth.

Ultimately, such integrations signal a shift toward AI-augmented workflows, where tools complement human expertise, fostering cultures of data-driven agility and innovation.

Links:

• Lecture Video on YouTube
• Decile Company Website
• Luma AI by Decile
• Santiago Giraldo on LinkedIn

Lecturer

Sudeep Kalindi is a Principal Solution Architect at Amazon Web Services (AWS), where he focuses on building scalable AI and machine learning solutions for the global financial services industry. With a deep expertise in high-frequency transaction systems and cloud infrastructure, Sudeep advises major financial institutions on modernizing their fraud detection and personalization engines using advanced neural network architectures.

Pahal Patangia is the Global Head of Business for the Payments Industry at NVIDIA. He has spent nearly five years at NVIDIA accelerating the adoption of AI and accelerated computing within the payments ecosystem. Pahal works closely with banks, fintechs, and payment processors to deploy large-scale foundation models that transform transactional data into real-time business value.

Abstract

As digital transactions explode in volume and complexity, traditional rule-based and machine learning models are reaching their limits in combating sophisticated fraud and providing personalized customer experiences. This article examines the emergence of transformer-based foundation models as the “next frontier” for financial systems. Unlike prior models that treated transactions as isolated events, transformers excel at capturing long-term dependencies and sequential patterns in tabular transactional data. The discussion details the technical advantages of “attention” mechanisms in finance, the role of NVIDIA’s accelerated computing in training these massive models, and the deployment strategies on AWS that enable real-time inference. By integrating tabular foundation models with Graph Neural Networks (GNNs), financial institutions can achieve unprecedented accuracy in fraud detection and customer behavioral analysis.

The Evolution of Payment Systems: Beyond Rule-Based Models

The world of digital transactions has undergone a massive expansion, with billions of events flowing through systems daily via credit cards, QR codes, contactless payments, and cross-border transfers. This explosion in volume has been matched by an increase in the complexity of financial crime. Fraudsters now leverage generative AI and chatbots to simulate synthetic identities and execute complex, multi-stage attacks.

Historically, payment systems relied on rules-based engines or traditional machine learning models (such as Gradient Boosted Trees) that analyzed data in a “flat” or non-sequential manner. While effective for basic anomalies, these systems often fail to resolve the deep contextual history of a customer. They may miss the subtle shift in behavior that signals a compromised account because they lack the “memory” to connect transactions across long periods. The industry’s challenge is to find a middle way: leveraging the cutting-edge innovation of deep learning while maintaining the explainability and governance required by global financial regulators.

Transformers for Tabular and Sequential Financial Data

The primary innovation discussed is the application of the transformer architecture—originally designed for Natural Language Processing (NLP)—to tabular financial data. Transformers introduce the “attention” mechanism, which allows a model to weigh the importance of different parts of a transaction sequence differently.

In a financial context, this means the model can distinguish between a user’s stable, long-term habits and their recent, potentially anomalous interests. For instance, if a customer who has lived in the same city for ten years suddenly makes a high-value purchase in a foreign country, a transformer can analyze the sequence leading up to that event—looking for “warm-up” transactions or patterns indicative of travel—rather than just flagging the high dollar amount.

Key technical advantages include:

• Contextual Understanding: Transformers treat the entire transaction history of an entity (customer, merchant, or card) as a sequence, similar to a sentence in a language model.
• Solving Vanishing Gradients: Unlike Recurrent Neural Networks (RNNs), transformers can capture long-range dependencies without the performance degradation typically associated with long sequences.
• Multi-Modal Integration: They can blend different data “worlds”—such as event logs, clickstream data, and structured transaction records—into a single global embedding that provides a 360-degree view of an entity.

NVIDIA Accelerated Computing in Financial AI Factories

The training and deployment of these large-scale foundation models require immense computational power, a concept referred to as the “AI Factory.” NVIDIA’s accelerated computing platform is the engine behind these factories, providing the necessary throughput for processing millions of transactions in real time.

NVIDIA’s contribution extends beyond hardware (GPUs like the H100 and Blackwell) to specialized software frameworks. For example, the use of the NVIDIA AI Enterprise suite on AWS allows for efficient tuning and scaling of these models. Furthermore, the integration of Graph Neural Networks (GNNs) with transformers allows systems to not only understand the sequence of transactions but also the relationships between different entities (e.g., shared IP addresses or common merchants among fraudulent accounts). This combined approach enables “pattern mining” at a scale previously thought impossible.

Code Sample: Conceptual Transformer Layer for Transaction Sequences

import torch
import torch.nn as nn

class TransactionTransformer(nn.Module):
    def __init__(self, input_dim, embed_dim, num_heads, num_layers):
        super(TransactionTransformer, self).__init__()
        '''Project tabular transaction features into an embedding space'''
        self.embedding = nn.Linear(input_dim, embed_dim)

        '''Transformer Encoder Layer to capture sequential dependencies'''
        encoder_layer = nn.TransformerEncoderLayer(d_model=embed_dim, nhead=num_heads)
        self.transformer = nn.TransformerEncoder(encoder_layer, num_layers=num_layers)

        '''Output layer for fraud classification (binary: 0 or 1)'''
        self.classifier = nn.Linear(embed_dim, 1)

    def forward(self, x):
        '''# x shape: [batch_size, sequence_length, input_dim]'''
        x = self.embedding(x)
        x = x.permute(1, 0, 2) # Transformer expects [seq_len, batch, embed]
        output = self.transformer(x)
        logits = self.classifier(output[-1]) # Use the last transaction's context
        return torch.sigmoid(logits)

print("Financial Transformer initialized for sequential analysis.")

Real-Time Fraud Detection and Personalized Banking

The ultimate goal of deploying these models on AWS is to move from reactive fraud detection to proactive prevention and hyper-personalization. By leveraging Amazon SageMaker, financial institutions can run “target experiments” and deploy models into a secure, scalable production environment.

The business impact is multifaceted:

1. Reduced False Positives: By understanding context, models can reduce the number of legitimate transactions being declined, improving customer satisfaction.
2. Authorization and Routing Optimization: Real-time insights allow for smarter routing of transactions through payment networks, reducing costs and increasing success rates.
3. Hyper-Personalization: Beyond fraud, these models understand customer intent, allowing banks to offer relevant products and services at the precise moment of need.

While it is still early in the adoption cycle, initial experiments show performance improvements in the range of 1% to 2% in fraud detection accuracy—a seemingly small number that translates into billions of dollars in saved revenue across the global economy.

Conclusion

The intersection of transformer architectures, NVIDIA’s accelerated computing, and AWS’s scalable infrastructure is redefining what is possible in financial services. By treating transaction data as a language to be understood rather than a set of rows to be filtered, the industry is building a more secure and personalized future for global payments. As these “global embeddings” continue to evolve, they will ultimately provide a comprehensive context for every customer, product, and entity in the financial ecosystem.

