--- title: New in Confluent Intelligence and AI Tools: Making... description: Confluent announced quarterly updates to its Confluent Intelligence and AI Tools portfolio. Highlights include GA of Real-Time Context Engine with new... canonical: https://daily.dev/posts/new-in-confluent-intelligence-and-ai-tools-making-agents-native-to-the-stream-expanded-model-suppo-rc1fwyggr twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: New in Confluent Intelligence and AI Tools: Making Agents Native to the Stream, Expanded Model Support, New Agent Skills, and Copilot | daily.dev og:description: Confluent announced quarterly updates to its Confluent Intelligence and AI Tools portfolio. Highlights include GA of Real-Time Context Engine with new... og:url: https://daily.dev/posts/new-in-confluent-intelligence-and-ai-tools-making-agents-native-to-the-stream-expanded-model-suppo-rc1fwyggr og:image: https://api.daily.dev/og/posts/rc1FwYGGr.png og:image:alt: New in Confluent Intelligence and AI Tools: Making Agents Native to the Stream, Expanded Model Support, New Agent Skills, and Copilot og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # New in Confluent Intelligence and AI Tools: Making Agents Native to the Stream, Expanded Model Support, New Agent Skills, and Copilot **[Confluent Blog](https://daily.dev/sources/conf)** · 11 min read · 0 upvotes · 0 comments ## Summary Confluent announced quarterly updates to its Confluent Intelligence and AI Tools portfolio. Highlights include GA of Real-Time Context Engine with new usage/cost metrics, early access support for IBM Granite time-series models (TTM, FlowState, PatchTST-FM) and Google TimesFM for anomaly detection and forecasting via Flink SQL functions AI_FORECAST and AI_DETECT_ANOMALIES, a GA fully managed MCP server with new write tools for connector restart/config updates, new open-source Agent Skills (Migrate, Java Kafka client, Flink UDF, Skill Creator) for coding assistants like Claude Code and Cursor, and an early-access Confluent Copilot for natural-language troubleshooting and operation of Confluent Cloud, including automated connector diagnostics and fixes. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What new time-series models does Confluent Flink support for forecasting and anomaly detection? Confluent Flink now supports IBM Granite time-series models (TTM, FlowState, PatchTST-FM) and Google's TimesFM model, both in early access. They plug into the existing AI_FORECAST and AI_DETECT_ANOMALIES Flink SQL functions via a single SQL parameter, so switching models requires no pipeline redesign. Granite suits manufacturing, IoT, or financial data; TimesFM offers general-purpose forecasting with confidence intervals. Both are hosted with zero configuration, currently on AWS. _Developers comparing time-series forecasting models can track platform updates like this on daily.dev._ ### What does Confluent's fully managed MCP server let AI assistants do in Confluent Cloud? Confluent's fully managed MCP server gives AI assistants permissioned access to Confluent Cloud resources without requiring a locally deployed MCP server. New write tools let assistants restart connectors and update connector configuration, available now, with Flink SQL creation and management tools planned for later in September. This removes the need for teams to run and maintain their own MCP infrastructure. _Engineers wiring AI agents into cloud infrastructure can follow MCP tooling changes like this on daily.dev._ ### What are Confluent Agent Skills and which ones were released for AI coding assistants? Confluent Agent Skills are open-source, reusable workflows that package Confluent expertise into coding assistants such as Claude Code and Cursor. The newly released skills cover migrating from MSK to Confluent Cloud, scaffolding Java Kafka producer/consumer apps with Schema Registry serializers, building Flink SQL user-defined functions, and a meta-skill for creating new Confluent skills. They install via 'npx skills add confluentinc/agent-skills'. _Teams adopting AI coding assistants for streaming work can keep up with skill releases like these on daily.dev._ ## Similar posts on daily.dev - [Confluent Makes it Easier to Build and Secure Real-Time AI at Scale](https://daily.dev/posts/confluent-makes-it-easier-to-build-and-secure-real-time-ai-at-scale-cwztvhsas) · SD Times · 0 upvotes · 0 comments - [Real-Time Intelligence with IBM Time Series Models on Confluent](https://daily.dev/posts/real-time-intelligence-with-ibm-time-series-models-on-confluent-korfuoerp) · Hugging Face · 0 upvotes · 0 comments - [Unleash Real-Time Agentic AI With Streaming Agents on Confluent Cloud and