Steffen Hoellinger
CEO at Airy
San Francisco, California, United States
Actions
Steffen is the CEO and co-founder of Airy, a Data Streaming for AI company building the agentic AI layer for stream processing powered by Apache Flink.
Links
Area of Expertise
Topics
Build Copilots on Streaming Data with Generative AI, Kafka Streams and Flink SQL
To unleash the power of Large Language Models (LLMs), organizations need to integrate them with their own data. Intelligent business-specific Copilots can serve as a vital link between LLMs and data streaming, enhancing developer productivity and making stream processing more accessible.
For structured data in Kafka topics, we'll demonstrate how to evolve schemas with LLMs, generating tags and descriptions. Starting from an open-source Copilot UI, we'll enable users to ask questions about streaming data in natural language and show step by step how to translate these queries with context-aware LLM prompts to Flink SQL. We'll then demonstrate how to run these statements as stream processing tasks, producing to and consuming from Kafka topics and sending messages via a websocket connection back to the Copilot UI.
For semi-structured and unstructured data (like text, JSON, PDFs, spreadsheets, and other binary files), we will explore strategies for creating data pipelines, continuously generating embeddings and storing them in vector databases for retrieval augmented generation (RAG). We will demonstrate dynamically creating consumers with Kafka Streams, managing LLM integrations, organizing metadata, as well as conducting post-processing tasks for quality assurance and for triggering actions by integrating with other systems.
In addition to developing custom Copilot UIs integrated with streaming data, we will also cover the deployment and monitoring of Copilots across various internal tools, such as Slack, Microsoft 365 Copilot, and OpenAI ChatGPT.
Building Copilots with Flink SQL, LLMs and vector databases
Generative AI apps such as Copilots can serve as a vital link between foundational models and enterprise data, enhancing developer and employee productivity. Users are able to ask questions about streaming and batch data in natural language, making stream processing more accessible to developers, data professionals and operational teams.
For structured data, the accuracy of foundation models to dynamically generate and run correct Flink SQL can be greatly improved by annotating the schema of Flink tables with LLMs first to provide the best context to the prompt. The schemas as well as other unstructured data (like text, JSON, and binary files) can be used to continuously generate embeddings, storing them in vector databases for retrieval augmented generation (RAG).
We will demonstrate in a concrete step-by-step example how to build and deploy a Copilot in TypeScript/JavaScript with open-source tools, integrated with Flink for stream processing, the latest OpenAI/Mistral models for model inference and vector stores. We will also discuss how to select and integrate the best foundation model for the relevant use case, to optimize for cost, performance and latency at inference.
Flink Jobs as Agents 🤖 – Unlocking Agentic AI with Stream Processing
Apache Flink is uniquely positioned to serve as the backbone for AI agents, enhancing them with stream processing as a new, powerful tool. We’ll explore how Flink jobs can be transformed into autonomous, goal-driven "Agents" that interact with data streams, trigger actions, and adapt in real time.
We’ll showcase Flink jobs as AI agents through two key stream processing & AI use cases: 1) financial planning & detection of spending anomalies, as well as 2) forecasting demand & supply chain monitoring for disruptions.
AI agents need business context. We’ll discuss embedding foundation models with schema registries and data catalogs for contextual intelligence while ensuring data governance and security. We’ll integrate Apache Kafka event streams with data lakes in open-table formats like Apache Iceberg, enabling AI agents to leverage real-time and historical data for consistency and reasoning. We’ll also cover latency optimization for time-sensitive use cases while preventing hallucinations.
Finally, we’ll demonstrate an open-source conversational platform on Apache Kafka, where multiple AI agents are assigned to a business process, continuously process real-time events while optimizing for their individual goals, interacting, and negotiating with each other.
By combining Flink and Kafka, we can build systems that are not just reactive but proactive and predictive, paving the way for next-generation agentic AI.
From 📎 to 🧠: Building Gen AI Apps & Copilots on Streaming Data with Flink SQL
Gen AI apps such as intelligent business-specific Copilots can serve as a vital link between foundational models and data streaming, enhancing developer and employee productivity. Enabling users to ask questions about streaming data in natural language can provide business and engineering teams with dynamic, real-time access to organizational knowledge, enhancing employee productivity and improving workflows across enterprise operations.
For structured data in Kafka topics, we have found the accuracy of LLMs to dynamically generate correct Flink SQL being greatly improved by establishing strong data contracts and evolving schemas through generating annotations and metadata with the help of LLMs. Providing the LLM with full context about the latest schema of Kafka topics and Flink tables proved to be crucial for the robustness of generated Flink SQL statements.
For semi-structured and unstructured data (like text, JSON, and binary files), continuously generating embeddings and storing them in vector databases for retrieval augmented generation (RAG) can serve as a powerful knowledge resource. Enterprises today only analyze and use 0.5% of unstructured data.
We will demonstrate in a concrete step-by-step example how to build and deploy a Copilot in TypeScript/JavaScript with open-source tools, integrated with Apache Kafka for event streaming, Apache Flink for stream processing, OpenAI/Mistral for model inference and vector stores. In addition to custom Copilot UIs, we will also cover the deployment and monitoring of Copilots across various internal tools, such as Slack, Microsoft 365 Copilot, and OpenAI GPTs.
Current London 2025 Sessionize Event
Flink Forward Berlin 2024 Sessionize Event
Current 2024 Sessionize Event
Kafka Summit London 2024 Sessionize Event
Current 2023: The Next Generation of Kafka Summit Sessionize Event
Steffen Hoellinger
CEO at Airy
San Francisco, 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