Manoj Agarwal
Chief Architect at Zeta Global
Cupertino, California, United States
Actions
Manoj Agarwal is Chief Architect and SVP of Engineering at Zeta Global (NYSE: ZETA), where he leads the architecture of Athena OS, the company's agentic AI platform, from its MCP gateway and skills registry to the durable runtimes that put autonomous agents into production. His career spans Amazon, Salesforce, Microsoft, and Walmart, building large-scale distributed systems, data platforms, and identity infrastructure, and he holds 13 patents. He speaks and writes regularly on agentic AI, API design, and the realities of running agents at scale.
Links
Area of Expertise
Topics
Identity supergraph: Building Trillion-Scale Identity Graph for Hyper-Personalization
In today's digital landscape, delivering hyper-personalized experiences is paramount for marketing and advertising platforms. Achieving this requires constructing and managing expansive identity graphs capable of real-time identity resolution across billions of identities and trillions of relationships. This session delves into the methodologies and technologies essential for building such colossal identity graphs, drawing insights from industry leaders like Zeta Global and others in the marketing and ad tech domain.
Empowering Modern Marketing: Building and Managing AI Agents in the Zeta Marketing Platform
In the rapidly evolving landscape of marketing and advertising technology, the integration of Artificial Intelligence (AI) has become pivotal in delivering personalized and efficient customer experiences. This talk will delve into the development and management of AI Agents within the Zeta Marketing Platform, highlighting how these agents automate processes, analyze data, and enhance customer interactions. We will explore strategies for managing data access to ensure privacy and compliance, and demonstrate how these AI Agents empower marketers to achieve unprecedented efficiency and effectiveness.
Designing APIs for Autonomous Agents
For three decades we've designed APIs for one kind of consumer: code written by a human who read the documentation before integrating. REST verbs, resource granularity, OpenAPI schemas, status codes, OAuth scopes, all of it assumes a developer makes the binding decisions at integration time and the running client merely executes them.
Agentic AI breaks that assumption. The consumer is now a non-deterministic reasoner that discovers capabilities, selects among them, and composes calls at runtime, with no human reviewing the request before it's made. An LLM doesn't read your docs; it reads your tool description, infers your parameters, and recovers, or doesn't, from your error messages. This session examines, concretely, what breaks at every layer of conventional API design when the caller is an agent, and the patterns that hold up under it.
We'll work through: why fine-grained CRUD surfaces push agents into brittle multi-step orchestration, and where intent-shaped operations outperform them; how schemas and descriptions become the agent's reasoning context, not just validation rules; designing error responses an agent can act on, retry, reformulate, escalate, rather than HTTP codes it merely logs; idempotency and confirmation patterns for a caller that may repeat or hallucinate a request, especially ahead of irreversible side effects; the authorization problem of delegated action, scoped capabilities, token binding, and the confused-deputy risk when an agent acts on a user's behalf across services; and async / long-running operation design for agents via MCP, tool-calling conventions, and durable execution.
Examples are drawn from building and operating an agentic platform in production at enterprise scale, an MCP gateway, a tool/skills registry, durable agent runtimes, but the patterns generalize to any API that expects autonomous-agent consumers, whether through MCP, native tool-calling, or direct invocation. Attendees leave with a checklist for auditing an existing API for agent-readiness, and a set of design defaults for new ones.
Designing and Hardening APIs for AI Agents and Agentic Workflows
As AI agents and agentic workflows become integral to modern enterprise operations, APIs must evolve to support these autonomous systems effectively. This session will explore the challenges of adapting APIs for AI-driven interactions and provide actionable strategies to design and fortify APIs that are AI-agent friendly.
Key Takeaways:
- Understanding Agentic Workflows: Gain insights into how AI agents operate within workflows and the specific demands they place on API interactions.
- Design Principles for AI-Compatible APIs: Learn about modular design, dynamic adaptability, and robust security measures essential for APIs in AI-driven environments.
- Future-Proofing API Strategies: Equip yourself with knowledge to anticipate and prepare for emerging trends in AI and API integration.
Why Attend: This session is essential for API developers, architects, and business leaders aiming to future-proof their systems in the era of AI. Attendees will gain valuable insights into the intersection of API design and AI, equipping them with the knowledge to enhance their platforms for intelligent automation and improved interoperability.
Building Scalable Data Lakes: AWS Managed Iceberg & S3 Table Buckets Workshop
In this workshop, we will explore AWS Managed Iceberg and dive into the latest S3 table buckets feature. Learn how to efficiently ingest data into Iceberg tables using EMR on EC2, along with best practices for building scalable and optimized data lakes.
Building Reliable and Resilient Services
In this session we will talk about the architectural patterns to make your services and distributed systems more resilient and reliable. We will discuss some of the challenges of the distributed systems, how to handle failures and error conditions, how to make your services highly available, highly scalable and improve latency. Concepts you learn in this talk are generally applicable to different platforms and frameworks used to build services and distributed systems.
Iceberg Summit 2025 Sessionize Event
DeveloperWeek 2021 Sessionize Event
AI DevWorld 2020 Sessionize Event
Big Mountain Data and Dev Conference Sessionize Event
DeveloperWeek Global 2020 Sessionize Event
DeveloperWeek 2020 Sessionize Event
Manoj Agarwal
Chief Architect at Zeta Global
Cupertino, California, United States
Links
Actions
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top