Enterprise AI brokers at the moment face a basic timing drawback: They’ll't simply act on essential enterprise occasions as a result of they aren't all the time conscious of them in real-time.
The problem is infrastructure. Most enterprise knowledge lives in databases fed by extract-transform-load (ETL) jobs that run hourly or each day — finally too sluggish for brokers that should reply in actual time.
One potential manner to sort out that problem is to have brokers straight interface with streaming knowledge methods. Amongst the major approaches in use at the moment are the open supply Apache Kafka and Apache Flink applied sciences. There are a number of industrial implementations based mostly on these applied sciences, too, Confluent, which is led by the authentic creators behind Kafka, being certainly one of them.
In the present day, Confluent is introducing a real-time context engine designed to remedy this latency drawback. The know-how builds on Apache Kafka, the distributed occasion streaming platform that captures knowledge as occasions happen, and open-source Apache Flink, the stream processing engine that transforms these occasions in actual time.
The corporate is additionally releasing an open-source framework, Flink Brokers, developed in collaboration with Alibaba Cloud, LinkedIn and Ververica. The framework brings event-driven AI agent capabilities straight to Apache Flink, permitting organizations to construct brokers that monitor knowledge streams and set off routinely based mostly on circumstances with out committing to Confluent's managed platform.
"In the present day, most enterprise AI methods can't reply routinely to essential occasions in a enterprise with out somebody prompting them first," Sean Falconer, Confluent's head of AI, instructed VentureBeat. "This leads to misplaced income, sad prospects or added danger when a cost fails or a community malfunctions."
The importance extends past Confluent's particular merchandise. The business is recognizing that AI brokers require totally different data infrastructure than conventional functions. Brokers don't simply retrieve information when requested. They want to observe steady streams of enterprise occasions and act routinely when circumstances warrant. This requires streaming structure, not batch pipelines.
Batch versus streaming: Why RAG alone isn't sufficient
To know the drawback, it's essential to distinguish between the totally different approaches to transferring knowledge by way of enterprise methods and the way they will connect to agentic AI.
In batch processing, knowledge accumulates in supply methods till a scheduled job runs. That job extracts the knowledge, transforms it and masses it right into a goal database or knowledge warehouse. This may happen hourly, each day and even weekly. The method works properly for analytical workloads, nevertheless it creates latency between when one thing occurs in the enterprise and when methods can act on it.
Knowledge streaming inverts this mannequin. As a substitute of ready for scheduled jobs, streaming platforms like Apache Kafka seize occasions as they happen. Every database replace, consumer motion, transaction or sensor studying turns into an occasion printed to a stream. Apache Flink then processes these streams to be part of, filter and combination knowledge in actual time. The outcome is processed knowledge that displays the present state of the enterprise, updating repeatedly as new occasions arrive.
This distinction turns into essential when you think about what sorts of context AI brokers really want. A lot of the present enterprise AI dialogue focuses on retrieval-augmented era (RAG), which handles semantic search over data bases to discover related documentation, insurance policies or historic information. RAG works properly for questions like "What's our refund coverage?" the place the reply exists in static paperwork.
However many enterprise use circumstances require what Falconer calls "structural context" — exact, up-to-date information from a number of operational methods stitched collectively in actual time. Think about a job advice agent that requires consumer profile knowledge from the HR database, looking habits from the final hour, search queries from minutes in the past and present open positions throughout a number of methods.
"The half that we're unlocking for companies is the potential to primarily serve that structural context wanted to ship the freshest model," Falconer mentioned.
The MCP connection drawback: Stale knowledge and fragmented context
The problem isn't merely connecting AI to enterprise knowledge. Mannequin Context Protocol (MCP), launched by Anthropic earlier this 12 months, already standardized how brokers entry knowledge sources. The issue is what occurs after the connection is made.
In most enterprise architectures at the moment, AI brokers join by way of MCP to knowledge lakes or warehouses fed by batch ETL pipelines. This creates two essential failures: The information is stale, reflecting yesterday's actuality moderately than present occasions, and it's fragmented throughout a number of methods, requiring important preprocessing before an agent can cause about it successfully.
The choice — placing MCP servers straight in entrance of operational databases and APIs — creates totally different issues. These endpoints weren't designed for agent consumption, which might lead to excessive token prices as brokers course of extreme uncooked knowledge and a number of inference loops as they struggle to make sense of unstructured responses.
"Enterprises have the knowledge, nevertheless it's usually stale, fragmented or locked in codecs that AI can't use successfully," Falconer defined. "The true-time context engine solves this by unifying knowledge processing, reprocessing and serving, turning steady knowledge streams into stay context for smarter, quicker and extra dependable AI choices."