Links:

• NVIDIA Financial Services Solutions
• AWS Financial Services Cloud
• NVIDIA and AWS Partnership

Lecturer

Mark Olsen and Jody Berenblatt are distinguished engineering and product leaders at Amazon Web Services, specializing in high-performance block storage. Mark Olsen serves as a Principal Product Manager for Amazon EBS, where he focuses on the architectural evolution of Provisioned IOPS volumes to meet the demands of mission-critical enterprise applications. Jody Berenblatt, a Senior Technical Product Manager, brings extensive expertise in the integration of storage subsystems with the AWS Nitro System and the optimization of storage networking protocols. Their work has been pivotal in the development of io2 Block Express, a storage tier designed to provide SAN-like performance in the cloud.

Abstract

This article provides a comprehensive examination of the technical foundations and performance characteristics of high-intensity block storage within the Amazon Elastic Block Store (EBS) ecosystem. Centered on the io2 Block Express architecture, the analysis explores how the integration of the AWS Nitro System, the Scalable Reliable Datagram (SRD) protocol, and Multi-Attach NVMe reservations enables ultra-low latency and high-throughput capabilities for data-intensive workloads such as SAP HANA, Oracle, and Microsoft SQL Server. The discussion details the methodology for managing tail latency, the benefits of decoupled storage architectures, and the operational strategies required to maximize I/O performance in a distributed cloud environment.

Infrastructure Foundations: The Evolution of Provisioned IOPS

The landscape of enterprise computing has shifted toward workloads that demand not only high throughput but also extreme consistency in I/O operations per second (IOPS). For decades, on-premises Storage Area Networks (SANs) were the only viable option for these applications. However, the maturation of Amazon EBS, particularly the transition from io1 to the io2 Block Express architecture, has redefined the capabilities of cloud-native block storage. The fundamental challenge in high-intensity storage is the management of latency, which is often the primary bottleneck for database performance.

In traditional storage models, performance was often tethered to the physical limitations of the disk or the controller. In the modern AWS architecture, the storage is decoupled from the compute instance, connected via a dedicated high-speed network. This separation allows for independent scaling of compute and storage resources but introduces the necessity for highly optimized networking to maintain sub-millisecond latency. The io2 Block Express volumes are engineered to provide up to 256,000 IOPS and 4,000 MB/s of throughput per volume, offering a level of performance that satisfies even the most demanding transactional databases.

Architecture of io2 Block Express: Performance and Durability

The architecture of io2 Block Express represents a paradigm shift in how block storage is provisioned and managed. Unlike standard volumes, io2 Block Express is designed to handle “high-intensity” workloads, defined by their sensitivity to latency and their requirement for high durability. These volumes provide a durability rating of 99.999%, which is a ten-fold improvement over standard io1 volumes. This reliability is achieved through sophisticated replication techniques across multiple physical hardwares within an Availability Zone.

A critical innovation in this architecture is the way it handles I/O operations. By utilizing the Nitro System, the overhead of the hypervisor is removed, allowing the EBS service to communicate directly with the instance’s memory. This “Block Express” layer acts as a high-performance interface that minimizes the processing time required for each I/O request. For applications like SAP HANA, where the speed of logging and data loading is critical, the reduced overhead translates directly into faster business processing cycles.

Networking Innovations: Scalable Reliable Datagram (SRD)

Perhaps the most significant technical advancement in maximizing block storage performance is the implementation of the Scalable Reliable Datagram (SRD) protocol. Traditional TCP protocols, while reliable, are prone to “head-of-line blocking,” where a single lost packet can delay the entire stream of data. In a high-performance storage environment, this creates “tail latency”—spikes in response time that can disrupt database synchronization and performance.

SRD solves this by utilizing multipath routing. Instead of sending data down a single network path, SRD spreads the traffic across as many as 64 different paths simultaneously. If a specific network switch becomes congested or a link fails, the protocol automatically reroutes the data without the latency spikes associated with TCP retransmissions. This protocol is implemented directly in the Nitro Cards, ensuring that the heavy lifting of network management does not consume CPU cycles on the user’s EC2 instance. The result is a more consistent “p99” latency profile, which is essential for maintaining stable performance in clustered environments.

Multi-Attach NVMe Reservations and High Availability

For enterprise applications requiring high availability, the ability for multiple EC2 instances to attach to a single EBS volume is a critical requirement. io2 Block Express supports Multi-Attach, allowing up to 16 Nitro-based instances to access the same volume simultaneously. This feature is particularly valuable for clustered file systems and applications that require shared storage for failover or parallel processing.

To manage concurrent access without data corruption, AWS implemented Multi-Attach NVMe Reservations. Based on the NVMe standard for persistent reservations (similar to SCSI-3 PR), this technology allows one instance to “reserve” the volume, ensuring that only authorized nodes can perform write operations. In the event of an instance failure, the reservation can be quickly cleared and reassigned to a healthy node, minimizing downtime. This mechanism provides the coordination layer necessary for complex deployments like Oracle RAC or SAP environments, where data integrity across multiple nodes is non-negotiable.

Observability and Performance Tuning for Enterprise Workloads

Achieving maximum performance requires a sophisticated approach to observability. Many administrators focus on average latency, but in high-intensity workloads, the “outliers” or tail latency are what truly matter. AWS provides tools such as Amazon CloudWatch and EBS Volume Insights to monitor these metrics in real-time. A key metric is the “Queue Depth,” which represents the number of pending I/O requests for a volume. To reach the full potential of an io2 Block Express volume (e.g., 256,000 IOPS), the application must maintain a sufficient queue depth—often 128 or higher—to keep the storage pipeline full.

// Example AWS CLI command to modify an EBS volume to io2 with high provisioned IOPS
aws ebs modify-volume \
    --volume-id vol-0123456789abcdef \
    --volume-type io2 \
    --iops 100000

Furthermore, the choice of the EC2 instance type is paramount. Performance is not solely a function of the storage volume; the instance must be “EBS-optimized” with sufficient dedicated bandwidth to handle the provisioned throughput. For instance, using an R5b or X2idn instance allows the application to utilize the full 4,000 MB/s throughput offered by Block Express. Failure to match the instance capability with the volume performance will lead to throttling at the instance level, regardless of how many IOPS are provisioned.

Links:

• Mark Olsen on LinkedIn
• Jody Berenblatt on LinkedIn
• Amazon EBS Product Page
• AWS re:Invent Session STG319

Lecturer

Sunnuk Kim is the Vice President and Head of the IT Strategy and Planning Division at Hyundai Motor Group. Based in Seoul, he is a primary architect of the group’s digital strategy, focusing on integrating legacy industrial operations with modern cloud intelligence to redefine the automotive lifecycle. Mahesh Shrivastava is a Director and Global Leader for SAP on AWS. He specializes in enterprise-scale digital transformation, helping multinational corporations move beyond infrastructure optimization to achieve true business model innovation through cloud-native ecosystems.

