Enterprise AI brokers right now face a elementary timing drawback: They’ll't simply act on essential enterprise occasions as a result of they aren't at all times 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 day by day — finally too gradual for brokers that should reply in actual time.
One potential option to sort out that problem is to have brokers immediately interface with streaming knowledge methods. Among the many main approaches in use right now are the open supply Apache Kafka and Apache Flink applied sciences. There are a number of business implementations based mostly on these applied sciences, too, Confluent, which is led by the unique creators behind Kafka, being considered one of them.
At the moment, Confluent is introducing a real-time context engine designed to resolve 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 can also be releasing an open-source framework, Flink Brokers, developed in collaboration with Alibaba Cloud, LinkedIn and Ververica. The framework brings event-driven AI agent capabilities on to Apache Flink, permitting organizations to construct brokers that monitor knowledge streams and set off mechanically based mostly on circumstances with out committing to Confluent's managed platform.
"At the moment, most enterprise AI methods can't reply mechanically to vital occasions in a enterprise with out somebody prompting them first," Sean Falconer, Confluent's head of AI, informed VentureBeat. "This results in misplaced income, sad clients 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 completely different knowledge infrastructure than conventional functions. Brokers don't simply retrieve data when requested. They should observe steady streams of enterprise occasions and act mechanically when circumstances warrant. This requires streaming structure, not batch pipelines.
Batch versus streaming: Why RAG alone isn't sufficient
To grasp the issue, it's vital to tell apart between the completely different approaches to transferring knowledge by enterprise methods and the way they will hook up with agentic AI.
In batch processing, knowledge accumulates in supply methods till a scheduled job runs. That job extracts the info, transforms it and hundreds it right into a goal database or knowledge warehouse. This may happen hourly, day by day and even weekly. The method works nicely for analytical workloads, but it surely creates latency between when one thing occurs within 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, person motion, transaction or sensor studying turns into an occasion revealed to a stream. Apache Flink then processes these streams to hitch, filter and mixture knowledge in actual time. The result’s processed knowledge that displays the present state of the enterprise, updating constantly 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 technology (RAG), which handles semantic search over data bases to search out related documentation, insurance policies or historic data. RAG works nicely 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 data from a number of operational methods stitched collectively in actual time. Think about a job advice agent that requires person 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 power to primarily serve that structural context wanted to ship the freshest model," Falconer stated.
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 right now, AI brokers join by way of MCP to knowledge lakes or warehouses fed by batch ETL pipelines. This creates two essential failures: The info is stale, reflecting yesterday's actuality fairly than present occasions, and it's fragmented throughout a number of methods, requiring vital preprocessing earlier than an agent can purpose about it successfully.
The choice — placing MCP servers immediately in entrance of operational databases and APIs — creates completely different issues. These endpoints weren't designed for agent consumption, which might result in excessive token prices as brokers course of extreme uncooked knowledge and a number of inference loops as they attempt to make sense of unstructured responses.
"Enterprises have the info, but it surely's typically stale, fragmented or locked in codecs that AI can't use successfully," Falconer defined. "The actual-time context engine solves this by unifying knowledge processing, reprocessing and serving, turning steady knowledge streams into reside context for smarter, quicker and extra dependable AI choices."
The technical structure: Three layers for real-time agent context
Confluent's platform encompasses three parts 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 assist, this may mix account historical past, present session habits and stock standing into one unified context object. The Engine exposes this by 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 mechanically based mostly on circumstances — they don't look forward to prompts. The framework consists of simplified agent definitions, built-in observability and native Claude integration from Anthropic. It's accessible 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 on 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 completely different knowledge infrastructure.
The day earlier than Confluent's announcement, rival Redpanda launched its personal Agentic Knowledge Airplane — combining streaming, SQL and governance particularly for AI brokers. Redpanda acquired Oxla's distributed SQL engine to present brokers customary 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 rivals, Databricks and Snowflake are essentially analytical platforms including streaming capabilities. Their power is complicated queries over giant datasets, with streaming as an enhancement. Confluent and Redpanda invert this: Streaming is the muse, with analytical and AI workloads constructed on high of information in movement.
How streaming context works in observe
Among the many customers of Confluent's system is transportation vendor Busie. The corporate is constructing a contemporary working system for constitution bus firms that helps them handle quotes, journeys, funds and drivers in actual time.
"Knowledge streaming is what makes that doable," Louis Bookoff, Busie co-founder and CEO informed VentureBeat. "Utilizing Confluent, we transfer knowledge immediately between completely different components of our system as an alternative of ready for in a single day updates or batch studies. That retains all the things in sync and helps us ship new options quicker.
Bookoff famous that the identical basis is what’s going to make gen AI worthwhile for his clients.
"In our case, each motion like a quote despatched or a driver assigned turns into an occasion that streams by the system instantly," Bookoff stated. "That reside feed of data is what’s going to let our AI instruments reply in actual time with low latency fairly than simply summarize what already occurred."
The problem, nevertheless, is the way to perceive context. When 1000’s of reside occasions movement by the system each minute, AI fashions want related, correct knowledge with out getting overwhelmed.
"If the info isn't grounded in what is going on in the actual world, AI can simply make improper assumptions and in flip take improper actions," Bookoff stated. "Stream processing solves that by constantly validating and reconciling reside knowledge in opposition to exercise in Busie."
What this implies for enterprise AI technique
Streaming context structure alerts a elementary shift in how AI brokers devour enterprise knowledge.
AI brokers require steady context that blends historic understanding with real-time consciousness — they should 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 day by day. In case your brokers have to act on occasions inside seconds or minutes of them occurring, streaming context turns into needed fairly than non-compulsory.
"If you're constructing functions on high of basis fashions, as a result of they're inherently probabilistic, you employ knowledge and context to steer the mannequin in a route the place you need to get some type of end result," Falconer stated. "The higher you are able to do that, the extra dependable and higher the end result."
