If you already using DevOps for deployments with your Content Hub environments, then you probably already aware of the breaking change that Sitecore introduced a few months ago. You can read the full notification on the Sitecore Support page The new version of the package import/export engine become the default in both the UI and CLI from Tuesday, September 30 according to the notification. Because of the breaking changes introduced, this means existing CICD pipelines won’t work. In fact, there is a high risk of breaking your environments if you try use existing CICD pipelines without refactoring.
In this blog post, I will look into details what breaking changes were introduced and how to re-align your existing CICD pipelines to work with the new import/export engine.
So what has changed in the new Import/Export engine?
Below is a screenshot from the official Sitecore docs summarizing the change. You can also access the change log here.
There is no further details available from the docs on specifics of the breaking change. However, it is very straightforward to figure out that Sitecore fundamentally changed the package architecture in the new import/export engine.
Resources are grouped by type
Within Sitecore Content Hub Import/Export UI, you have an option to Export components using both the previous/legacy engine and the new engine. As shown below, you can notice a toggle for Enable Legacy version, which when switched on will allow you to export a package with previous/legacy engine.
Also we can note that Publish definition configurations and Email templates are now available for Import/Export with the new engine. Email templates are unchecked by default.
If you did a quick comparison between the export package from the old/legacy engine vs the new engine, it comes clear that Sitecore has updated the packaging structure to organise content by resource type rather than by export category
This change makes navigation more straightforward and ensures greater consistency throughout the package.
Summary of the changes between legacy and new export packages
Below is a graphic showing how the package structure was changed. On the left hand-side, we have the legacy/old package and on the right hand side is the new one.
Full comparison of package contents between old and new
Below is a more detailed comparison, showing how the packages differ.
Component
Legacy package sub folders
New package sub folders
Copy profiles
copy_profiles
entities
Email templates
n/a
entities
Entity definitions
entities schema option_lists
datasources entities schema
Export profiles
export_profiles
entities
Media processing
media_processing_sets
entities
Option lists
option_lists
datasources
Policies
policies
datasources entities policies schema
Portal pages
entities portal_pages
datasources entities policies schema
Publish definition configurations
n/a
entities
Rendition links
rendition_links
entities
Settings
settings
entities
State flows
state_flows
datasources entities policies schema
Taxonomies
taxonomies
datasources entities schema
Triggers
actions triggers
entities
Scripts
actions scripts
entities
Resources are grouped by type
Instead of separate folders like portal_pages, media_processing_sets, or option_lists, the new export engine places files according to their resource type.
For example:
All entities are stored in the entities/ folder.
All datasources (such as option lists) are found in datasources/ folder
Policies and schema files have their own dedicated folders.
Each resource is saved as an individual JSON file named with its unique identifier.
Related components are now separated
When a resource includes related items—such as a portal page referencing multiple components—each component is now saved in its own JSON file.
These files are no longer embedded or nested under the parent resource.
Updating your CICD pipelines
It is very straight forward to update you existing CICD pipelines once we have analysed and understood the new package architecture. You can revisit my previous blog post where I covered this topic in detail You need to simply map your previous logic to work with the new package architecture. You will also need to re-baseline your Content Hub environments within your source control so that you are using the new package architecture.
Next steps
In this blog post, I have looked at the new Content Hub Import/Export engine. I dived into how you can analyse the packages produced from the legacy/old engine and compared it with the new engine. I hope you find this valuable and the analysis provides a view of what has changed in the new package architecture.
Please let me know if you have any comments above and would like me to provide further or additional details.
As you may be aware, the Marketer MCP now has a capability to integrate with Microsoft Copilot studio. You can now connect your Microsoft Copilot Studio agents to the Sitecore Marketer MCP for seamless access to Sitecore’s marketing features.
The Marketer MCP is the Model Context Protocol (MCP) for marketing in Sitecore. It connects AI agents to Sitecore tools through the Agent API, providing secure access across the entire digital experience lifecycle.
In this blog post, I will walk you through a step-by-step guide, complete with screenshots.
Pre-requisites
Before you begin, make sure you have:
A valid Sitecore account with required permissions
A valid Microsoft Copilot studio account with access permissions to Create agents and Create Custom Connectors
Step 1 – Create a new agent in Copilot Studio
Open Copilot Studio and either create a new agent or open an existing one.
As shown in the screenshot below, specify the following minimal details for your agent:
Name: The name of your agent
Description: Description of your agent
Icon: You can choose an icon for your agent (optional)
Step 2 – Add a tool to the agent
Go to the Tools tab for your agent then click Add a tool.
Select New tool then choose Model Context Protocol. The MCP onboarding wizard opens
Enter the following details, as show in screenshot below
Server name – for example, Marketer MCP.
Server description – a short description of what the Marketer MCP does.
Open a new browser window, paste the updated URL into the address bar and press Enter.
In the Marketer MCP authorization request dialog (see screenshot below), click Allow Access.
This will prompt you to login to your Sitecore Cloud Portal
Then select the organization and tenant you want to use when interacting with the MCP server (as per screenshot below)
Return to the Add tool dialog in Copilot Studio. When it shows that you’re connected to the MCP server, click Add and configure.