Abstract

The modern enterprise technology landscape is undergoing a fundamental shift where global organizations no longer view cloud migration as an isolated technical objective but rather as a catalyst for comprehensive business transformation. This article examines the strategic collaboration between Hyundai Motor Group and Amazon Web Services (AWS) to modernize its mission-critical SAP environment through the integration of “Pan-Amazon” services. By moving beyond traditional “lift-and-shift” methodologies, Hyundai has adopted a “clean core” strategy that bridges the gap between back-office ERP functions and front-end consumer touchpoints. The analysis explores how the integration of Amazon Business, Prime logistics, and multi-channel fulfillment centers with SAP allows Hyundai to optimize global sales, inventory management, and personalized retail experiences. This transformation signifies the evolution of the automotive industry into a data-driven, customer-centric retail model.

The Strategic Shift: From Infrastructure Migration to Business Evolution

Historically, large-scale enterprises approached the cloud with the narrow objective of reducing capital expenditure by transitioning physical data centers to virtualized environments. For a global manufacturer like Hyundai, the initial focus was often on the stability and performance of SAP systems that manage the “heartbeat” of production and finance. However, as market dynamics evolved toward direct-to-consumer models and digital-first interactions, the group identified that true value lay in how cloud-native capabilities could solve complex business challenges. This realization prompted a move away from simply “running” SAP in the cloud toward “transforming” the business through the cloud.

The strategic pivot was driven by an urgent need for customer-centricity, requiring Hyundai to provide seamless, omnichannel experiences that mirror the speed and predictability of modern e-commerce. Furthermore, the limitations of rigid, monolithic legacy architectures necessitated a “clean core” approach. This methodology allows the organization to maintain a stable, standard ERP foundation while rapidly innovating through extensions and external integrations. By breaking down the long-standing silos between manufacturing data and external consumer insights, Hyundai has positioned itself to make real-time decisions that directly impact global sales volume and customer retention.

Methodology: Integration of the Pan-Amazon Ecosystem

A core innovation in Hyundai’s transformation is the sophisticated utilization of “Pan-Amazon” services, a broad collection of Amazon’s diverse business units that are now integrated directly into the AWS cloud platform. This strategy extends far beyond typical compute and storage services. For instance, the integration of Amazon Business has allowed Hyundai to streamline indirect procurement and supply chain management directly within the SAP workflow, reducing manual overhead and improving spend visibility.

Furthermore, the application of Amazon Prime and its global fulfillment network to the automotive sector represents a significant methodology shift. By leveraging these world-class logistics models, Hyundai can manage automotive parts and vehicle accessories with unprecedented efficiency. This creates a “Y process” where product portfolio management and sales volume planning converge. In this model, the back-office operations managed by SAP are directly connected to the front-end retail experience. This integration ensures that when a customer interacts with a digital retail channel, the system can provide real-time data on vehicle availability, delivery timelines, and personalized configuration options, all backed by a robust, cloud-native logistics engine.

Technical Analysis of Modernized Operations

The transition from legacy environments to an AWS-integrated SAP landscape has yielded transformative results across several key performance indicators. In terms of scalability, the previous architecture was constrained by fixed capacity and physical hardware limitations, whereas the current AWS-integrated system offers elastic scaling that adapts to real-time demand spikes without manual intervention. Global inventory management has transitioned from fragmented data silos, which often suffered from latency and inaccuracies, to a unified system providing real-time visibility across all global fulfillment centers.

Customer experience has seen a similar leap in sophistication. What was once a linear and offline-heavy journey has been replaced by an integrated omnichannel digital retail platform that provides consumers with the speed and reliability they expect from modern digital platforms. This operational efficiency at scale is further supported by the ability to access the world’s largest online marketplace and fulfillment network. The technical result is a modular environment where the core ERP remains upgradable and stable while a vast array of custom, cloud-native services drive innovation on the periphery. This architecture ensures that even as the company expands into new geographic regions or business channels, the underlying infrastructure remains resilient and performant.

Implications for Global Automotive Retail and Beyond

The consequences of Hyundai’s “Go to Cloud” strategy are profound for the broader automotive sector. The industry is moving toward a state of direct-to-consumer readiness, where traditional dealership models are being augmented by digital platforms that offer complete transparency and predictability. This shift is enabled by the ability to treat vehicle sales not as a one-time transaction, but as a continuous relationship supported by digital services and efficient parts logistics.

The success of this project also highlights the importance of data-driven innovation. By analyzing vast amounts of data across the combined SAP and Amazon ecosystem, Hyundai can better forecast market trends and optimize production cycles accordingly. This represents a broader trend of Industry 4.0, where the lines between manufacturing, retail, and technology are increasingly blurred. The ability to achieve such high levels of operational agility while maintaining a secure and compliant global footprint sets a new benchmark for enterprise-scale digital transformation.

Conclusion

The collaboration between Hyundai Motor Group and AWS serves as a comprehensive blueprint for how large enterprises can successfully navigate the complexities of modernizing mission-critical systems. By prioritizing the customer experience and leveraging the full breadth of the Pan-Amazon ecosystem, Hyundai has evolved from a traditional manufacturer into a leader in digital automotive retail. The journey underscores that the future of enterprise IT is defined not just by the technology itself, but by the intelligent integration of diverse services to create tangible business value. As global competition intensifies, the move toward a “clean core” SAP environment supported by cloud-native logistics and AI will be the defining factor for sustainable growth and innovation.

Links:

• Hyundai Motor Group Official Website
• AWS SAP on AWS Solutions
• Amazon Business for Enterprise
• Watch the Lecture Video

Lecturer

Sam Cool is a Director and Global Lead for Healthcare Solutions at Amazon Web Services (AWS), where he focuses on accelerating digital transformation for global health organizations. With extensive experience in cloud architecture and clinical workflows, Sam works with industry leaders to dismantle data silos and implement scalable AI solutions. Jared Nicks is a Principal Solutions Architect at AWS, specializing in medical imaging and Health-IT. His work is instrumental in developing the AWS HealthImaging service, which provides high-performance storage and retrieval for large-scale medical datasets. Wilson Toe serves as a Senior Product Manager at AWS, focusing on the intersection of Generative AI and healthcare analytics. Dr. Praeloski is a Senior Clinical Scientist at Philips, bringing decades of expertise in diagnostic imaging, pathology, and cardiology. He leads Philips’ efforts to integrate multi-modal data into a unified platform that enhances clinical decision-making. Together, these experts have pioneered a collaboration that leverages cloud-native technologies to redefine the diagnostic landscape.

