Skip to main content

Sitecore Stream - Platform DxP Evolution

Hi Team,

I am absolutely Sitecore Stream enthusiast, and if you also keep following what is new in it and explore it features, This blog post is for you

Since it was announced in symposium 2024 and probably the first platform DxP version package was released in FEB-2025 and we are now in Sep end and there have been significant roll outs and we are into 6th release of the platform DxP package.

The purpose of this blog post is to summarize all improvements which came along with different releases for all of you and community, If you have not explored all of the packages.


NOTE: Remember Stream is "AI capabilities throughout the composable stack, be it Content Hub, XMC, CDP, Personalized but this blog post is only for platform DxP package for on-prem XP/XM.

If you see the image above, i have tried to show the package rollout on the timeline as an when they were released and watchout for next package rollout, For other useful features :) 

Important improvements

1) Less configurations and less manual config changes

Only changing connection string will do rest, where in initial versions you had to change both in connection string and Sitecore.AIClient.config file too.

It was little lengthy process where you had to

1) Find your organization id, Brand kit id

2) Update them in Sitecore.AiClient.Config

3) Update the connection string

But now with latest version, you just use connection string and provide client_id and client_secret generated from portal and you will be able to use Stream with available brand kits.

2) Metadata extraction from an image 

Now, you can have metadata like Title, Description, Alt text, Keywords auto populated by AI metadata extraction, This was released in latest 1.4.54 package which was not available before, Some example of how efficiently it works is below

For example, I am uploading below image in my media library, For your context, This image is a screenshot of one of my podcast on Sitecore TECH Talks, and if you see how intelligently AI is able to extract its metadata is amazing

Here is the image i uploaded, where Varun and i are having a podcast


Below shows when i uploaded it to a media library and when i click on "Extract" button on the toolbar, How it extracts the metadata using AI.


After selecting a brand kit, You can click next and it will automatically generate metadata for the image.


And it correctly identified that,

1) There are two people engaged in a discussion

2) Event is "Sitecore TECH Talks"

3) It also identified that we are in a modern office 

4) Identified that, There are colorful featuring hanging banners in a backdrop.

Based on above it created Title, Description, Alt, Keywords fields, Pretty cool !!!


3) Availability of multiple brand kits 

Initially only one brand was supported and had to be mapped in config, but with 1.1.63 version onwards, Multiple brand key selection was allowed (of course one brand at a time)

In older versions, You had access to only one brand kit, and that also needed to be configured into Sitecore.AiClient.Config like giving these two settings

<setting name="Sitecore.AiClient.Stream.BrandKitId" value="<<brand kit id>>" />

<setting name="Sitecore.AiClient.Stream.BrandKitReferencePath" value="/api/brands/v1/organizations/org_<<org. id>>/brandkits/<<brand kit id>>" />

but now only connection string is needed and it will automatically allow you to select from multiple brands


4) AI-Assisted generation of translated text 

Language translation was not available which was introduced from 1.2.45 onwards, Where user can select the content item, its fields to translate, the target language, then trigger the AI-assisted generation of translated text. Users can also improve content in an existing language by generating a new version of the same language, I think this is a leap in content generation where language translation is available OOTB and co-pilot and agents can work hand in hand, where content author is in control of the end results, Because translation will just translate content and then content authors can proof read and finalize and publish the content.


5) Content Variants

From 1.1.63 package onwards, Now we are able to generate variants of the content using AI, So for example you can either enter your prompt, or select from existing prompt and AI will generate content in 5 different variants, and you can select the best suited for you and proof read it and save it.


6) AI-assisted content extraction

This is my fav. and huge leap in how we have been using Sitecore as CMS, You can now actually extract content from different sources and put them into your Sitecore item, It was introduced in 1.3.23 package release.


Basically, You can let AI extract content from 

1) File - Allowed file extensions are .jpg, .jpeg, .png, .webp, .txt, or .pdf

2) URL - You can give any files available on internet or your asset management or content hub, Basically any public URL and it will extract the content from it, Only above file extensions are allowed.

3) Text : Just paste a raw text and it will do the extraction.

With content extraction, It not only extracts but also creates an item based on selected template and fill those data in.

Way to go #SitecoreStream team, I keep my self aligned with new rollouts to get my hands onto latest developments

I hope this article will give other people highlights of what have been released so far.

I have some webinars on Stream which i took in past, Do have a look for better understanding of what is stream and what it can do from marketers perspective and from content author perspectives too

Pasting the links here so you can go and check them out

Part-1 : Ideation to Execution, Do more in era of less

Part-2: Configuration to Consumption

Podcast - Stream basics for everyone

NOTE: By the time you read this blog sometime in the future, There could be a new version released, So this blog was published on 30th Sep-2025, So don't get confuse if you happen to read in future where Stream already have new versions released.

Reference - Sitecore Stream



Comments

Popular posts from this blog

High CPU to completely normal CPU - SXA issue, SXA pages not loading in mobile device

  Hi Team, Today i am going to share one of the nightmarish issue with you all, We are having Sitecore 9.1.1 hosted in azure PaaS environment Our site was working just fine and no noise, but we have been working on a feature release where 7-8 months of development needed to be released to production, Big GO LIVE event right?  Also to make the development smoother we also introduced BLUE/GREEN deployment slots in the same release, so we can easily SWAP slots and go live Everything went well, we went live, we even did load and performance testing on our staging and pre-prod and we were confident enough of results Very next day we started getting "SITE DOWN" alerts, and also product owners and clients mentioned that site is very slow for them in US time and in our morning when we were accessing it, it was working lighting fast so we were clue less at start, but we started digging  1) First thing caught our eyes were HIGH CPU spikes, in US time, also without any traffic CPU u...

An error occurred while receiving the HTTP response to This could be due to the service endpoint binding not using the HTTP protocol. This could also be due to an HTTP request context being aborted by the server (possibly due to the service shutting down). See server logs for more details.

You have noticed many times that everything was working fine and suddenly the below error starts coming and you find no way to work it out An error occurred while receiving the HTTP response to This could be due to the service endpoint binding not using the HTTP protocol. This could also be due to an HTTP request context being aborted by the server (possibly due to the service shutting down). See server logs for more details. The reason for this is the receiving size of WCF service is smaller then the data which is coming from service It was working before because it was small,So you will have to try to increase the receiving setting in your end point,Possible settings can be following maxStringContentLength="2147483647" maxReceivedMessageSize="2147483647" maxBufferSize="2147483647" maxArrayLength="2147483647" That would definately help you!!!