You should now see the Marketer MCP details and its tools enabled and ready to use. You can begin entering prompts to interact with Sitecore through the MCP.
Step 3 – Get prompting
From your Copilot prompt text area, you can now use natural language to prompt and perform actions in SitecoreAI. The first time you write a prompt, you may see a connection warning message shown below.
Simply follow the Open connection manager link to get connected. The link will open the dialog shown below
Click on Connect link. You will now get a response from your Sitecore AI as shown below.
Troubleshooting
You may come across some issues when establishing the connectivity into Marketer MCP from Copilot Studio. Below are the issues I encountered and how I resolved them.
Issue 1: Timeout error
I got this error when Creating the connection:
Issue 1 Resolution:
I simply repeated that step for the second time and issue was resolved
Issue 2: Environment Access permission error
The error below may occur when your Copilot Studio account doesn’t have access permissions to create a custom connection
Issue 2 Resolution:
Work with your ITS teams to provision the correct level of needed access in Copilot Studio
Next steps
In this blog post, we looked at a step-by-step guide on how to set the Marketer MCP integration with Microsoft Copilot Studio. We looked at potential connectivity issues that you may encounter and how to resolve them to get it working.
The Marketer MCP provides tools to create content, manage campaigns, run marketing automation, and handle content management. This is an evolving tool and remember to check latest updates from Sitecore.
The Marketer MCP is only reliable for the supported use cases listed here. Responses outside this scope have not been validated by Sitecore and might be inaccurate.
The content below was generated with help of AI. I prompted AI to help create an executive summary and curated list that covers everything AI in upcoming Sitecore Symposium 2025, scheduled for November 3-5 in Orlando.
Executive Summary: The AI Mandate at Sitecore Symposium 2025
Sitecore Symposium 2025, will center on the fundamental redefinition of digital experience driven by Artificial Intelligence. The overarching theme, “Next is Now,” acknowledges that AI has profoundly altered consumer behavior, replacing traditional search with summarization and converting clicks into definitive conclusions. This shift mandates that brands meet customers across novel channels and touchpoints that did not exist recently.
The New Paradigm: Augmentation vs. Automation – A key strategic indicator of Sitecore’s direction is articulated by CEO Eric Stine, who will emphasize the limitations of existing, disconnected marketing solutions and the fragmented experiences they create. The strategic focus of Sitecore’s platform evolution is clear: prioritizing augmentation over automation and relevance over reach. This positioning redefines Sitecore’s AI not merely as a tool for reducing labor costs, but as a critical growth engine designed to scale human creativity and accelerate the marketer’s capacity to connect, create, and compete.
Industry Context and Strategic Sponsorship: Accenture’s Agentic Shift – The focus on agentic frameworks at Sitecore mirrors a broader industry trend among global professional services firms. Accenture, for example, is leveraging similar principles, having recently launched its “Physical AI Orchestrator” solution. This cloud-based offering integrates AI agents from Accenture’s AI Refinery™ platform to help manufacturers create software-defined facilities and live digital twins, highlighting the enterprise reliance on autonomous, goal-oriented AI systems. Accenture is participating as a Strategic Sponsor at Sitecore Symposium 2025. Furthermore, they are the exclusive partner for the highly anticipated #ExecutiveExchange, a premier program designed for senior industry leaders to explore the possibilities of content, data, and AI, and gain valuable actionable insights. Joined by Sitecore’s leadership and a select group of global thought leaders, this Exchange is designed to spark ideas and foster meaningful connections for C-suite attendees.
The Three Pillars of Sitecore’s AI Strategy – The Symposium agenda is structured to address the complete lifecycle of enterprise AI adoption, from strategic planning to implementation and governance. The sessions reveal a focus on three core pillars essential for achieving the AI advantage:
Strategic Vision: Establishing the architectural foundation, the product roadmap, and the necessary governance frameworks for the future “Agentic Web.”
Tactical Execution: Showcasing specific, measurable use cases in both content orchestration (velocity and compliance) and developer acceleration (code generation and platform governance).
Real-World Validation: Presenting client stories that validate how global brands build trust, achieve scalable personalization, and modernize their architecture to be truly “AI-ready.”
Strategic Vision: Sitecore’s AI Roadmap and Agentic Future
The strategic sessions at Symposium will focus on establishing the architectural and corporate intent behind Sitecore’s AI investments, demonstrating a shift beyond rudimentary generative capabilities toward advanced, integrated intelligence.
Defining the Advantage: Speed, Scale, and Trust – The General Session, “Speed, scale, and trust: The AI advantage for marketers,” sets the executive tone for the event. Sitecore Chief Product Officer Roger Connolly, joined by leaders from major global enterprises including Infor, Regal Rexnord, AFL Global, and Berkeley Homes, will discuss how intelligence and imagination must work together to unlock entirely new ways to compete in the digital space. The discussion centers on utilizing AI to accelerate content delivery, amplify creative output, and, most critically, build lasting trust at scale. The repeated emphasis on “trust” is highly significant in the enterprise context. It signals that Sitecore recognizes the profound corporate liability associated with AI outputs, such as hallucinations or compliance breaches. Therefore, the core strategy involves developing AI solutions with inherent guardrails for brand safety, data integrity, and regulatory adherence, positioning AI not just as an efficiency tool, but as a critical competitive advantage built on verifiable governance.
