Building Context-Aware AI Agents with Real-Time Data

Learn how to build production-grade, context-aware AI agents with real-time streaming data in this online ODSC AI Skills Accelerator webinar on 9 September. Hosted by ODSC AI Barcelona, this expert-led session examines the architectural layer that AI applications often lack: a continuous supply of fresh, refined context. Rather than relying on brittle pipelines or stale snapshots, you’ll see how operational data can be transformed into timely context that helps agents make reliable decisions based on the current state of a business. ## What the session covers Experts from IBM, Confluent and Google Cloud will explain how their technologies work together to support real-world AI systems. The session will explore how Confluent’s data-streaming platform converts operational data into automated decisions, while Google Cloud adds real-time investigation and explanation. It will also show how governed data can be synced to BigQuery to create a historical record for later analysis. The speakers are: - Karan Sachdeva , Global Lead, IBM–Google Strategic Partnership, IBM - Sean Falconer , Head of AI, Confluent - Sohrab Rahimi , Director and AI/ML Lead, Google Cloud ## Live anomaly-detection demo A central feature is a live demonstration of a streaming-native architecture built around racing telemetry. Data will flow through Confluent’s Real-Time Context Engine, where a Confluent Streaming Agent detects anomalies and recommends pit timing in real time. You’ll then see a Gemini agent in Google Antigravity, connected through MCP, investigate those decisions and explain the reasoning behind them. This practical scenario demonstrates how detection, recommendation, investigation, explanation and historical analysis can form one connected AI workflow. ## Who should attend? The webinar is aimed at AI engineers, data professionals, developers, architects and technical decision-makers who want to move agentic AI beyond proofs of concept. It will be especially relevant if you are working with streaming data, anomaly detection, cloud AI systems or production agent architectures. The technical focus makes some familiarity with AI and data platforms useful, while the expert-led format also provides a clear architectural overview for people evaluating these approaches.… Register for this event