Abstract

Modern healthcare is characterized by an explosion of diagnostic data, yet this information remains largely fragmented across disparate systems for radiology, cardiology, and pathology. This fragmentation hampers the ability of clinicians to form a holistic view of the patient, leading to diagnostic delays and suboptimal treatment planning. This article examines the strategic journey of Philips in transforming integrated diagnostics through its partnership with AWS. By shifting from on-premises infrastructure to a cloud-native architecture, Philips has successfully integrated diverse data streams, with a particular focus on the emerging frontier of digital pathology. The discussion explores the technical implementation of AWS HealthImaging, the transition to standardized DICOM formats for pathology, and the application of Generative AI to streamline clinical reporting. Ultimately, this framework enables global collaboration and real-time diagnostic consensus, moving the needle toward truly personalized and precise medicine.

The Paradox of Fragmented Diagnostic Intelligence

The clinical diagnostic process is the cornerstone of patient care, influencing over 70% of medical decisions. However, the current infrastructure supporting these decisions is often a patchwork of “black boxes.” A patient’s journey typically involves multiple diagnostic touchpoints: an X-ray in radiology, an ECG in cardiology, and a tissue biopsy in pathology. Historically, each of these domains has operated in a silo, utilizing proprietary data formats and isolated storage systems. Sam observes that while the volume of data is increasing—driven by higher-resolution imaging and molecular diagnostics—the “intelligence” derived from that data remains localized.

For a clinician, this fragmentation means navigating multiple interfaces and manually correlating reports, a process prone to error and inefficiency. The transition to integrated diagnostics is not merely a technical upgrade; it is a clinical necessity. By centralizing these streams in the cloud, healthcare providers can move from a reactive, department-centric model to a proactive, patient-centric one. Philips’ vision for integrated diagnostics centers on breaking down these silos to provide a “single source of truth” for every patient, regardless of where the data was generated.

Digital Pathology: The Final Frontier of Digitalization

While radiology and cardiology have been digital for decades, pathology—the study of tissue samples—has remained stubbornly analog. For over a century, pathologists have relied on glass slides and manual microscopy. The sheer scale of the data involved has been the primary barrier; a single high-resolution digital slide can exceed several gigabytes in size, and a single patient case may involve dozens of slides.

Dr. Praeloski highlights that digital pathology represents the next great shift in clinical innovation. By digitizing these slides, Philips enables pathologists to work in an environment that is “born digital,” allowing for the application of computer vision and machine learning. This transition is facilitated by the adoption of the DICOM (Digital Imaging and Communications in Medicine) standard for pathology images. Standardizing these massive datasets allows them to be treated with the same rigor and interoperability as traditional radiological images, enabling them to be stored, shared, and analyzed within the same AWS-backed ecosystem.

Architecting for High-Throughput Imaging with AWS HealthImaging

The technical challenge of managing millions of high-resolution pathology slides requires an infrastructure that can handle extreme throughput and low-latency retrieval. Standard object storage, while durable, often struggles with the specific access patterns required for medical imaging, where a clinician needs to “zoom and pan” through a multi-gigabyte image in real-time.

To solve this, Philips leverages AWS HealthImaging. This purpose-built service allows for the ingestion of medical images at scale while providing sub-second access to specific image frames. By decoupling storage from the viewing application, AWS HealthImaging ensures that clinicians can access images from any device, anywhere in the world, without the need for high-powered local workstations.

'''# Conceptual example of fetching metadata for a DICOM image set'''
import boto3

health_imaging = boto3.client('healthimaging')

def get_image_metadata(datastore_id, image_set_id):
    response = health_imaging.get_image_set_metadata(
        datastoreId=datastore_id,
        imageSetId=image_set_id
    )
    return response['metadata']

Jared emphasizes that this architecture is foundational for “high-throughput” clinical environments. In a traditional setup, moving a slide from storage to a viewer could take minutes; with HealthImaging, it takes milliseconds. This efficiency is critical in pathology, where time-to-diagnosis directly impacts patient outcomes in oncology and acute care.

Empowering Clinicians through Generative AI and Automated Reporting

Once diagnostic data is centralized and accessible, the next challenge is synthesis. Pathologists and radiologists spend a significant portion of their day dictating and transcribing findings. Generative AI offers a transformative solution by automating the creation of structured reports and summarizing complex longitudinal patient histories.

Wilson explains how Philips integrates Amazon Bedrock to assist in the “last mile” of the diagnostic process. By analyzing the metadata and AI-detected features of an image, the system can draft a preliminary report that the clinician then reviews and validates. This doesn’t replace the expert; rather, it removes the “blank page” problem and ensures that reports follow a standardized, high-quality format. Furthermore, LLMs (Large Language Models) can scan years of a patient’s prior records to highlight relevant changes—such as the growth of a lesion over time—that might be missed in a manual review.

Global Collaboration and the Future of Consensus

One of the most profound impacts of shifting integrated diagnostics to the cloud is the enablement of global collaboration. In the analog world, seeking a second opinion on a rare pathology case required physically shipping glass slides across borders—a process that was slow, expensive, and risky.

Through Philips’ cloud-native platform, a specialist in New York can consult on a case in London in real-time. The digital platform supports “shared view” sessions where multiple clinicians can annotate the same slide simultaneously. Dr. Praeloski notes that in recent surveys, 100% of pathologists using the digital system reported that it facilitated reaching a diagnostic consensus more effectively than manual methods. This democratization of expertise is particularly vital for underserved regions, where access to specialized sub-pathologists is limited.

Conclusion: A Paradigm Shift in Precision Medicine

The journey of Philips and AWS illustrates that the future of healthcare is not just about “better machines,” but about “smarter data.” By integrating radiology, cardiology, and pathology into a unified cloud-native framework, they have laid the groundwork for the next generation of precision medicine. This evolution reduces clinical burnout by automating administrative tasks, improves diagnostic accuracy through AI assistance, and accelerates the pace of care through global collaboration. As the system continues to scale, the data captured today will become the training ground for the cures of tomorrow, proving that when diagnostic intelligence is integrated, the potential for clinical innovation is limitless.

Links:

• Philips Healthcare
• AWS HealthImaging Service Page
• Sam Cool on LinkedIn
• Philips Integrated Diagnostics

Lecturer

Tom Godden is an Executive in Residence at Amazon Web Services (AWS), where he draws on his prior role as Chief Information Officer at Foundation Medicine, a leading genomics diagnostics company in Cambridge, Massachusetts. Ian (co-presenter) offers additional insights from regulated environments.

Abstract

Regulated industries face a persistent dilemma: how to deliver software rapidly while satisfying stringent compliance requirements. Traditional development models, with their linear handoffs and manual processes, often exacerbate this tension, producing delays, fragmented evidence, and a compliance burden that feels detached from core engineering work. Modern approaches, however, demonstrate that compliance can emerge naturally from practices focused on quality and automation. By integrating tools like version control and continuous pipelines, organizations generate robust audit trails as a byproduct of efficient delivery. This article examines the flaws in legacy methods, details the mechanisms of contemporary practices, explores the leadership needed for change, and considers the broader implications, illustrated by experiences in genomics diagnostics under standards such as FDA 21 CFR Part 11, ISO 13485, and GMP Annex 11.