The Agentic Framework: The Technical Roadmap – A key session provides an exclusive look into Sitecore’s product roadmap, focusing on how its platform is being reimagined with intelligence. This session details how advanced agentic frameworks will power intelligent and seamless workflows across the entire product suite. This move toward agentic frameworks signifies a major architectural transition. Rather than relying on rigid, sequential DXP workflows, Sitecore is building decentralized, goal-oriented AI entities—or “agents”—that possess the autonomy and context needed to execute complex, cross-product tasks. These AI agents will be empowered to “plan, synthesize, and act” wherever assistance is needed. The necessary precursor for this capability is a fully composable, API-first backbone, such as XM Cloud, which provides agents with the required data context and execution permissions to operate effectively and autonomously across the DXP ecosystem.
The Foundational Imperative: The Experience OS – For AI acceleration to be effective, a unified and governed digital ecosystem must be in place. The session “The Experience OS: Preparing Digital Foundations for AI Acceleration” addresses this foundational requirement. The analysis indicates that fragmented, ungoverned legacy systems (characterized by low content and data maturity) inevitably lead to inconsistent AI outputs and dramatically increase the human resources required for correction and oversight. Leaders from Horizontal Digital and Gradial will share how AI can accelerate site operations only after a foundation is built that successfully unifies teams, standardizes components, and establishes scalable governance. Establishing this “Experience OS” is therefore the fundamental structural step that enables the desired strategic outcome: efficiency, consistency, and accelerated delivery across all digital properties.
Strategic Partner Spotlight: Accenture’s AI and Innovation Sessions
Accenture’s presence at Sitecore Symposium 2025 extends far beyond the Executive Exchange, featuring a strong lineup of engaging sessions that showcase innovation and customer impact, particularly around AI-driven strategies. Attendees are encouraged to visit Accenture at booth 229 to connect with their Sitecore experts and explore how AI-driven content strategies are shaping the future of digital experience.
Key sessions featuring Accenture include:
Main Stage Showcase: Accenture will present a “CoNEXTion Partner” segment alongside their customer, showcasing innovation and customer impact.
Fireside Chat with Vercel: “Driving Engineering Innovations with Generative AI & Sitecore,” featuring Joe Kehoe.
Healthcare Panel Discussion: A healthcare-focused panel, moderated by Benjamin Adamski from Accenture and featuring insights from Anish Chadalavada (Gradial Co-Founder), Brice Bauer (Accenture), and Adeline Ashley (Sitecore’s Healthcare Industry Expert).
The following table provides a curated list of key Sitecore Symposium 2025 agenda items, summarizing their strategic importance, technical focus, and client application.
Session Title
Core Theme/Focus
Speakers/Client Case Study
Summary and Key Takeaways
Registration Link
Speed, scale, and trust: The AI advantage for marketers (General Session)
Executive Strategy & Trust
Roger Connolly (Sitecore CPO), Infor, Regal Rexnord, AFL Global, Berkeley Homes
Executive insights on positioning AI as an advantage, leveraging intelligence and imagination to accelerate delivery and build lasting trust at scale, moving beyond mere automation.
Sitecore’s AI roadmap: How agentic frameworks will transform digital experience
AI Roadmap & Agentic Architecture
Sitecore Product Team
Exclusive look at the AI roadmap, demonstrating how future AI agents will be empowered to “plan, synthesize, and act” across the DXP for seamless, intelligent workflows.
Harnessing AI for content creation: Introducing AI Experience Generation for Sitecore XM Cloud
Content Use Case & Product Demo
Richard Seal (Principal Engineer, Sitecore), Mo Cherif
Practical demonstration of the new AI Experience Generation app in the XM Cloud Marketplace, detailing AI-driven page creation and the technical architecture for building Marketplace extensions.
Orchestrating the Future: AI-Powered Content Operations with Sitecore, Gradial, and EPAM
Content Supply Chain & Operational Efficiency
Timothy Marsh, Amanda Follit (EPAM)
Strategic methods to overcome content fragmentation and slow cycles by implementing intelligent, orchestrated AI content supply chains that enhance audience resonance.
Addresses the non-technical hurdles of AI implementation, focusing on organizational resistance, strategic roadblocks, and how to effectively manage change in the enterprise.
Creating an AI-powered content supply chain for regulatory markets using Sitecore
Industry Use Case & Compliance
Mike Shaw (CI Digital)
Essential session for high-compliance sectors (H&LS, FS) detailing how AI-driven automation ensures governance, streamlines approvals, and transforms regulatory data into compliant narratives.
Cutting Sitecore development time by up to 80% with AI
Developer Tooling & Code Generation
Rajitha Khandavalli (Meritage Homes)
Deep dive into leveraging context augmentation with MCP Servers and integrating external data (Jira, Figma) to enable accurate, high-speed, AI-generated code generation, drastically reducing development cycles.
Deliver Measurable Operation Efficiency with Agentic AI
Platform Governance & DevOps
N/A (HelixGuard Focus)
Introduction to the HelixGuard “AI co-pilot,” blending MCP intelligence, analytics, and automation to proactively elevate platform performance, governance, and experience delivery in an agentic framework.