Couchbase](https://daily.dev/posts/unleash-real-time-agentic-ai-with-streaming-agents-on-confluent-cloud-and-couchbase-1fjiz7qo5) · Couchbase · 1 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#mcp](https://daily.dev/tags/mcp), [#apache-kafka](https://daily.dev/tags/apache-kafka), [#confluent-cloud](https://daily.dev/tags/confluent-cloud), [#apache-flink](https://daily.dev/tags/apache-flink) [View this post on daily.dev](https://daily.dev/posts/new-in-confluent-intelligence-and-ai-tools-making-agents-native-to-the-stream-expanded-model-suppo-rc1fwyggr) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"New in Confluent Intelligence and AI Tools: Making Agents Native to the Stream, Expanded Model Support, New Agent Skills, and Copilot","url":"https://daily.dev/posts/new-in-confluent-intelligence-and-ai-tools-making-agents-native-to-the-stream-expanded-model-suppo-rc1fwyggr","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/new-in-confluent-intelligence-and-ai-tools-making-agents-native-to-the-stream-expanded-model-suppo-rc1fwyggr"},"datePublished":"2026-08-18T14:06:42.609Z","dateModified":"2026-09-14T08:45:37.101Z","description":"Confluent announced quarterly updates to its Confluent Intelligence and AI Tools portfolio. Highlights include GA of Real-Time Context Engine with new...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/5957214543e61b2009e2522cc6045172?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/5957214543e61b2009e2522cc6045172?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Confluent Blog","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Confluent Blog","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/cb2c20a237b7409591c7a087c42fb714","url":"https://daily.dev/sources/conf"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/new-in-confluent-intelligence-and-ai-tools-making-agents-native-to-the-stream-expanded-model-suppo-rc1fwyggr","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,mcp,apache-kafka,confluent-cloud,apache-flink","timeRequired":"PT11M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Confluent Blog","item":"https://daily.dev/sources/conf"},{"@type":"ListItem","position":3,"name":"New in Confluent Intelligence and AI Tools: Making Agents Native to the Stream, Expanded Model Support, New Agent Skills, and Copilot"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/new-in-confluent-intelligence-and-ai-tools-making-agents-native-to-the-stream-expanded-model-suppo-rc1fwyggr#faq","mainEntity":[{"@type":"Question","name":"What new time-series models does Confluent Flink support for forecasting and anomaly detection?","acceptedAnswer":{"@type":"Answer","text":"Confluent Flink now supports IBM Granite time-series models (TTM, FlowState, PatchTST-FM) and Google's TimesFM model, both in early access. They plug into the existing AI_FORECAST and AI_DETECT_ANOMALIES Flink SQL functions via a single SQL parameter, so switching models requires no pipeline redesign. Granite suits manufacturing, IoT, or financial data; TimesFM offers general-purpose forecasting with confidence intervals. Both are hosted with zero configuration, currently on AWS. Developers comparing time-series forecasting models can track platform updates like this on daily.dev."}},{"@type":"Question","name":"What does Confluent's fully managed MCP server let AI assistants do in Confluent Cloud?","acceptedAnswer":{"@type":"Answer","text":"Confluent's fully managed MCP server gives AI assistants permissioned access to Confluent Cloud resources without requiring a locally deployed MCP server. New write tools let assistants restart connectors and update connector configuration, available now, with Flink SQL creation and management tools planned for later in September. This removes the need for teams to run and maintain their own MCP infrastructure. Engineers wiring AI agents into cloud infrastructure can follow MCP tooling changes like this on daily.dev."}},{"@type":"Question","name":"What are Confluent Agent Skills and which ones were released for AI coding assistants?","acceptedAnswer":{"@type":"Answer","text":"Confluent Agent Skills are open-source, reusable workflows that package Confluent expertise into coding assistants such as Claude Code and Cursor. The newly released skills cover migrating from MSK to Confluent Cloud, scaffolding Java Kafka producer/consumer apps with Schema Registry serializers, building Flink SQL user-defined functions, and a meta-skill for creating new Confluent skills. They install via 'npx skills add confluentinc/agent-skills'. Teams adopting AI coding assistants for streaming work can keep up with skill releases like these on daily.dev."}}]} ```