/Events /AgentCon Washington DC 2025
AgentCon Washington DC 2025
This event is part of AgentCon, organized by Global AI Washington DC.
About
Join us for the AI Agents World Tour, a global series of one-day conferences designed exclusively for developers building the future with AI agents.
From San Francisco to Singapore, we’re bringing together leading engineers, researchers, and creators to explore the cutting edge of AI agent design, deployment, and integration. Whether you’re building intelligent assistants, autonomous systems, or next-gen developer tools, this event is your fast track to practical knowledge, hands-on demos, and real-world insights.
What to Expect:
- Deep-Dive Talks from AI pioneers and industry leaders
- Technical Workshops on building, deploying, and scaling agents
- Live Demos of powerful open-source frameworks and tools
- Networking with a global community of builders and innovators
This isn't just another AI event — it’s where developers meet to talk about real code.
Ready to build the future?
Sessions & tracks
Civic Agents: The Rise Of AI In Modern Public Service
Governments are starting to use AI agents to improve how services are delivered—from permits and public works to citizen support. These “Civic Agents” are helping staff work more efficiently and making public services easier to access.
In this session, we’ll look at real examples from local governments already using AI, and share a simple 5-step framework (Purpose, Pilot, Playbook, Production, Performance) for scaling these solutions. Whether you're in tech or public service, you’ll walk away with practical ideas to start or grow your AI journey.
Himanshu Goil is a visionary entrepreneur and technologist with over 20 years of experience in building innovative technology solutions and scaling SaaS ventures. He is the founder of Ignatiuz and the driving force behind several successful ventures, including ScoutFoto, MyLink, WebTalkx, Accelance Partners, and TechForGov—a platform dedicated to bringing responsible AI and automation to government agencies. A pioneer in artificial intelligence, Himanshu has led the development of Retrieval-Augmented Generation (RAG) systems, intelligent agents, and enterprise-grade AI solutions that deliver measurable impact. His work spans ground-up product innovation to large-scale IT transformations for public and private sector clients. Himanshu’s entrepreneurial journey began with securing early-stage funding for startups, showcasing his ability to turn bold ideas into reality. He is passionate about fostering collaboration within diverse teams, optimizing processes, and delivering value through cutting-edge digital products and AI-driven user experiences.
AI-Powered Legacy Modernization: Turning Technical Debt into Enterprise Agility
Legacy systems continue to drain IT budgets, slow transformation, and increase regulatory risk. Recent research shows that nearly three-quarters of financial institutions cite outdated technology as the biggest barrier to innovation, with 62% identifying it as a key compliance challenge. Traditional modernization approaches often lengthy, costly, and risky struggle to keep pace with today’s business demands.
This session introduces an AI-driven modernization framework that leverages transfer learning and neural networks to accelerate transformation while safeguarding mission-critical business logic. By automating test suite generation, contextual documentation, security scanning, and deployment packaging, the approach reduces errors, enhances compliance alignment, and delivers production-ready systems faster.
Drawing on case studies, we’ll explore best practices for phased rollouts, governance structures, and continuous feedback loops that mitigate risks and maximize adoption. Attendees will also gain insight into emerging trends, including predictive performance optimization, autonomous architecture recommendations, and continuous lifecycle management advances that redefine modernization as an ongoing enabler of agility and innovation rather than a one-off cost center.
Participants will leave with practical strategies and data-backed insights to reposition modernization as a strategic driver of competitive advantage in an AI-first enterprise landscape.