Scaling smarter: How Vizient uses Sitecore to personalize, integrate, and innovate in a complex B2B healthcare landscape
Client Story & AI Foundation
Jonathan Price (Americaneagle.com)
Case study detailing how a complex B2B healthcare organization established “AI-ready infrastructure” and achieved smart personalization and faster time to market following a digital transformation.
The Experience OS: Preparing Digital Foundations for AI Acceleration
Infrastructure Strategy & Governance
Pam Butkowski (Horizontal Digital)
Strategic session outlining the necessary pre-conditions for AI success: unifying teams, standardizing components, and establishing scalable governance models for faster delivery and consistency.
Conclusion: Leading the Future of DX with Sitecore AI
The Sitecore Symposium 2025 agenda confirms a decisive strategic pivot: Sitecore is transitioning from providing a traditional Digital Experience Platform (DXP) to offering an Intelligent Experience OS built on the principles of augmentation and agency. The analysis of the session topics suggests that the focus is on three intertwined strategic vectors: the deployment of agentic frameworks to automate complex, cross-platform workflows; the delivery of measurable efficiency via AI-driven content orchestration and developer acceleration; and the commitment to enterprise governance to ensure trust and compliance in high-stakes environments.
For digital leaders and technologists, the Symposium presents a compelling narrative that moves beyond simple generative AI experimentation. It outlines a comprehensive, strategic path forward where AI serves as the catalyst for continuous innovation, provided that organizations first establish the required foundational agility, standardization, and change management principles necessary to support a truly intelligent and composable digital future.
Next steps
In this blog post, we looked at the upcoming Sitecore Symposium 2025, where we looked at everything AI related. With help of AI, I have managed to review the agenda items and come up with this curated list. Stay tuned for future posts, feel free to leave us comments and feedback as well.
In this blog post, we are going to explore Agentic AI prominent integration architectures. We are going to discuss RAG, MCP and A2A architectures. If you are not familiar with these terminologies, don’t worry as you are in good company. Let us begin with how we got here in the first place.
What is an Agentic AI?
An AI agent is a system designed to pursue a goal autonomously by combining perception, reasoning, action, and memory. Often built using a large language model (LLM) and integrated with external tools. These agents perceive inputs, reason about what to do, act on those plans, and whilst also remembering any past interactions (memory).
We will now expound more on some of the key words below:
Perception – this is how your agent recognises or receives inputs such as a user prompt or some event occurring
Reasoning – this is the capability to break down a goal or objective into individual steps, identify which tools to use and adapt plans. This will usually be powered by an LLM
Tool – is any external system the agent can call or interact with, such as an API call or a database
Action – is the execution of the plan or decision by the agent, the act of sending an email for example, or submitting a form. Agent will perform the action leveraging the tools
What is Retrieval Augmented Generation (RAG)?
Carrying on with our AI agent conversation, suppose we need to empower our agent with deep, factual knowledge of a particular domain. Then RAG is the architectural pattern to use. As an analogy, think of RAG as an expert with instant access to your particular domain knowledge.
This pattern allows us to connect an LLM to an external knowledge source, which is typically a vector database. Therefore, the agent’s prompts are then “augmented” with this more relevant, retrieved data before the final response is generated.
Key benefit
With RAG, agents drastically reduces “noise” or “hallucinations” ensuring that the responses and answers are based on specific and latest domain knowledge or enterprise data
Some use cases
Q&A scenarios over Enterprise Knowledge – think of an HR agent that answers employee questions by referencing HR policy documents. Ensures the answers are accurate and citations of policies
Legal Team agent – that analyses company data rooms, summarizing risks and cross-referencing findings with internal documents and playbooks
What is Model Context Protocol (MCP)?
MCP is an open-source standard for connecting AI applications to external systems. As an analogy, think of MCP as a highly skilled employee who knows exactly which department (API) to call for a particular task.
This is an emerging standard for enabling agents to discover and interact with external systems (APIs) in a structured and also predicable manner. It is like a USB-C for AI agents
Key benefit
MCP provides a governable, secure and standardized way for our agents to take action and interact with enterprise systems, doing more and going beyond simple data retrieval as in the use cases for RAG
Some use cases
Self-service sales agent – think of a Sales agent that allows a salesperson to create a new opportunity in a company CRM, then set up and add standard follow-up tasks as required. The agent does discovery of available CRM APIs, understand the required parameters and executes the transactions securely.
An accounting agent – think of automated financial operations where upon receiving an invoice in a email inbox, the agent calls the ERP system to create a draft bill, match it to Purchase Order and schedule a payment.
What is Agent-to-Agent (A2A)?
This does what is says on the tin. Multiple, specialized or utility agents collaborate to solve a problem that is too complex for a single agent. The graphic below illustrates this collaboration. As an analogy, think of a team of specialists collaborating on a complex project.
Key benefit
A2A enables tackling highly complex, multi-domain problems by leveraging specialized skills, similar to a human workforce.
