.jpg)
Confluent, Inc. announced Streaming Agents on August 19, 2025, a new capability in Confluent Cloud for Apache Flink® that enables enterprises to build and scale AI agents that monitor, reason, and act on real-time data. By integrating data processing and AI workflows, Streaming Agents overcomes barriers to enterprise-grade agentic AI, offering secure connections to large language models (LLMs), embedding models, and business systems, accelerating adoption and unlocking new business opportunities.
Streaming Agents integrates agentic AI into Apache Kafka® and Flink® pipelines.
Enables real-time monitoring, reasoning, and action for AI agents.
Features tool calling, secure integrations, external data enrichment, and replayability.
Addresses prototype-to-production challenges, with only 3 of 23 AI proofs reaching production (2023-2024, IDC).
Supports use cases like competitive pricing in ecommerce.
Available in open preview for Confluent Cloud users.
“Agentic AI is on every organization’s roadmap, but most companies are stuck in prototype purgatory,” said Shaun Clowes, Chief Product Officer at Confluent. IDC research indicates that between 2023 and 2024, enterprises averaged 23 generative AI proofs of concept, but only three reached production, with just 62% meeting expectations. Streaming Agents addresses this by unifying data processing and AI reasoning, providing agents with fresh, contextual real-time data to prevent hallucinations and ensure reliable responses.
Streaming Agents embeds AI directly into stream processing pipelines, enabling event-driven automation. Key features include:
Tool Calling for Context-Aware Automation: Uses Model Context Protocol (MCP) to select external tools (e.g., databases, SaaS, APIs) for precise actions based on business context.
Secure Integrations: Connects to models, vector databases, and MCP via Flink, with credential protection and centralized management for scalability.
External Tables and Search: Enriches streaming data with non-Kafka sources like relational databases and REST APIs, enhancing AI accuracy for retrieval-augmented generation (RAG) applications.
Replayability: Supports dark launches and A/B testing by allowing agent development with real data without live impacts, ensuring safety and faster iteration.
For example, in ecommerce, Streaming Agents can monitor competitor prices across platforms and adjust a retailer’s prices in real time to stay competitive.
“Organizations should prioritize agentic AI solutions that offer easy, secure integration and leverage real-time data,” said Stewart Bond, Vice President of Data Intelligence at IDC. Streaming Agents leverages Apache Kafka® and Flink® to deliver continuous, context-aware reasoning, akin to human operators, while handling high-volume data streams. This enables enterprises to move from prototypes to production-ready AI, addressing challenges like fragmented workflows and unreliable data integration.
As of August 20, 2025, Confluent (Nasdaq: CFLT) closed at $21.82, with a market cap of $7.07B. The stock’s 1-month range was $20.09-$25.24, and its 1-year range was $18.36-$34.31, reflecting volatility but recent stability. Confluent’s Q2 2025 earnings reported an EPS of $0.06, beating forecasts of $0.02, with revenue of $234.8M against $229.2M expected, signaling strong growth aligned with this AI innovation.
Confluent is the data streaming platform that is pioneering a fundamentally new category of data infrastructure that sets data in motion. Confluent’s cloud-native offering is the foundational platform for data in motion—designed to be the intelligent connective tissue enabling real-time data from multiple sources to constantly stream across an organization. With Confluent, organizations can meet the new business imperative of delivering rich, digital frontend customer experiences and transitioning to sophisticated, real-time, software-driven backend operations.
TechIntelPro empowers B2B technology decision-makers with the latest industry trends, deep insights, leadership perspectives and actionable intelligence to drive both organizational and professional milestones—and thrive on the tech pulse.