Nagaraju Gaddigopula is a seasoned Senior Engineering Manager with over 21 years of experience leading high-performing software engineering teams and delivering innovative, scalable, and resilient technology solutions. Currently serving as Sr. Manager, Software Engineering at Capital One, Nagaraju plays a pivotal role in shaping technical strategy, overseeing delivery execution, and fostering cross-functional collaboration to build fraud prevention applications and models that safeguard millions of customers. Throughout his career at Capital One, Nagaraju has advanced from Principal Software Engineer to Manager, and now Senior Manager, consistently driving complex projects that modernize systems and strengthen fraud detection capabilities. His leadership was instrumental in developing the Customer Servicing Agent application, implementing advanced fraud prevention systems, and influencing engineering best practices across the enterprise. Before joining Capital One, Nagaraju contributed to several large-scale transformation initiatives, including the Registry of Motor Vehicles Modernization Program in Boston, the Credit Card Core Platform Modernization at Bank of America, and the AT&T Marketing Rules Engine at Convergys. His expertise in designing and implementing microservices-based, event-driven architectures and enterprise-scale platforms has been critical to the modernization of financial, telecom, and government systems. An innovator at heart, Nagaraju holds a U.S. patent on real-time generation of challenge questions for fraud detection, alongside published patents in identity verification and behavioral biometrics. His technical depth spans cloud computing (AWS Certified Solutions Architect & Developer), Java/J2EE, Python, NodeJS, SQL, and advanced security practices (Certified Ethical Hacker). With a Master’s degree in Computer Applications and multiple professional certifications, Nagaraju is committed to mentoring engineering talent, driving digital transformation, and aligning technology strategies with business growth. His leadership philosophy emphasizes innovation, agility, and continuous improvement, making him a trusted leader in building next-generation systems that balance security, scalability, and customer experience.
Scaling Ethical AI Agents: From Prototype to Production in Government Digital Transformation
Deploying AI agents at scale in government systems requires balancing performance optimization with ethical considerations and environmental sustainability. This technical session explores practical frameworks for transitioning agent prototypes into production-ready systems serving millions of citizens. Drawing from implementations across 217 government organizations, we'll demonstrate how to architect agent systems that maintain fairness metrics while achieving operational efficiency. The presentation covers critical implementation challenges including bias detection in autonomous decision-making, building trust through interpretable agent behaviors, and optimizing computational resources for sustainability. We'll showcase code examples using Semantic Kernel for building ethically-aligned agents, implementing feedback loops for continuous improvement, and creating monitoring dashboards for agent transparency. Attendees will learn concrete strategies for addressing the "trust-privacy paradox" in citizen-facing agents through careful UX design and meaningful human oversight mechanisms. Practical demonstrations include architecting carbon-efficient agent systems that reduced emissions by 43% while maintaining performance, implementing fairness assessments for multi-agent workflows, and building evaluation frameworks for agent behavior in production. This session equips developers with tools and techniques for creating AI agent systems that scale responsibly, maintain public trust, and deliver measurable improvements in government service delivery while adhering to emerging regulatory frameworks and sustainability goals.Retry
Manichandra Sajjanapu is an accomplished Associate Director and Senior Software Engineer with over 11 years of experience leading transformative digital initiatives in both public and private sectors. Based in Washington, D.C., he specializes in architecting cloud-native solutions, modernizing enterprise applications, and driving technical innovation through emerging technologies. Currently serving as Associate Director at FINRA, Manichandra leads a high-performing engineering team in executing one of the organization's most significant digital transformations. He successfully consolidated multiple legacy regulatory systems into a unified, scalable cloud-native platform, achieving a remarkable 70% reduction in operational costs while enhancing regulatory compliance capabilities for FINRA, SEC, NASAA, and state regulators. His innovative micro-frontend architecture leveraging AWS serverless technologies and GraphQL has set new standards for system scalability and performance. A recognized innovator, Manichandra won second place at FINRA's hackathon for developing an AI-based Document Redaction Tool, which was subsequently adopted and funded by the R&D department. His expertise spans cutting-edge technologies including generative AI, AWS cloud services, and modern JavaScript frameworks, while maintaining deep knowledge of enterprise Java and DevOps practices. Beyond his corporate achievements, Manichandra is an active contributor to the global technology community. He has made significant contributions to the open-source PrimeNG component library, resolving critical accessibility issues that benefit thousands of users worldwide. His work on federal accessibility standards (Section 508 compliance) during his tenure at the Equal Employment Opportunity Commission has positively impacted government services nationwide. Additionally, he has contributed to internet standards through official IANA media type registrations. Manichandra's technical leadership extends beyond code to mentoring and community service. He volunteered as a programming teacher with Career Catchers Inc., introducing underserved youth to technology careers. His approach combines technical excellence with strategic thinking, consistently delivering solutions that drive measurable business value while advancing technological innovation. With expertise spanning AI/ML, cloud architecture, regulatory technology, and accessibility compliance, Manichandra continues to shape the future of enterprise software development through his leadership at FINRA and contributions to the broader technology ecosystem.