Some use cases
Autonomous product development team – think of an autonomous product development teams consisting of “PM agent”, “Developer agent”, “QA agent” all working together. PM writes specs, Developer writes code and QA tests the code, iterating until a feature is completed. Specialization means agents can achieve higher quality of outputs at each stage of a complex workflow.
So which is it, RAG, MCP or A2A?
As architects we often rely on rubrics when we need to make architectural decisions. With Agent AI solutions, you can use a set of guidelines that best helps you assess the business domain problem and come up with the right solution. Below is an example rubric to help with your assessments and criteria when to leverage RAG, MCP or A2A.
Start with a goal
Agentic AI solutions are not any different. There is no “one size fits all” solutions. Always start with a goal, business objective so you can map the right Agentic AI solution for it. Sometimes Agentic AI many not be the right solution at all, don’t just jump on the bandwagon.
Trends and road ahead
Agentic AI is at very early stages and expect more emergence patterns in coming days and months. We may need to combine RAG and MCP and leverage a hybrid approach to solving AI problems. We already seeing the most valuable enterprise agents are not pure RAG or MCP but a hybrid.
Next steps
In this blog post, we looked at prominent integration architectures in this age of Agent AI. We explored RAG, MCP and A2A architectural patterns. We also looked at some of the use cases for each as well as key benefits we get from each pattern. We finished with a sample architecture rubric that can be leveraged.
Stay tuned for future posts, feel free to leave us comments and feedback as well.
I previously blogged about Sitecore Stream Brand Management and looked at a high level architecture on how the Brand Kit works under the hood. Today, I continue this conversation and look at a more detailed step-by-step guide on how you can start integrating with the Stream Brand Management APIs.
As a quick recap, Sitecore have evolved the Stream Brand Management to provide a set of REST APIs to manage life-cycle of the brand kit as well as getting a list of all brand kits. You can now use REST APIs to create a new brand kit, including sections and subsections, and create or update the content of individual subsections. You can also upload brand documents and initiate the brand ingestion process.
Brand Management REST API (brand kits, sections/subsections)
Document Management REST API (upload/retrieve brand documents).
These new capabilities opens opportunities such as allowing you to ingest brand documents directly from your existing DAM. You could also integrate them with your AI agents so that you can enforce you brand rules
Step 1 – Register and get Brand Kit keys
Brand Management REST APIs use OAuth 2.0 to authorize all REST API requests. Follow these steps below:
a) From your Sitecore Stream portal navigate to the the Admin page and then navigate to Brand Kit Keys section, as shown below.
b) Then click on Create credential button which opens the Create New Client dialog similar to one shown below. Populate with the required client name and a description, then click on Create
c) Your new client will be created as shown below. Ensure you copy the Client ID and Client Secret and keep them in a secure location. You will not be able to view the Client Secret after you close the dialog.
Step 2 – Requesting an access token
You can use your preferred tool to a request the access token. In the sample below, I am leveraging Postman to send a POST request to the https://auth.sitecorecloud.io/oauth/token endpoint.
client_id This is the Client ID from previous step
client_secret This is the Client Secret from previous step
Sitecore API Catalog lists all the REST APIs plus sample code on how to integrate with them. Below is a snapshot of the list of operations at the time of writing this post:
Have you started integrating Sitecore Stream Brand Management APIs yet? I hope this step-by-step guide helps you start exploring the REST APIs so you can integrate them with your systems.
Stay tuned for future posts, feel free to leave us comments and feedback as well.
In this blog post, we will explore further How the Brand Aware AI works, by looking at the architecture of Agents and how we bring them to life in our Stream Brand Assistant agent. There is also an accompanying video series on my YouTube channel.
What is an agent?
An agent is simply a software service that uses AI to assist users with information and task automation: An agent does a task, Take this do it and let me know when you are done.
We have three main elements on an Agent, as shown in the architecture below:
Model – We now have access many Large Language Models and Small Language models that does the thinking
Knowledge – This is the Instructions, data sources that enable the agent to ground prompts with Contextual data
Tools – A set of tools that agents can invoke such as retrieving information, Actions such as making API calls, and keeping a thread in memory of current conversation. You can also create custom tools using your own code or Azure Functions
How Brand Assistant agent works
Below are the steps involved when interacting with the Brand Assistant within Sitecore Stream:
The user enters a prompt – the user enters a prompt in Brand Assistant – such as a question or an instruction as shown during the demo by Alessandro earlier.
The system passes information from the Brand Context – the system automatically provides information from the Brand Context brand kit section as a system prompt.
Copilot analyzes if it can answer from Brand Context – the thinking process begins. The Brand Assistant evaluates whether the information passed from the Brand Context alone is enough to answer the prompt.
Based on the analysis, the process continues in one of two ways:
Generate a direct response – if the Brand Context provides sufficient information, the Brand Assistant generates a direct response using only that content.
Invoke other AI agents – if the Brand Context doesn’t answer the prompt and more information is needed, the Brand Assistant automatically activates one or more AI agents to search and organize the information and generate a response:
Search agent – uses tools to find information from your brand knowledge, web searches, or both.
Brief agent – activated only when the user specifically requests a campaign or creative brief
•Summary agent – condenses all retrieved information into a concise, relevant response.