The technical structure: Three layers for real-time agent context
Confluent's platform encompasses three components that work collectively or adopted individually.
The real-time context engine is the managed knowledge infrastructure layer on Confluent Cloud. Connectors pull knowledge into Kafka subjects as occasions happen. Flink jobs course of these streams into "derived datasets" — materialized views becoming a member of historic and real-time alerts. For buyer help, this may mix account historical past, present session habits and stock standing into one unified context object. The Engine exposes this by way of a managed MCP server.
Streaming brokers is Confluent's proprietary framework for constructing AI brokers that run natively on Flink. These brokers monitor knowledge streams and set off routinely based mostly on circumstances — they don't anticipate prompts. The framework contains simplified agent definitions, built-in observability and native Claude integration from Anthropic. It's out there in open preview on Confluent's platform.
Flink Brokers is the open-source framework developed with Alibaba Cloud, LinkedIn and Ververica. It brings event-driven agent capabilities straight to Apache Flink, permitting organizations to construct streaming brokers with out committing to Confluent's managed platform. They deal with operational complexity themselves however keep away from vendor lock-in.
Competitors heats up for agent-ready knowledge infrastructure
Confluent isn't alone in recognizing that AI brokers want totally different knowledge infrastructure.
The day before Confluent's announcement, rival Redpanda launched its personal Agentic Knowledge Aircraft — combining streaming, SQL and governance particularly for AI brokers. Redpanda acquired Oxla's distributed SQL engine to give brokers normal SQL endpoints for querying knowledge in movement or at relaxation. The platform emphasizes MCP-aware connectivity, full observability of agent interactions and what it calls "agentic entry management" with fine-grained, short-lived tokens.
The architectural approaches differ. Confluent emphasizes stream processing with Flink to create derived datasets optimized for brokers. Redpanda emphasizes federated SQL querying throughout disparate sources. Each acknowledge brokers want real-time context with governance and observability.
Past direct streaming opponents, Databricks and Snowflake are essentially analytical platforms including streaming capabilities. Their energy is complicated queries over giant datasets, with streaming as an enhancement. Confluent and Redpanda invert this: Streaming is the basis, with analytical and AI workloads constructed on prime of knowledge in movement.
How streaming context works in observe
Amongst the customers of Confluent's system is transportation vendor Busie. The corporate is constructing a contemporary working system for constitution bus corporations that helps them handle quotes, journeys, funds and drivers in actual time.
"Knowledge streaming is what makes that potential," Louis Bookoff, Busie co-founder and CEO instructed VentureBeat. "Utilizing Confluent, we transfer knowledge immediately between totally different elements of our system as a substitute of ready for in a single day updates or batch experiences. That retains every little thing in sync and helps us ship new options quicker.
Bookoff famous that the identical basis is what is going to make gen AI useful for his prospects.
"In our case, each motion like a quote despatched or a driver assigned turns into an occasion that streams by way of the system instantly," Bookoff mentioned. "That stay feed of information is what is going to let our AI instruments reply in actual time with low latency moderately than simply summarize what already occurred."
The problem, nevertheless, is how to perceive context. When 1000’s of stay occasions move by way of the system each minute, AI fashions want related, correct knowledge with out getting overwhelmed.
"If the knowledge isn't grounded in what is taking place in the actual world, AI can simply make unsuitable assumptions and in flip take unsuitable actions," Bookoff mentioned. "Stream processing solves that by repeatedly validating and reconciling stay knowledge towards exercise in Busie."
What this implies for enterprise AI technique
Streaming context structure alerts a basic shift in how AI brokers eat enterprise knowledge.
AI brokers require steady context that blends historic understanding with real-time consciousness — they want to know what occurred, what's taking place and what may occur subsequent, all of sudden.
For enterprises evaluating this method, begin by figuring out use circumstances the place knowledge staleness breaks the agent. Fraud detection, anomaly investigation and real-time buyer intervention fail with batch pipelines that refresh hourly or each day. In case your brokers want to act on occasions inside seconds or minutes of them occurring, streaming context turns into essential moderately than non-obligatory.
"While you're constructing functions on prime of basis fashions, as a result of they're inherently probabilistic, you utilize knowledge and context to steer the mannequin in a course the place you need to get some form of final result," Falconer mentioned. "The higher you are able to do that, the extra dependable and higher the final result."
Disclaimer: This article is sourced from external platforms. OverBeta has not independently verified the information. Readers are advised to verify details before relying on them.