Keynote : Agents of Tomorrow: Building the Next Generation of Intelligence
We stand at the edge of a profound shift in artificial intelligence. Over the last five years, generative AI has moved from novelty to necessity—transforming how we create, code, and collaborate. Now, a new frontier is emerging: AI agents. Unlike traditional tools that wait for instructions, agents can perceive, decide, and act toward goals—expanding the boundaries of what humans and machines can achieve together.
In this keynote, we’ll explore the evolution from copilots to fully agentic systems, highlight breakthroughs that are reshaping industries, and imagine the future horizons where autonomous agents redefine productivity, creativity, and discovery. Most importantly, we’ll discuss the role of humans in this new era—not as bystanders, but as leaders guiding how agents operate, align with our values, and amplify our potential.
The Agents of Tomorrow are here—and the future will be built by those bold enough to partner with them.
Henk is a Cloud Advocate specializing in Artificial intelligence and Azure with a background in application development. He is currently part of the AI cloud advocate team and based in the Netherlands. Before joining Microsoft, he was a Microsoft AI MVP and worked as a software developer and architect building lots of AI powered platforms on Azure.
Build Multimodal Agents to talk with your data & take actions using Azure AI
An agent is a powerful AI companion that handles a range of interactions and tasks—from managing complex conversations to autonomously deciding the best course of action based on its instructions and context. A multimodal agent takes this a step further by seamlessly interacting across text, images, video, and audio, all at the same time.
In this demo-driven session, Microsoft AI and Business Applications MVP and Microsoft Certified Trainer Prashant G Bhoyar will explore the technical intricacies of building robust multimodal agents. They'll provide practical guidance on creating scalable solutions that integrate Azure SQL, Cosmos DB, and Azure AI, tailored to meet real-world industry requirements.
This session will cover:
• What are Multimodal Agents? • Overview of Azure AI Services • Creating Enterprise-Level Multimodal Agents: Practical guidance for developing agents that interact with your data and take actions using Azure SQL, Cosmos DB, and Azure AI. • Best Practices
Whether you're building your first AI agent or scaling an enterprise-grade solution, this session offers actionable insights to help you succeed.
Prashant G Bhoyar is a Microsoft AI & Business Applications MVP and Microsoft Certified Trainer (MCT). Currently, he works as an AI architect in the Office of the Chief Technology Officer at Applied Information Sciences (www.ais.com). Prashant is a leading AI Architect and trusted advisor specializing in Azure OpenAI, Conversational AI, Applied AI, AI Agents, Intelligent Business Process Automation, Azure AI, Microsoft Power Platform, Copilot Studio, and Microsoft 365. He co-authored "PowerShell for Office 365" and was the technical reviewer for "Pro SharePoint 2013 Administration." Prashant is on the leadership committee for AI Fest, AI & ML User Group, Northern Virginia Data Platform User Group, and DC Metro Microsoft 365 User Group. As a renowned international speaker, he frequently presents at technical conferences. Additionally, Prashant was awarded the "Antarctic Service Medal of the United States of America" for his outstanding service in Antarctica. Microsoft MVP Profile Link : https://mvp.microsoft.com/en-us/PublicProfile/5002595?fullName=Prashant%20G%20Bhoyar
Ask Us Anything About AI Agents
Curious about AI Agents? Bring your questions, big, small, or weird, and we’ll answer them live. No jargon, no gatekeeping, just real talk about how AI Agents works, what it can (or can’t) do, and where it’s headed. Nothing’s off-limits, ask away!
