The managed service delivers predictions alongside live events and consolidates all resource consumption into existing Confluent billing. It complements the previously launched External Model Inference feature, which requires teams to configure their own credentials. Large language models and embedding solutions are already generally available, while tools for forecasting, anomaly detection, and text analysis are offered under Early Access.
Key points
Direct stream inference eliminates delays caused by moving information across detached pr…: Direct stream inference eliminates delays caused by moving information across detached processing pipelines.
Organizations can check which specific models are accessible within their region by runni…: Organizations can check which specific models are accessible within their region by running a standard SQL command.
Advanced features like sentiment analysis, sensitive data detection, and time-series fore…: Advanced features like sentiment analysis, sensitive data detection, and time-series forecasting are currently limited to Early Access.
Sources checked by our analysis pipeline: 1
AI models are becoming increasingly powerful. But intelligence alone isn't enough. What matters is whether that intelligence can drive decisions in real time, when they matter most. With Managed Model Inference, we're closing the gap between data and AI-powered decision-making. We are extending Confluent's shift-left approach to AI, bringing AI models closer to the data source and making inference available directly in the stream, through a single SQL call, with zero configuration.
We bring AI to the data.
Consider timing. A suspicious transaction is worth stopping while the payment is still in flight. Minutes later, it is a loss to investigate, and an hour later, the opportunity to act may be gone. The model can be equally accurate in all three cases. What changed is when it answered. The same is true in manufacturing, where drift has to be caught before it becomes downtime; in retail, where a shelf has to be restocked before it empties; and in energy, where unusual load has to be spotted as it happens.
When mission-critical actions lose value with every passing minute, inference belongs…
Security researchers are relying on advanced artificial intelligence models to uncover critical software flaws. These efforts identified dangerous flaws in Nginx that allow unauthorized remote code execution. The findings were independently corroborated when a separate security organization revealed it had also pinpointed the exact same security risks.
Addressing the sudden leadership vacuum at a critical hardware partner, OpenAI leaders highlighted their deep operational ties with Nvidia at the DealBook Summit. Jensen Huang's exit follows serious controversies, yet key allies are emphasizing corporate continuity to ensure their ongoing technological collaboration remains on track.
Enterprise software teams face mounting computational expenses as they deploy continuous, around-the-clock automated agents for critical engineering and operational tasks. The latest licensed-weight release targets this financial barrier by sharply reducing token costs while maintaining elite benchmark capabilities across specialized domains. These efficiencies allow businesses to scale automated workflows across developer tooling, cybersecurity, clinical documentation, and live customer interactions without incur…