The Inefficiencies and Risks of Traditional Sequential Development

Many organizations continue to structure software development in a sequential manner, akin to an assembly line in manufacturing. Requirements are defined by one group, passed to designers, then to developers, testers, and finally to those responsible for deployment. Although this approach may appear structured, it introduces fundamental inefficiencies that become especially problematic in regulated settings.

A primary issue is the idle time that arises during handoffs. Teams often wait for deliverables from previous stages, creating bottlenecks that extend project timelines significantly. In complex projects, these delays compound, turning weeks into months and hindering the ability to respond to new insights or market demands.

Context loss during these transitions compounds the problem. When knowledge moves between specialized groups, critical details—such as the rationale for design choices or awareness of subtle edge cases—frequently fail to transfer completely. This leads to misunderstandings, rework, and the accumulation of technical debt that makes systems increasingly difficult to maintain.

Documentation suffers particularly in this model. It is often treated as a separate, post-development activity, requiring teams to reconstruct events after the fact. The resulting records tend to be incomplete or inconsistent, as memories fade and priorities shift. In regulated industries, where auditors demand clear, contemporaneous proof of every decision and change, this creates ongoing anxiety and resource-intensive preparation.

The sequential structure also reinforces organizational silos. Quality and compliance teams position themselves as final gatekeepers, reviewing work produced by others. This can foster adversarial dynamics, with engineers perceiving oversight as obstructive and assurance personnel viewing development as insufficiently rigorous. Compliance thus becomes an added layer of work rather than an integrated aspect of engineering.

In fields like medical devices or pharmaceuticals, where software directly influences patient safety, these inefficiencies carry high stakes. They delay innovations that could improve outcomes and consume resources that could be directed toward scientific advancement.

How Modern Practices Generate Compliance Inherently

Contemporary methodologies offer a fundamentally different approach, one where compliance evidence arises automatically from the act of building high-quality software. At the heart of this shift is the use of distributed version control systems like Git. Every change to code is recorded with precise details: who made it, when, and why, along with links to related discussions or requirements. This creates a complete, immutable history that serves as a reliable source of truth.

Automated testing builds on this foundation. Tests execute whenever code changes, generating detailed reports on coverage, results, and any regressions. These reports provide objective validation that the software functions as intended, without requiring manual creation.

Continuous integration and delivery pipelines integrate these elements into a cohesive flow. They define and enforce the exact steps for building, testing, and deploying software, ensuring consistency across environments. Human approvals can be incorporated where necessary, but they become part of the automated process rather than separate hurdles.

The pipeline itself receives the highest level of governance. Changes to deployment logic undergo the same review as application code, recognizing that the mechanism responsible for consistency must be trustworthy.

In this ecosystem, evidence accumulates continuously and effortlessly: commit histories, test executions, pipeline runs, approval records, and deployment details, all linked and timestamped. There is no need for a parallel compliance effort; the work of engineering excellence produces the required proof.

This also transforms the role of compliance specialists. Instead of reviewing completed work, they collaborate early to design effective controls and automations. Their expertise helps prevent issues rather than detect them late.

Transformation in Practice: The Genomics Diagnostics Example

Foundation Medicine’s experience provides a concrete illustration of these principles in action. The company develops genomic tests for cancer treatment, and its software falls under FDA classification as medical devices, requiring rigorous control and traceability.

Initially operating with sequential processes and manual documentation, the organization faced the common challenges: slow releases, high administrative overhead, and stressful audits.

Tom Godden led a comprehensive shift to automated, AWS-hosted pipelines. These became the most carefully controlled components, with any modification subject to thorough review.

The outcomes were substantial. Release cycles shortened dramatically, enabling faster incorporation of new scientific knowledge into clinical tools. Defect rates decreased as automated checks identified issues early. Audits became collaborative, with inspectors able to trace production releases directly to source changes, tests, and approvals.

Compliance teams moved from policing to partnering, contributing to system design and improving overall quality. Time previously spent on documentation and audit preparation was redirected toward advancing patient care.

This case demonstrates that modern practices not only meet regulatory demands but exceed them, delivering better software faster and with less risk.

The Essential Role of Leadership in Driving Change

Implementing these changes requires strong leadership to overcome inertia and align the organization. Executives must clearly articulate the vision: compliance is not a separate goal but a natural result of building reliable software quickly.

Building a coalition of advocates across engineering and compliance creates internal momentum. Transparency, such as dashboards showing adoption progress, can harness positive competition.

Temporary parallel operations—running old and new processes side by side—provide undeniable evidence of improvement, reducing skepticism.

Reorganizing into cross-functional squads eliminates silos and aligns incentives, so that success is shared.

Leaders grant teams autonomy in how they achieve outcomes, within defined guardrails, to maintain engagement and innovation.

Long-Term Benefits and Strategic Implications

Short, focused initiatives—such as ninety-day sprints—allow steady progress without disrupting ongoing work.

Leveraging built-in telemetry for evidence archiving minimizes additional effort.

Over time, the old “compliance theater” fades, replaced by systems where pipelines enforce standards reliably and evidence flows continuously.

Organizations gain multiple advantages: faster innovation, higher quality, lower risk, and compliance that enables rather than constrains. In regulated markets, this can become a competitive differentiator, allowing leadership in both technology and responsibility.

Relevant links and hashtags

Links:

• Session Video

Lecturer

Abhijit Chakravarty, Mike Bechtel, and Michael J. Kavis
Abhijit Chakravarty is a seasoned technology leader at LogicMonitor, focusing on the intersection of artificial intelligence and infrastructure monitoring. Mike Bechtel serves as the Chief Futurist at Deloitte Consulting LLP, where he leads research into emerging technologies and their long-term impact on the enterprise. Michael J. Kavis is a Managing Director at Deloitte Consulting and a renowned expert in cloud computing and enterprise architecture, having authored multiple books on cloud transformation. Together, they represent a convergence of industry-leading monitoring solutions and strategic advisory expertise, specifically targeted at preparing global organizations for the complexities of the agentic AI era.

Abstract

As enterprise IT environments grow in scale and complexity, traditional AIOps frameworks—which primarily focused on pattern recognition and anomaly detection—are evolving into “Agentic AIOps.” This article explores the conceptual transition from systems that merely observe and alert to autonomous agents capable of reasoning, planning, and executing remediation tasks. By examining the integration of Large Language Models (LLMs) with operational telemetry, the study highlights a methodology centered on reducing “mean time to repair” (MTTR) and minimizing human intervention in repetitive incident management cycles. The analysis delves into the maturity model for agentic adoption, the necessity of rigorous data grounding, and the evolving role of the human operator in a supervised autonomous ecosystem. The findings suggest that agentic AIOps is not merely an efficiency tool but a fundamental redesign of IT governance and service reliability.