Prashant G Bhoyar is a Microsoft AI & Business Applications MVP and Microsoft Certified Trainer (MCT). Currently, he works as an AI architect in the Office of the Chief Technology Officer at Applied Information Sciences (www.ais.com). Prashant is a leading AI Architect and trusted advisor specializing in Azure OpenAI, Conversational AI, Applied AI, AI Agents, Intelligent Business Process Automation, Azure AI, Microsoft Power Platform, Copilot Studio, and Microsoft 365. He co-authored "PowerShell for Office 365" and was the technical reviewer for "Pro SharePoint 2013 Administration." Prashant is on the leadership committee for AI Fest, AI & ML User Group, Northern Virginia Data Platform User Group, and DC Metro Microsoft 365 User Group. As a renowned international speaker, he frequently presents at technical conferences. Additionally, Prashant was awarded the "Antarctic Service Medal of the United States of America" for his outstanding service in Antarctica. Microsoft MVP Profile Link : https://mvp.microsoft.com/en-us/PublicProfile/5002595?fullName=Prashant%20G%20Bhoyar
As Chief Technology Officer at AIS, Brent Wodicka leads the company’s overarching technology vision and strategy. In his role, Brent continues to drive technological innovation, ensuring the development and implementation of advanced solutions that enhance business and mission outcomes for AIS customers. His leadership is instrumental in fostering the growth of technical talent across the organization.
Rima Reyes is a Principal Product Manager at Microsoft, leading innovation within the Copilot, Agents and Platform Ecosystem (CAPE) Engineering team. With over 20 years of experience building solutions on the Microsoft platform—including six years at the White House—Rima brings deep expertise in architecting and building scalable, AI-powered solutions that transform how people work. She focuses on agentic AI, driving platform integrations for Microsoft 365 Copilot and Copilot Studio to enable the development and deployment of intelligent agents across Microsoft’s most strategic customers, including the U.S. Government. Outside of work, Rima enjoys watching Golden Girls reruns while using Microsoft Copilot to design her next knitting project.
Henk is a Cloud Advocate specializing in Artificial intelligence and Azure with a background in application development. He is currently part of the AI cloud advocate team and based in the Netherlands. Before joining Microsoft, he was a Microsoft AI MVP and worked as a software developer and architect building lots of AI powered platforms on Azure.
MCP Demystified: The New Standard for AI and App Communication
Model Context Protocol (MCP) is emerging as the new standard for seamless AI-to-application communication. This session will demystify MCP, showing how it simplifies integrations, reduces complexity, and powers smarter, context-aware solutions.
Lead Software Engineer | Crafting Highly Reliable & Scalable AI Solutions | Innovating with Cutting-Edge Technologies which makes positive impact on society.
Are AI Agents the Ultimate Confused Deputy: Exploring AI Agent Authorization Issues
AI agents have unlocked limitless use cases, but at the same time, they have also introduced new threats as AI agents are now given extensive permissions to data sources and mutating actions through APIs. This talk dives into some of the real-world authorization issues affecting AI agents to discover the common patterns and causes, e.g.
- Github's MCP vulnerability leading to private repo access link
- VS Code Co-pilot's RCE CVE-2025-53773 link
The talk also discusses the possible mitigations such as proper isolation, least privilege, use of OAuth, and limiting agent scope.
I am currently an Application Security engineer at IronClad, where I am building a new Application Security Program. Before that, I was also an Application Security Engineer at Amazon for ~ 4 years, and during this period, I reviewed and collaborated on 500+ AWS services/features/tools. You can check my blog at https://medium.com/@mohamed.osama.aboelkheir
Scan, Extract, Automate: Large Files Meet Low-Code AI
What do you get when you mix scanned PDFs, legal jargon, and a developer’s itch to automate? A document-processing AI agent that does the heavy lifting—so humans don’t have to. In this session, we’ll walk through how we built a low-code solution using Microsoft Copilot Studio, Power Automate, and Dataverse to extract key fields from large files and turn them into structured, searchable data. This solution tackled OCR challenges, metadata extraction, and downstream automation—all without writing a mountain of code. You’ll learn how to orchestrate AI flows, handle fuzzy document layouts, and build scalable workflows that make your work teams cheer. If you’ve ever wanted to turn a dusty PDF into a dynamic data source, this one’s for you.
Rima Reyes is a Principal Product Manager at Microsoft, leading innovation within the Copilot, Agents and Platform Ecosystem (CAPE) Engineering team. With over 20 years of experience building solutions on the Microsoft platform—including six years at the White House—Rima brings deep expertise in architecting and building scalable, AI-powered solutions that transform how people work. She focuses on agentic AI, driving platform integrations for Microsoft 365 Copilot and Copilot Studio to enable the development and deployment of intelligent agents across Microsoft’s most strategic customers, including the U.S. Government. Outside of work, Rima enjoys watching Golden Girls reruns while using Microsoft Copilot to design her next knitting project.
