Kafka in the Cloud: Why it’s 10x better with Confluent | Find out more
Author: Sean Falconer
Powering AI Agents With Real-Time Data Using Anthropic’s MCP and Confluent
Model Context Protocol (MCP), introduced by Anthropic, is a new standard that simplifies AI integrations by providing a secure and consistent way to connect AI agents with external tools and data sources…
Real-Time Toxicity Detection in Games: Balancing Moderation and Player Experience
Prevent toxic in-game chat without disrupting player interactions using a real-time AI-based moderation system powered by Confluent and Databricks.
Your AI Project Has a Data Liberation Problem
Most AI projects fail not because of bad models, but because of bad data. Siloed, stale, and locked in batch pipelines, enterprise data isn’t AI-ready. This post breaks down the data liberation problem and how streaming solves it—freeing real-time data so AI can actually deliver value.
A Distributed State of Mind: Event-Driven Multi-Agent Systems
This article explores how event-driven design—a proven approach in microservices—can address the chaos, creating scalable, efficient multi-agent systems. If you’re leading teams toward the future of AI, understanding these patterns is critical. We’ll demonstrate how they can be implemented.
Automating Podcast Promotion with AI and Event-Driven Design
We built an AI-powered tool to automate LinkedIn post creation for podcasts, using Kafka, Flink, and OpenAI models. With an event-driven design, it’s scalable, modular, and future-proof. Learn how this system works and explore the code on GitHub in our latest blog.
Event-Driven AI: Building a Research Assistant with Kafka and Flink
The rise of agentic AI has fueled excitement around agents that autonomously perform tasks, make recommendations, and execute complex workflows. This blog post details the design and architecture of PodPrep AI, an AI-powered research assistant that helps the author prepare for podcast interviews.
Stop Treating Your LLM Like a Database
GenAI thrives on real-time contextual data: In a modern system, LLMs should be designed to engage, synthesize, and contribute, rather than to simply serve as queryable data stores.