The Conceptual Evolution: From Observability to Autonomy

The IT landscape has historically progressed through distinct phases of monitoring. Early systems were reactive, relying on static thresholds to trigger alerts. This gave way to the first generation of AIOps, which utilized machine learning for event correlation and root cause analysis. However, even these advanced systems remained largely “human-in-the-loop,” where the AI identified a problem, but a person had to decide and act on the solution.

Agentic AIOps represents a paradigm shift where the AI moves from an advisor to a doer. Unlike traditional automation, which follows a rigid, pre-defined script (e.g., “if X, then do Y”), agentic systems utilize the reasoning capabilities of LLMs to handle “non-deterministic” scenarios. These agents can interpret natural language incident reports, query multiple databases to gather context, and generate a step-by-step remediation plan that adapts to the specific nuances of the failure.

Methodology: Reasoning, Tool-Use, and Grounding

The architecture of a modern agentic AIOps system, such as LogicMonitor’s “Edwin AI,” relies on three core pillars: reasoning, tool-use, and grounding.

Strategic Reasoning and Planning

The “brain” of the agent is the LLM, which processes incoming alerts through a reasoning framework—often employing the “ReAct” (Reason + Act) pattern. When an incident occurs, the agent first decomposes the problem into smaller, manageable sub-tasks. It formulates a hypothesis about the root cause and identifies the necessary information required to validate that hypothesis.

Dynamic Tool-Use

To act on its reasoning, the agent must be able to interact with the environment. This is achieved through “function calling” or tool-integration. An agent might have access to a suite of tools, including:

• Infrastructure APIs: To restart services, scale resources, or modify configurations.
• Knowledge Bases: To retrieve historical documentation or runbooks.
• Communication Platforms: To update Slack channels or create ServiceNow tickets.

The Grounding Requirement

A critical challenge in applying generative AI to IT operations is “hallucination.” To ensure the agent makes decisions based on facts rather than probability, the methodology emphasizes “grounding” via Retrieval-Augmented Generation (RAG). The system feeds the LLM real-time telemetry from LogicMonitor alongside enterprise-specific runbooks. This ensures that the agent’s reasoning is constrained by the actual state of the infrastructure and the organization’s approved operating procedures.

Implementation: The Agentic Maturity Model

Adopting agentic AIOps is not an “all-or-nothing” proposition; it follows a maturity curve that balances autonomy with risk management.

1. Assisted Mode: The agent acts as a co-pilot, summarizing incidents and suggesting remediation steps to a human operator for approval.
2. Supervised Autonomy: The agent executes low-risk tasks autonomously (e.g., clearing disk space) while requiring permission for higher-impact changes (e.g., rebooting a production database).
3. Full Autonomy: The system operates independently within strictly defined guardrails, only involving humans for unprecedented or catastrophic failures.

This tiered approach allows organizations to build trust in the agent’s decision-making while gradually reducing the cognitive load on Site Reliability Engineering (SRE) teams.

Consequences for Enterprise IT and the Workforce

The shift toward agentic operations necessitates a change in the mindset of IT leadership. The focus moves from “managing tasks” to “managing outcomes.” The role of the human operator evolves from a manual troubleshooter to a “curator of intent.” Engineers will spend less time reacting to pagers and more time defining the policies, objectives, and constraints within which the agents must operate.

Furthermore, the integration of LogicMonitor with platforms like Worldwide Technologies (WWT) and NTT highlights a growing ecosystem of partnerships designed to provide the testing grounds (labs and POVs) necessary for enterprises to validate these autonomous workflows. The ultimate consequence is a significant reduction in noise—where thousands of alerts are distilled into a handful of actionable, or even self-resolving, insights.

Conclusion

Agentic AIOps marks the beginning of the autonomous enterprise. By combining the deep visibility of infrastructure monitoring with the sophisticated reasoning of generative AI, organizations can finally address the scale and speed requirements of modern digital services. While the technology is revolutionary, its success remains rooted in the fundamentals: high-quality data, clear governance, and a phased approach to building autonomous trust.

Links:

• AWS re:Invent 2025 – Agentic AIOps: How LogicMonitor Prepares Enterprises for AI-Driven IT (AIM232)
• LogicMonitor Official Website
• Deloitte Consulting – Emerging Technology Research
• Worldwide Technology (WWT) – LogicMonitor Partnership

Lecturers

Resh Desai, Zach Miller, and Jake Farrell presented this session. Resh Desai works as a solutions architect at Amazon Web Services, driving forward developments in secrets management. Zach Miller is a Senior Worldwide Security Specialist Solutions Architect at AWS, specializing in cryptography, keys, secrets, and certificates. Jake Farrell serves as Senior Director of Engineering at Acquia, which provides open digital experience platforms.

Abstract

The presentation sheds light on the evolution of secrets management, highlighting AWS Secrets Manager as a central tool for handling the complete lifecycle of sensitive credentials. It weighs the advantages and drawbacks of centralized versus decentralized approaches, outlines key capabilities like encryption, automated rotation, cross-region replication, and high-volume retrieval, and details Acquia’s comprehensive migration efforts. In addition, it explores strategies for multi-tenant separation, patterns for Kubernetes integration, future synergies with agentic AI, and the latest service improvements that support third-party rotations and easier container-based deployments.

Core Functionalities of AWS Secrets Manager

AWS Secrets Manager provides a purpose-built service dedicated to managing the entire lifecycle of application secrets, database credentials, and API keys, setting it apart from IAM for identity management or KMS for cryptographic operations. By design, every secret undergoes envelope encryption with AWS-managed KMS keys, though users can opt for customer-managed keys to support scenarios such as cross-account sharing.

This setup integrates smoothly with CloudTrail to deliver thorough auditing of all actions, from creation and modification to deletion. Automation through Lambda enables rotation schedules that align precisely with enterprise policies, whether set at 30 or 90 days. For resilience, multi-region replication ensures secrets remain available during regional failovers. The service handles up to 10,000 transactions per second for retrieval, further enhanced by an open-source agent that implements caching with configurable time-to-live periods, thereby improving both efficiency and the overall developer experience.

Together, these features create a secure and traceable environment that integrates seamlessly with the wider AWS security landscape.

Navigating Centralized and Decentralized Deployment Choices

When designing secrets storage, architects must decide between consolidating secrets in a single dedicated account or distributing them closer to the applications that consume them. Centralized configurations often resonate with organizations in regulated sectors, as they allow for standardized practices in naming, tagging, and permission enforcement—typically achieved through enforced CI/CD pipelines or bespoke abstraction layers. Such consistency bolsters monitoring and control across the enterprise, although it requires significant initial investment in development and can introduce latency when adopting newly released capabilities.