As generative AI continues to evolve and become more deeply embedded in our digital landscape, its applications have expanded well beyond simple chat interfaces. Today, these models are powering intelligent agents capable of autonomously executing complex tasks and streamlining operations.
Forward-thinking organizations are now harnessing this potential to build AI-driven agents that orchestrate business processes and manage workloads in ways that were once out of reach.
In this post, we’ll take a closer look at how Sitecore is embracing this shift—leveraging Brand-Aware AI to transform the way enterprise marketing teams operate. There is also an accompanying video series on my YouTube channel.
Some of pain points that marketers face today
Before we look at how Sitecore are leveraging AI with Sitecore Stream, let me set the context around some of the pain points that marketers face today:
Keeping brand consistency – challenges around keeping their brands aligned with latest trends, efficiently improving previous campaigns & briefs, assets to keep a consistent brand tonal voice
Taking longer time to make decisions – challenges around decision making turnaround time due to manual processes and large volumes of content and material that needs reviewing as part of the creative process
Availability of robust Self-Serve tools – challenges around lack of tools for efficient task planning, content supply chains, moving faster removing blockers and having more control
To address these challenges, Sitecore has taken steps to introduce AI-Driven marketing by creating Sitecore Stream. Sitecore Stream is the way Sitecore are infusing AI capabilities across their products.
Sitecore Stream consists of three components: Brand-aware AI, Copilots & agents and Agentic workflows, as discussed below.
Brand-aware AI
This is what powers Sitecore AI tools to generate content that reflects your brand’s identity. This is made possible by a foundational understanding of your brand called brand knowledge. In the next slide, I will show in detail how this brand knowledge is created in Sitecore Stream.
Brand-aware AI enables marketers to create high-quality content faster, by combining deep brand knowledge with real-time Web insights to generate outlines and long-form drafts in seconds.
Copilots and agents
These are the AI assistants designed to increase marketers’ productivity by speeding up decision-making and task execution. Copilots are for humans, Agents are for processes. Copilot is the UI for AI – the chat based interface is where you can ask specific questions about your brand. Better still, you can actually brainstorm with AI, e.g. you want to create new content for blog post or a campaign brief.
Agentic workflows
These are advanced tooling to orchestrate tasks and streamline marketing project management across teams. This capability enables you to discover gaps in your campaigns and reduce planning time with help of AI that understands your brand and project context.
You can essentially ideate & plan entire campaign with help of AI. AI will recommend key top deliverables to bring your campaigns to life and recommend tasks to get them completed within seconds. Providing full agentic experiences to marketing campaigns, which human-in-the-loop too keep or discard suggestions
How to create your brand knowledge in Stream
This involves a 6-step process as outlined in the infographic shown below. If you are managing a multi-brand enterprise, you can repeat this process for each of your separate brands. Essentially creating multiple brand kits within Sitecore Stream.
Next steps
Have you started using Sitecore Stream with your Sitecore products yet? You can reach out to Sitecore directly by filling in the ‘Sitecore Steam: Get Your Demo’ form on their website.
Sitecore User Group Conference Europe 2025 has just concluded. It was held over two days in Antwerp city, Belgium last week (3-4 April 2025) and I was one of the lucky attendees. In this blog post, I will be sharing my experiences and key takeaways from the conference.
Firstly, I would like to thank the SUGCON organizers and the Sitecore community for making the event such a success. The choice of venue was spot on! Held in A Room with a ZOO – Antwerp, Belgium, the venue was most accessible via train seamlessly connected to the adjacent Belle Époque international station, which links to the European rail network. And right next to the Antwerp Central Station, the most beautiful station in the world. The food and hospitality were top notch, with variety of Belgian cuisine and desserts on the menu.
Secondly, the event schedule was the best you could have asked for. It catered for both developers and marketers alike, with keynotes from Sitecore leadership team, Sitecore product updates, great Sitecore community contents and demos alike. This year SUGCON also provided an accompanying SUGCON app to help personalise your sessions, keep track schedule and the room switches! Whether it was the usual ad hoc chit chat along corridors with other attendees, over lunch and dinner everyone was engaged. Including a Community Scavenger hunt app powered by Deckle, that kept everyone engaged and exploring the venue with many prizes won by those on top of the leaderboard at close of the event!
Keynote: Powering the Future of Sitecore Together
Dave O’Flanagan (CEO, Sitecore)
Roger Connolly (CPO, Sitecore)
Danny Robinson(CTO, Sitecore)
Keynote from Dave: This was Dave’s 4th SUGCON, and his first as Sitecore CEO. Dave shared stats that highlighted the key role our Sitecore community in success of Sitecore, such as 100+ user groups with over 30k members across 30+ countries, producing over 1k+ developer artefacts. Keynote was held in the “Darwin Room” which had a huge skeleton of a whale provided a great backdrop of his “Adapt” messaging. He reminded us, to echo famous Darwin mantra, that those who “evolve” and “adapt” thrive and survive. We are at what he called “The AI Inflection point”. His key message was he’s very much building Sitecore as an “AI First” company going forward. We will see marketing significantly change, let’s embrace the “The Intelligent DXP” built on a world-class CMS that is underpinned by AI (Sitecore Stream). With AI capabilities already being infused across Sitecore products and as AI agents are becoming more capable, Sitecore can deliver on their promises such as personalisation.