Srinivas Varukala is an experienced professional currently working as a Sr. Customer Engineer (formerly known as Premier Field Engineer) at Microsoft. His focus is on development covering Microsoft 365 workloads, Microsoft Graph, Azure PaaS, Power Platform etc. One of my recent contributions to the community is the 30 Days of Microsoft Graph blog series. Thinking outside the box and producing creative solutions to problems is his strong forte. He also enjoy rapid prototyping and helping customers achieve more every day.
A Developer’s Playbook for Operating AI Agents at Scale
Building autonomous agents is exciting, but once they’re live they can drift off-policy, consume stale data, or behave in ways developers never intended. As teams move from prototypes to production, the challenge isn’t building agents, it’s running them responsibly.
In this talk, SUPERWISE Chief Product Officer John Leschorn will share a developer-first playbook for taking agents from demo to reliable, scalable systems. Drawing on lessons from deploying agents across manufacturing, construction, commerce/retail, healthcare and Enterprise IT, Russ will introduce a four-step operating framework:
Experiment: Start small with pilots that surface edge cases early.
Observe: Add real-time monitoring for drift, anomalies, and unintended behaviors.
Control: Implement guardrails and policies that keep agents aligned with business goals and compliance requirements.
Scale: Confidently expand across frameworks (LangChain, CrewAI, Dify, etc.) without losing oversight.
The session will include practical examples of how developers can integrate observability, testing, and guardrails directly into agent workflows, without slowing down innovation.
Attendees will walk away with a framework they can apply immediately: a roadmap to build, test, and scale agents that are not only powerful, but also safe, auditable, and production-ready.
Key Takeaways:
The top three ways agents fail in production (and how to catch them).
A reusable framework (Experiment → Observe → Control → Scale) for operating agents.
How to integrate observability and guardrails into today’s leading agent frameworks.
True leadership transcends the day-to-day; it's about crafting a vision, committing to the journey, and inspiring an entire organization to realize that future together. My leadership philosophy is deeply rooted in these ideals, informed by continuous learning and experiences throughout my career. These experiences have taught me the profound impact of empowerment, humility, and strategic insight on driving sustainable growth and fostering a culture of innovation. Key to this journey has been the recognition of the value in nurturing talent from within our organization. By prioritizing the development of our team, we've unlocked incredible potential, leading to innovation and a strong sense of loyalty and belonging. Each day, I strive to live by these principles, seeking not just to lead but to inspire those around me to share in our collective vision. The lessons learned have also highlighted the importance of mentorship as a pivotal component of leadership. Implementing structured mentorship programs has enabled valuable knowledge exchange, accelerating the personal and professional growth of our emerging leaders. This approach ensures our leadership pipeline is not only robust but also aligned with our organizational values and mission. Furthermore, the significance of aligning with the right partners and collaborators who share our vision and values cannot be overstated. Such partnerships have amplified our capacity to achieve our goals, reinforcing the idea that true progress is a collective effort. It's through this synergy that we’ve been able to navigate the complexities of the business landscape effectively. My experiences have emphasized that leadership is about more than achieving objectives; it's about cultivating an environment where every individual feels valued and motivated to contribute to our shared goals. This commitment to developing talent and fostering a culture of continuous learning and mentorship has been invaluable. As we move forward, the insights gained from these experiences will continue to guide our approach, ensuring that we not only meet our current objectives but also lay the foundation for long-term success. Leadership, in essence, is about building a legacy of resilience, growth, and innovation. By championing a vision, embracing the journey, and inspiring our organization, we're not just achieving milestones—we're shaping the future.
“Agentic AI and Azure Energy: Scaling Autonomous Systems for Real World Impact”
Abstract: The next wave of Agentic AI is about systems that can operate in real-world, high-stakes environments. This talk will focus on how Microsoft’s Azure AI, IoT, Edge, and Digital Twins capabilities can be used to create agents that monitor infrastructure, predict failures, coordinate maintenance, and optimize operations. We will walk through scenarios in energy grids, manufacturing floors, and smart city systems, showing how agents can learn and improve over time. The session will also explore the engineering challenges like latency, safety, and governance and share strategies to overcome them.