On the other hand, a decentralized model empowers individual application teams to manage secrets directly via consoles or SDKs, offering greater adaptability to unique requirements. This approach streamlines onboarding and accommodates specialized needs more naturally, but it calls for robust supplementary governance to ensure alignment with broader standards.

In practice, the ideal configuration depends on factors like secret creation processes, ongoing management, replication demands, access patterns, and visibility needs, reflecting insights gathered from diverse customer experiences rather than a one-size-fits-all rule.

Acquia’s Migration Experience and Multi-Tenant Architecture

Acquia maintains oversight of over 300,000 distinct secret paths distributed across multiple AWS accounts, supporting millions of daily ephemeral pod instances and tens of thousands of hourly API interactions. Moving away from older systems required careful categorization of secrets into groups such as customer-supplied elements (including third-party tokens and environment variables), internal service communications, and emerging hybrid forms suited to AI agents.

To manage this complexity, Acquia developed a custom fronting API that applies type-specific rules for validation, scoping, and lifecycle policies, such as mandatory rotation or timed expiry. Rigorous least-privilege principles ensure complete separation between platform operations and customer data. For delivery into runtime environments, the organization relies on open-source components like the External Secrets Operator combined with AWS CSI drivers, which synchronize and inject secrets into Kubernetes as variables, configuration templates, or command-line flags. Strategic caching layers further reduce direct API calls, delivering noticeable gains in speed and expense control.

Through this disciplined, layered framework, Acquia achieves robust multi-tenancy while addressing gaps that IAM alone cannot fully cover in interconnected service scenarios.

Future Directions in Agentic AI Collaboration

Looking ahead, Acquia’s designs feature an AI gateway that provides a unified point for observing model invocations routed through Amazon Bedrock, complemented by a standardized factory for quickly provisioning secure agents. By embedding Secrets Manager deeply, the platform enables on-demand injection of properly scoped credentials, allowing smooth evolution alongside emerging AI features without compromising protective measures.

This ongoing partnership with AWS has yielded tangible benefits in operational streamlining, lower maintenance burdens, and enhanced overall performance.

Latest Service Developments and Their Wider Impact

Innovations continue to simplify adoption in container environments, with EKS add-ons now automating the installation and configuration of CSI drivers. The introduction of managed external secrets brings one-click rotation capabilities to external providers like Salesforce, removing the need for custom scripting and eliminating risks of desynchronization.

Native integrations now span more than 55 AWS services, making secret management largely invisible to end users. These progresses reduce entry barriers to advanced security practices, enabling teams to concentrate on innovation even as autonomous systems increase demands on privilege management.

In essence, effective secrets governance forms the bedrock of durable, expandable systems vital for both current operations and forthcoming intelligent workloads.

Links:

• Lecture Video
• Jake Farrell on LinkedIn
• Acquia Official Website

Lecturer

Elizabeth Fuentes is a Senior Developer Advocate at Amazon Web Services (AWS), specializing in the intersection of Artificial Intelligence and DevOps practices. With extensive experience in cloud architecture and software engineering, Elizabeth focuses on how Generative AI can streamline complex CI/CD pipelines and enhance Site Reliability Engineering (SRE). She is a key contributor to AWS educational initiatives, having co-developed advanced courses on AI-driven automation. Joining her is Laas Alina, a software architect and open-source enthusiast who focuses on implementing multi-agent systems and the Model Context Protocol (MCP) to solve observability challenges at scale.

Abstract

As software systems grow increasingly distributed and complex, traditional observability—centered on manual log analysis and reactive dashboards—is becoming insufficient. This article explores the paradigm shift toward AI-driven observability, where Generative AI serves not just as a query tool, but as an active participant in failure detection, correlation, and resolution. By leveraging Amazon Bedrock and Amazon Q, organizations can transition from “reactive” to “predictive” DevOps. The discussion analyzes the methodology of building AI agents that simulate architectural stress, automatically explain multi-layered failures, and provide traceable, actionable recommendations. We examine the implementation of the Model Context Protocol (MCP) in establishing sophisticated multi-agent systems (MAS) that transform raw data into contextual understanding, ultimately reducing the Mean Time to Resolution (MTTR) and enhancing systemic resilience.

The Evolution of Observability: From Metrics to Contextual Understanding

The traditional pillars of observability—metrics, logs, and traces—provide the “what” of a system’s state but often fail to provide the “why” in real-time. In high-velocity DevOps environments, the sheer volume of telemetry data can overwhelm human operators, leading to “alert fatigue” and delayed responses to critical incidents. Elizabeth posits that the integration of Generative AI marks the fourth pillar of observability: Contextual Intelligence. This evolution moves the industry beyond simple threshold-based monitoring toward systems that understand the semantic relationship between a failed deployment, a spike in latency, and a specific line of code.

By utilizing Large Language Models (LLMs) through Amazon Bedrock, DevOps teams can ingest vast amounts of unstructured log data and receive summaries that highlight anomalies that might be missed by traditional regex-based filters. The methodology involves training the AI to recognize “normal” operational patterns and identifying deviations not just by value, but by the intent of the system’s behavior. This contextual layer allows for a more nuanced interpretation of system health, where the AI can distinguish between a benign resource spike and a precursor to a cascading failure.

Architecting AI Agents for Predictive Troubleshooting

The transition to AI-driven observability is characterized by the deployment of “Micro-agents”—specialized AI entities designed to handle specific segments of the DevOps lifecycle. These agents operate within a Multi-Agent System (MAS), where they collaborate to solve complex incidents. For instance, a “Monitoring Agent” might detect a performance degradation and immediately trigger a “Diagnosis Agent” to correlate the event with recent CI/CD pipeline changes.

Elizabeth and Laas Alina emphasize the importance of the Model Context Protocol (MCP) in this architecture. MCP acts as the communication backbone, allowing agents to share context without losing the “lineage” of a decision. When an AI agent recommends a specific architectural change or a rollback, it must provide clear traceability. This is crucial for maintaining trust in automated systems. The agents do not operate in a vacuum; they interact with tools like Amazon Q to provide developers with instant explanations of failures directly within their Integrated Development Environment (IDE) or chat interface.

// Example of an AI-driven Observability Agent Configuration
agent:
  name: "IncidentDiagnosticAgent"
  provider: "AmazonBedrock"
  model: "claude-3-sonnet"
  capabilities:
    - log_analysis
    - metric_correlation
    - trace_summarization
  mcp_config:
    protocol_version: "1.0"
    shared_context: "deployment_metadata"
  safety_guardrails:
    - max_token_usage: 4000
    - human_in_the_loop_required: true

Transforming CI/CD through Generative AI and Simulation

Beyond reactive troubleshooting, AI-driven observability empowers proactive system design. One of the most innovative concepts discussed is the use of AI agents to simulate “stress-test” scenarios within a digital twin of the production environment. These agents can intentionally inject failures—similar to Chaos Engineering—and then observe how the observability stack responds. This creates a feedback loop where the AI helps engineers identify “blind spots” in their monitoring before a real incident occurs.

