{"id":5706,"date":"2025-11-03T07:42:00","date_gmt":"2025-11-03T07:42:00","guid":{"rendered":"https:\/\/dalelane.co.uk\/blog\/?p=5706"},"modified":"2026-03-14T21:21:11","modified_gmt":"2026-03-14T21:21:11","slug":"ai-patterns-in-event-driven-architectures","status":"publish","type":"post","link":"https:\/\/dalelane.co.uk\/blog\/?p=5706","title":{"rendered":"AI patterns in event driven architectures"},"content":{"rendered":"

I gave a talk at Current<\/a> last week about how artificial intelligence and machine learning are used with Kafka topics. I had a lot of examples to share, so I wrote up my slides across several posts.<\/p>\n

I’ll use this post to recap and link to my write-ups of each bit of the talk:<\/p>\n

<\/p>\n

I started by talking about the different building blocks that are needed<\/a>, and the sorts of choices that teams make.<\/p>\n

Next, I talked about how projects to introduce AI into event driven architectures typically fall into one or more of these common patterns:<\/p>\n

<\/p>\n

The most common, and the simplest: using AI to improve and augment the sorts of processing we can do with events<\/a>. This can be as simple as using off-the-shelf pre-trained models to enrich a stream of events, and using this to filter or route the event as part of processing.<\/p>\n

Perhaps the newest (and the pattern that is recently getting the most interest and attention) is to use streams of events to trigger agents<\/a>, so that they can autonomously take actions in repsonse.<\/p>\n

Maybe the less obvious approach is to collect and store a projection of recent events, and use these to enhance an agentic AI<\/a>, by making it available as a queryable or searchable form of real-time context.<\/p>\n

And finally, the longest established pattern is to simply use the retained history of Kafka topics as a relevant source of historical training data<\/a>, for training new custom and bespoke models.<\/p>\n","protected":false},"excerpt":{"rendered":"

I gave a talk at Current last week about how artificial intelligence and machine learning are used with Kafka topics. I had a lot of examples to share, so I wrote up my slides across several posts. I’ll use this post to recap and link to my write-ups of each bit of the talk: I […]<\/p>\n","protected":false},"author":1,"featured_media":5712,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[3],"tags":[593,584,580],"class_list":["post-5706","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-tech","tag-apachekafka","tag-kafka","tag-machine-learning"],"_links":{"self":[{"href":"https:\/\/dalelane.co.uk\/blog\/index.php?rest_route=\/wp\/v2\/posts\/5706","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dalelane.co.uk\/blog\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dalelane.co.uk\/blog\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dalelane.co.uk\/blog\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/dalelane.co.uk\/blog\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=5706"}],"version-history":[{"count":1,"href":"https:\/\/dalelane.co.uk\/blog\/index.php?rest_route=\/wp\/v2\/posts\/5706\/revisions"}],"predecessor-version":[{"id":5886,"href":"https:\/\/dalelane.co.uk\/blog\/index.php?rest_route=\/wp\/v2\/posts\/5706\/revisions\/5886"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dalelane.co.uk\/blog\/index.php?rest_route=\/wp\/v2\/media\/5712"}],"wp:attachment":[{"href":"https:\/\/dalelane.co.uk\/blog\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=5706"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dalelane.co.uk\/blog\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=5706"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dalelane.co.uk\/blog\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=5706"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}