Keynote from Roger: Roger swiftly picked on from where Dave left and his messaging revolved around Content with Context will fuel the AI future. Content is King. Simple. He challenged whether “Is AI the UX of the future?” as we are seeing UX patterns shifting fast. With AI capabilities already being infused across Sitecore products, you can use Sitecore Stream with DXP 10.2+ and XM Cloud to generate content. As well as Contextual AI tagging and Visual Search in Content Hub which solves the metadata and retrieval main issues he sees within Content Hub. He also touched on the changing face of Search in the AI age and showcased the AI-powered A/B/n testing, personalisation and language translation tools available to us now.
Keynote from Danny: Last but not least, Danny shared his vision and roadmap with his key messaging also revolving around Innovating faster with AI. He re-emphasized Dave’s “Intelligent DXP” by showcasing how he is evolving the architecture for the future. He is also very much driven in improving developer experience by enabling developers with tools and SDKs they need. He sees this as ground-up, embedded AI capabilities, federated content, AI-powered site creation and bringing Sitecore Stream to all products. He promised that on June 4th, 2025 he will be making a significant future innovation announcement, so keep an eye on that date.
Key product roadmaps and announcements
Throughout the conference, we were given key product roadmap announcements.
a) Delivery on the promise, Sitecore Stream set of AI capabilities are available now.
Sitecore Stream in itself is not a product, but a set of AI capabilities that are already being infused across Sitecore products.
Available now on DXP 10.2+
Available now on XM Cloud
Available now for A/B/n testing/personalisation
Available now on Content Hub for Contextual AI metadata auto tagging and AI Visual Search
b) Sitecore’s Marketplace & Developer program
We had two separate sessions around Sitecore Marketplace. First session by Liz Nelson (Product Lead of XM Cloud) and Spyros Misichronis (Marketplace Architect, Sitecore) where they showcased the Sitecore XM Cloud Marketplace Apps, which she called an “Extensibility Umbrella” comprising of a Public Portal and Developer Marketplace.
Developers can now leverage the CLI, SDK on GitHub to build extensions to integrate with XM Cloud APIs.
Developers can embed features into Pages directly or creating standalone tools.
Developers can build applications that enhances functionality and streamline workflows
Spyros Misichronis demonstrated a live demo of building a sample Marketplace App leveraging the developer tooling.
The second session was by Krassi Eneva and Justin Vogt (Product Managers from Sitecore) who took a deep dive into more detail and showcased different use cases for Sitecore’s Marketplace and Developer program. Sitecore Marketplace brings the following benefits: faster time to value, flexibility & extensibility and growth & enablement.
Contribute to the community or build for your use cases. Sitecore is providing three models for this
Custom Single Tenant – Built for a specific organization & available right away
Custom Multi Tenant – Build for selected number of organizations & partner managed
Public – Available to any Sitecore customer or partner
What can you build? This is about what experience can you tailor for your end-users and not what type of apps. Scope is wide and covers creation of the following:
apps to the Sitecore portal
apps within XM Cloud
apps within custom touchpoints such as panels in Page Builder in context of a page, fields editor and panels within sites dashboard
Early Access Developer Program – Sitecore’s Marketplace Early Access Program is currently in progress and Sitecore is actively working with the following:
Technology Partners
Sitecore Partners
Internal Sitecore teams
Individual community members
Is this like an App store we are used to? Similar analogy if you like. You are responsible for testing your own apps, responsible for supporting them in the marketplace. Apps once submitted will undergo review process before approval to Sitecore’s marketplace
This was a major announcement that brings a solution to plug in gaps currently available in XM Cloud as result of moving from Platform DXP. They demonstrated cool apps like copying content between XM Cloud environments, leveraging third party content translations within XM Cloud UI among others. Interesting space to keep an eye on.
c) XM Cloud Content (previously known as “Content Service”)
Alistair Deneys (System Architect, Sitecore) session focused on showcasing the progress made with the Enterprise-grade, innovative headless “CMS” which we now know will be called XM Cloud Content. He set context by giving the brief history and evolution of CMS from the monolith old days, through headless and a look at the future as XM Cloud Content. He also introduced the XMC Content Architecture, diving into domain models covering the following:
Content Types define structure
Taxonomies define classification
Content is stored in Content Items
Fragments allow composition. He highlighted the preference for composition over inheritance in the design
He gave a live demonstration of the core set of APIs that underpin XM Cloud Content, walking through various scenarios on how you can build content using API-first.
Some of the key capabilities from XM Cloud Content are:
Entity lifecycle – Draft/Published/Archived
Worksets – new concept of publishing
Content Delivery – GraphQL endpoints includes tenant name. “IsDirectQuery=false” keeps query cleaner. Persisted queries, restrict query tokens to specific persisted queries, schema pinning
Fragments with composition over inheritance enables re-usability of set of fields thus a mechanism of delivering “system functionality and extensions”
Separate queries for “Pages” content, say, articles, news, etc
Query Token security enhancements such as disabling of Introspection
Content management capabilities: environment merging, availability & archive dates on content items, more field types, content collections among others
Sitecore Change Logs are running from XM Cloud Content
Developers will be excited with XM Cloud Content, although what was demonstrated is still in early development. Watch this space and future announcements.
d) Modernizing the JSS SDK and Starter Kits for XM Cloud
Liz Nelson (Product Lead of XM Cloud) and Christian Hahn (Technical Product Manager) unveiled groundbreaking updates to the JSS SDK and starter kits, designed to simplify workflows, eliminate legacy complexity, and enhance flexibility.
Welcome the “new” one. In summary, in the new solution
Split responsibilities
Only get what you really need
Reduce complexities and sizes
Some of key improvements shared in the session
disk size of the starter kit site folder reduced from 8MB down to 600KB
almost halving the bundle size
overall improvements in First Contentful Paint FCP metric of 200 milliseconds
editorial performance gains, with about 10x as many UI components can be added to an editable page
The SDK and documentation are available now, and currently in “Beta” but confident developers can start building new projects. Watch this space for announcements on the final releases which will be soon.
e) June 4th, 2025 – Future Innovation Announcement
Look out for an announcement from Danny Robinson(CTO, Sitecore) in June 4th
f) November 3-5, 2025 – Sitecore Symposium Orlando 2025
Sitecore Symposium 2025 is back and will be held at Walt Disney World Dolphin Resort, Orlando, the week of November 3, 2025. Ready to start your submission and step into the spotlight at Sitecore Symposium 2025 in Orlando, they are currently calling for speakers.
Key highlight sessions
With a total of about forty (40) sessions, it is impossible to attend them all. Below are some of my key highlight sessions that I attended. I will complete the list in a follow up blog post.
Session: XM/XP to XM Cloud Best Practices – Free Workshop
Summary: This was an early bird free workshop sponsored by Brimit which covered the best practices, decisions and considerations when migrating to XM Cloud. If you thinking of making the move, this session amplified what a migration path could look like. Sitecore provides XM/XP Migration Navigator as well and you can reach out directly to them.
Session: Optimizing your Content Hub development – Free Workshop
Summary: Another early bird free workshop sponsored by Brimit highlighting the productivity gains by leveraging Content Hub CLI in your workloads. A live CLI demo for developers and key takeaways in terms of best practices and optimising Content Hub DevOps journey.
Conclusion and Next steps
I observed a positive sentiment overall during the conference. There was positive energy and buzz throughout, and this was echoed in various social media posts as well. I look forward to reading and reviewing more feedback from other attendees. SUGCON Europe is a key event in our calendar and there is already talk about next year! We are also looking forward to SUGCON ANZ later in the year and Sitecore Symposium back again in Orlando during November 2025, with call for speakers now open.
This year I mostly created content within Content Hub, Sitecore Experience Edge and Sitecore Personalize space. This is where I felt there were gaps based on industrial client work I have done this year. I believe I have produced content that meets expectations in terms of quality, quantity, and visibility and more importantly, adds value to our community. This has been through blog posts, code sharing via GitHub, YouTube content, Product Feedback via Gartner Peer Reviews among other social channels:
I have continued online and offline conversations and driven Sitecore community engagement throughout 2024 in order to amplify the content I have created.
I regularly provide answers to questions from Sitecore community as well on our engagement channels
Next steps
For 2025, I look forward keeping up producing more valuable content in terms of quality, quantity, and visibility to our Sitecore community. I will be putting myself forward for public speaking events throughout the calendar year. I intent to continue identifying any gaps and filling them, providing product feedback, improvements, and references
Stay tuned and best of luck with those submitting the Sitecore MVP 2025 applications.
On the previous post, I looked at how to securely share your DAM assets externally by leveraging collections. Among other things, we covered four options you can use to secure the asset collections. One of the options involved defining a permissions policies on M.Asset (model for your assets) based on M.Collection (model for your asset collections). However, this option seems to come with some nuances and will not work by default. I will carry on the conversation to demonstrate how to make this option to work.
Why doesn’t the policy definition work?
In simple terms, the above policy states that we would like to allow all assets belonging to our collection named “External” to be downloadable. Simple. But it doesn’t work.
But why?
This is because the “Inherits security” setting for the CollectionToAsset relation is turned off by default. In other words, this means security related metadata (from the parents towards the children) can not be inherited while this setting is turned off.
M.Asset is a child of M.Collection (as shown below in the schema details for M.Asset definition). To access M.Asset schema page, click on Manage -> Schema -> then search for M.Asset
How do I turn on “Inherits security” for the CollectionToAsset relation?
Short answer is you can’t modify this by yourself. You will need support from Sitecore Technical Support to make this change for you. Please note CollectionToAsset is a system relation and is locked down to Super users as well.
You can raise Sitecore Support Cases using the Support portal and request the team to enable the “Inherits security” on CollectionToAsset on your environments. This should be actioned swiftly after which your policy definitions can start to work as expected.
Next steps
In this blog post, we have looked at how to make user group permissions policies on M.Asset based on M.Collection work. We looked at nuances that make this not to work by default and how to resolve and get it working. I hope you find this useful for your similar use cases.
Stay tuned and please give us any feedback or comments.