Furthermore, Generative AI transforms the CI/CD pipeline by automatically generating “failure explanations.” Instead of a developer sifting through a 5,000-line build log, Amazon Q can provide a concise summary: “The build failed because the new database schema in commit X is incompatible with the connection pool settings in environment Y.” This level of automated insight accelerates the “inner loop” of development, allowing engineers to focus on innovation rather than infrastructure archeology.

The Human-AI Partnership: Strategic Implications

A common concern in the industry is the replacement of human engineers by AI. However, Elizabeth argues that the future belongs to the “augmented engineer.” AI is a force multiplier that automates the repetitive, “drudge work” of observability—log parsing and initial triage—allowing human experts to focus on high-level strategy and complex architectural decisions. The goal is to transform teams from being “reactive” (fighting fires) to “proactive” (preventing fires).

Implementing these systems requires a cultural shift toward AI-literacy within DevOps teams. Organizations must establish safety guardrails to ensure that AI-driven recommendations are validated and that automated actions (like auto-remediation) have clear rollback paths. By embracing AI as a strategic tool, DevOps and SRE teams can achieve a level of operational excellence that was previously unattainable, ensuring that as systems grow in scale, their reliability grows in parallel.

Links:

• Amazon Bedrock Service Page
• Amazon Q Developer Information
• AWS DevOps Solutions
• Model Context Protocol (MCP) Specification

Lecturer

Mortaza Chowri is the Head of Product Management for the AWS Transform team, where he leads the development of next-generation tools for complex workload migration. He is an expert in leveraging generative AI to automate technical debt reduction for large-scale enterprises. Joining him are Alexi and Ravi, who serve as senior architects within the AWS Transform division, specializing in agentic AI implementation and the creation of composable system frameworks. The session also features strategic insights from the leadership team at Capgemini, who collaborate with AWS to deliver industry-specific modernization solutions for global banking and automotive clients.

Abstract

Enterprise modernization is frequently paralyzed by the extreme complexity of legacy systems, particularly decades-old mainframes and aging Windows-bound .NET applications. This article explores the innovative framework of AWS Transform, a centralized service that utilizes “Agentic AI” to automate and streamline the migration process. The methodology centers on the concept of composability, which allows AWS partners to integrate their proprietary industry knowledge and specialized tools with foundational AI agents. By utilizing a sophisticated chat-based interface and automated business rule extraction, the platform enables a seamless transition from legacy COBOL and .NET Framework 4.x to modern, cloud-native architectures. The analysis demonstrates how these composable agents create a continuous feedback loop that significantly reduces manual effort, improves documentation, and ensures business logic remains intact during high-risk migrations.

Context: The Burden of Technical Debt and Knowledge Atrophy

Many of the world’s most critical systems, particularly in finance and manufacturing, are still dependent on infrastructure built in the late 20th century. These legacy environments present three primary obstacles that prevent organizations from achieving modern agility. First, knowledge atrophy has become a critical risk, as the original architects of these mainframe systems have often retired, leaving behind “black box” applications that lack contemporary documentation. Second, the technical debt associated with older languages like COBOL is immense, as these systems were never designed to leverage modern cloud features such as serverless compute or elastic auto-scaling.

Third, the mission-critical nature of these systems creates a state of risk aversion, where the fear of breaking a core business process during a manual rewrite often leads to stagnation. AWS Transform was specifically developed to break this cycle of inertia. By providing a unified experience that integrates discovery, assessment, and modernization into a single platform, AWS allows enterprises to view their legacy code as an asset to be reimagined rather than a liability to be feared.

Methodology: Agentic AI and the Composable Framework

The core technical innovation of AWS Transform is the transition from static point solutions to a dynamic, “unified experience” powered by specialized AI agents. These agents are designed to perform complex technical tasks with a level of autonomy that far exceeds traditional automation scripts. The methodology is built upon several key pillars of agentic behavior. Discovery agents are tasked with automatically mapping technical artifacts, such as physical servers and complex database schemas, to their optimal cloud-native equivalents.

Modernization agents, specifically those tuned for mainframe environments, perform the difficult work of extracting business rules from legacy code. This process generates comprehensive documentation that allows current engineers to “comprehend” the underlying logic of systems they did not build. The most transformative aspect of this methodology is its composability for partners. AWS provides the foundational intelligence and large language models, while partners such as Capgemini can “compose” these with their own specialized knowledge bases and custom transformation rules. This enables the creation of industry-specific agents, such as a modernization assistant specifically optimized for banking regulations or complex automotive production logic.

Technical Analysis of Mainframe Rule Extraction

The implementation of these agents in real-world scenarios, particularly through the collaboration with Capgemini, highlights a sophisticated “forward engineering” approach. In this workflow, the AI agents first scan the legacy code to identify core business logic and immutable rules. This extraction phase is critical because it ensures that while the code is updated, the essential business functions remain perfectly intact. Following extraction, the reimagination phase begins, where these rules are integrated into a modern architecture that meets cloud-native standards for security and performance.

Practitioners interact with these systems through a chat experience within the AWS Transform interface, allowing them to query both the AI agents and integrated domain experts directly. This interaction model democratizes the modernization process, making it accessible to developers who may not have expertise in COBOL but are proficient in modern languages like Java or Python. The platform serves as a bridge, translating the “what” of legacy business logic into the “how” of modern cloud execution.

Outcomes: Efficiency, Consistency, and Continuous Learning

The deployment of composable AI agents has fundamentally altered the economics and speed of enterprise modernization. By automating the most labor-intensive parts of code comprehension and translation, organizations have reported a reduction in manual effort by as much as 80%. This allows teams to focus on high-value innovation rather than the repetitive task of line-by-line code migration. Furthermore, the platform ensures architectural consistency across a large organization, preventing the fragmentation that often occurs when different teams use varying migration tools.

One of the most significant consequences of this approach is the continuous improvement of the agents themselves. Every modernization task performed through the platform provides feedback data that enhances the underlying AI models. As these agents encounter more diverse enterprise environments, their ability to handle edge cases and complex business rules grows exponentially. This creates a virtuous cycle where each successful migration makes the next one faster and more reliable, effectively solving the problem of knowledge atrophy for the long term.

Conclusion

The shift toward agentic AI and composable architectures represents a milestone in the evolution of enterprise IT. AWS Transform provides a robust framework that allows organizations to tackle their most daunting legacy challenges with a level of confidence and speed that was previously impossible. By allowing partners to integrate their unique industry expertise into a centralized AI system, AWS has created a scalable ecosystem that transforms modernization from a risky, multi-year endeavor into a manageable and continuous strategic process.

Links:

• AWS Transform Service Overview
• Capgemini Mainframe Modernization
• AWS Partner Central
• Watch the Technical Deep Dive