Accomplished Engineering Leader with 21+ years of experience architecting and delivering large-scale cloud-native digital solutions Deep background in engineering, API and Microservices development, and enterprise-wide transformations from legacy to modern platforms (including AWS, Azure, GCP, OpenShift). Demonstrated success advising CXO stakeholders on technology roadmaps, application modernization, and next-gen digital strategies. Adept at consultative sales leadership with full P&L and margin accountability across global engagements. Passionate about GenAI and AgenticAI innovation to embed AI-driven capabilities into financial services offerings.
The Inquisitive Agent: Curing RAG's Ambiguity with Autonomous Dialogue
For all their power, most RAG systems today are locked in a monologue. They listen to a query, retrieve what they think is relevant, and speak their answer. If the initial query is vague, the monologue fails. The future of intelligent assistance, however, is not a monologue; it's a rich, collaborative dialogue.
This session dives deep into the architecture of AID (Assisted Intelligent Dialogue), an Agentic system we built and deployed at Cisco to make this future a reality. We've designed an system that doesn't just search for answers, but actively seeks clarity. Instead of a linear pipeline, our agents operates in a cognitive loop, embodying different roles to deconstruct ambiguity and co-create understanding with the user.
We will walk you through its autonomous reasoning process:
The Agent as the Detective (Ambiguity Assessment): When a query arrives, the agent’s first task is to assess the evidence. It doesn't immediately jump to conclusions. Instead, it analyzes the query for semantic ambiguity and potential for misinterpretation, identifying cases where a simple vector search would likely fail.
The Agent as the Strategist (Hypothesis and Reasoning): Upon detecting ambiguity, the agent consults its "knowledge model"—a rich knowledge graph. Here, it maps the user's query onto the graph to explore interconnected concepts and relationships. It generates multiple hypotheses about the user's true intent and identifies the critical piece of missing information needed to validate one of them. This is the agent’s core reasoning phase.
The Agent as the Interviewer (Probing with Purpose): Armed with this insight, the agent reaches its "moment of truth." It plans and executes a dialogue action, formulating a targeted, clarifying question. This isn't a generic "Can you rephrase?"; it's a precise probe designed to efficiently collapse the space of uncertainty and guide the user toward the correct context.
The Agent as the Expert (High-Fidelity Resolution): Once the user responds, the agent integrates this new, crucial context. With the ambiguity resolved, it can now perform a high-fidelity retrieval from a precisely defined subgraph, delivering an accurate, actionable answer that solves the user's true underlying problem.
Join us to learn how to build agents that don't just answer, but actively listen, reason, and understand. This is the blueprint for the next generation of truly helpful, conversational AI.
What Attendees Will Learn: a)Design Pattern: How to architect an Agentic "clarification loop" to move beyond brittle, single-shot RAG systems. b)Cognitive Architecture: How to leverage a graph as a "world model" for an agent to reason about information and generate hypotheses. c)Practical Implementation: Techniques for an agent to autonomously decide when to ask a question and how to formulate it with purpose. d)Human-Agent Interaction: Principles for designing effective, low-friction dialogues that guide users without causing fatigue. e)From Prototype to Production: Lessons learned from deploying this Agentic system at enterprise scale at Cisco to solve daily customer issues, complete with a look at our evaluation metrics.
Rajarshee Dhar is a Technical Leader in the CX org within Cisco. He is dedicated to leveraging Artificial Intelligence to transform collaboration experiences and develop impactful, real-time solutions for complex business challenges. With expertise spanning AI/ML, RAG, and GraphRAG, he contributes to projects aimed at enhancing data retrieval, optimizing AI workflows, and building advanced knowledge systems. As an inventor with over 10 patents, Rajarshee is passionate about applying his knowledge to make a tangible impact particularly in the intersection of collaborative solutions and AI. In his free time, he enjoys exploring new technologies, hiking, and photography.
I am Sr Technical Leader in Cisco Customer Experience for Collaboration Technology. Currently focused on Gen AI-based innovation and its impact on the customer experience within Cisco Org. I have been a speaker in Cisco Live and have about 4 Patents pending in the US.
This is how it looked
Explore AgentCon
AI Agents Developer Conference
AgentCon made possible by:
