Blog posts by Opti Chronicles

Commerce 15 and CMS 13: Optimizely’s Next Step Toward AI-Powered, Graph-First Commerce

Thu, 07 May 2026 22:55:12 GMT

Optimizely is preparing to release Commerce 15 in mid-May 2026, positioning this as a foundational shift—not just an upgrade. The direction is clear: move from fragmented tooling and isolated AI features toward a graph-first, AI-embedded commerce platform where search, content, and operations are unified.

The headline changes are not cosmetic. Visual Builder replaces legacy editing paradigms, OptiGraph becomes the default search and data layer, and Opal evolves from a set of tools into a core operational interface for commerce teams. At the same time, the upgrade path introduces real architectural considerations—especially for organizations still dependent on Find, legacy APIs, or external service layers.

For decision-makers, the implication is straightforward: Commerce 15 is where Optimizely is investing future innovation, particularly around AI agents and automation. The question is less “should we upgrade?” and more “how do we prepare to adopt a fundamentally different operating model?”

Market Context: Commerce Is Moving from Systems to Systems of Intelligence

Modern commerce platforms are no longer judged solely on catalog management, checkout performance, or integration flexibility. The competitive frontier has shifted toward:

Speed of content and campaign execution
Search and discovery quality (increasingly semantic and AI-driven)
Operational efficiency for merchandisers and marketers
Embedded intelligence across workflows

What’s often missed is that most commerce stacks still operate as systems of record, not systems of intelligence. Data exists—but it isn’t continuously activated.

Commerce 15 reflects a broader industry trend:

moving from “tools that support workflows” to “platforms that participate in workflows.”

The Optimizely Perspective: Commerce 15 as a Graph-First, AI-Embedded Platform

Commerce 15 is being framed as a modern, AI-powered, graph-first commerce platform

Three structural shifts define this positioning:

1. Graph as the foundation (not an add-on)

OptiGraph replaces Find as the default search and data layer, enabling unified indexing across CMS, commerce, DAM, and CMP.

2. AI embedded into workflows

Opal is no longer a side feature. It becomes part of day-to-day commerce operations, from product management to promotions.

3. Experience creation without developer bottlenecks

Visual Builder and integrated tooling shift control toward business users—particularly merchandisers.

This combination is what makes Commerce 15 feel less like a version upgrade and more like a platform reset.

What’s New (and Why It Matters)

Visual Builder: Merchandiser-Led Experience Creation

Visual Builder replaces the traditional on-page editor and is now embedded directly into commerce workflows.

Build PDPs, category pages, and promotions visually
Access all blocks, templates, and components in one interface
Reduce dependency on developer tickets

The practical impact is significant:

Faster campaign launches
Lower backlog pressure on engineering
More experimentation at the merchandising level

Or, as framed in April 28th Optimizely session Introduction to Commerce 15:

“Visual Builder gives your developers their time back.”

External Content: Breaking Down System Silos

Commerce 15 introduces stronger support for pulling data from external systems (ERP, PIM, etc.) into CMS.

Centralized product and content management
Reduced need for custom integration layers
Single UI for merchandisers

This is less about convenience and more about operational coherence.
When product data, content, and customer context live together, personalization and campaign execution become materially easier.

Embedded DAM: Content Operations at Scale

The embedded DAM brings:

AI-powered tagging
Automated renditions
Integrated asset workflows

For SKU-heavy organizations, this addresses a persistent bottleneck: managing media at scale without introducing content chaos.

CMP-to-CMS Publishing: Closing the Campaign Gap

Campaign workflows now connect directly to CMS:

Content moves from planning to publishing without manual handoffs
Templates and previews streamline execution
Alignment between marketing and web teams improves

This is a subtle but important shift—reducing the friction between strategy and execution.

OptiGraph: The Shift from Search Engine to Experience Layer

OptiGraph replaces Find as the default search and navigation engine.

Key capabilities include:

Unified indexing across platforms
Semantic, intent-aware search
Support for AI-driven context (Opal)

“Graph is now acting as the de facto experience/discovery layer and internal search provider instead of Find.”

This matters because search is no longer just about retrieval—it’s about interpretation and relevance in context.

Opal: From Feature to Operating Model

The most strategic change in Commerce 15 is how AI is positioned.

Available now:

Opal Chat for content and optimization
Product catalog translations
Promotions agent
Data-fetching tools via Graph

Expected next:

Product catalog management agent (bulk operations)
Expanded Opal Chat for commerce workflows
Google AI Search (leveraging vector-based retrieval)

The narrative is clear:

AI is moving from isolated capabilities into embedded commerce workflows.

In practice, this means:

Merchandisers can generate and optimize content in context
Promotions can be created via natural language
Catalog operations can be automated at scale

Commerce 14 vs Commerce 15: A Strategic Decision Point

One of the more important signals from the announcement:

Commerce 14 will receive limited future out-of-the-box agent support
Commerce 15 becomes the primary platform for all future AI innovation

This creates a clear fork in the road:

Stay on Commerce 14 → maintain stability, rely on custom solutions
Move to Commerce 15 → access future Opal agents and platform capabilities

For most organizations, this isn’t just a technical upgrade—it’s a roadmap decision.

What Merchants and Teams Gain

For Merchandisers

Greater autonomy (Visual Builder, Opal agents)
Faster campaign execution
Less reliance on dev cycles

For Marketing Teams

Direct CMP-to-CMS workflows
Better alignment between planning and publishing
Improved personalization potential

For Engineering

Reduced content-related workload
Opportunity to focus on higher-value architecture and integrations

For Leadership

Faster time-to-market
Improved operational efficiency
Platform aligned with AI-driven future capabilities

Migration Reality: What You Need to Plan For

This is where many organizations underestimate the effort.

1. Find → OptiGraph Migration

This is not optional.

Search logic must be re-implemented
Indexing strategies must be redesigned
Category and content rendering may need refactoring

2. API and Architecture Changes

Deprecated APIs require review
Content Delivery APIs are migration-only (not future-facing)
New development must align with a Graph-first approach

3. OptiID Becomes Mandatory

OptiID is required for:

Content Manager
DAM
Opal
Connect Platform

Organizations not already using it must plan for identity and access transitions.

4. Service API Timing

Not available at launch (mid-May)
Expected later in Q2 2026

If your implementation depends on Service API or PIM connectors, timing your upgrade becomes critical.

Risks and Trade-offs (Pragmatic View)

Even with a strong platform direction, there are real considerations:

Migration complexity (especially search and indexing)
Dependency alignment (Service API, connectors)
Organizational readiness (AI adoption, workflow changes)
Learning curve for new tooling (Graph, Opal, Visual Builder)

That said, these are not unusual for a major platform evolution—they’re the cost of moving to a more modern architecture.

What’s Often Missed

Most discussions will focus on features. The more interesting shift is operational:

Commerce 15 is designed to make merchandisers more self-sufficient and AI part of daily execution, not strategy decks.

That changes:

How teams work
How fast they move
How value is created

Conclusion: A Platform Shift Worth Planning For Now

Commerce 15 represents a decisive move by Optimizely:

From search engine → experience graph
From tools → embedded intelligence
From developer-led workflows → merchandiser-led execution

For decision-makers, the takeaway is not just “this is a new version.”

It’s this:

Commerce 15 defines where Optimizely is going—and where your commerce capabilities can go if you align early.

Next Steps for Leaders

Assess your current dependencies
- Find usage
- Service API reliance
- Identity model (OptiID readiness)
Engage your implementation partner early
- Review upgrade complexity
- Validate timelines against Q2 dependencies
Explore preview packages
- Understand Graph and Visual Builder in practice
- Evaluate Opal use cases relevant to your business
Align internal teams
- Prepare merchandisers for new workflows
- Define governance for AI usage (human-in-the-loop, approvals, auditing)

From Prompting to Production: Optimizely Opal University Cohort and the Future of Agentic MarTech

Tue, 28 Apr 2026 16:59:46 GMT

Most organizations today are still playing with AI. They experiment with prompts, test ideas in isolated chats, and occasionally automate a task or two. It creates value, but it’s inconsistent, difficult to scale, and almost impossible to govern in a meaningful way.

What the Optimizely Opal University Cohort makes clear is that we’re moving beyond that phase. This is no longer about using AI—it’s about operationalizing it.

Over the course of the workshop, the experience wasn’t just about building agents. It was about understanding what it actually takes to make AI reliable, reusable, and embedded into the day-to-day workflows of marketing and digital teams. And that distinction matters, because the organizations that figure this out won’t just be more efficient—they’ll fundamentally change how work gets done.

The Real Shift: From Conversations to Systems

One of the most important ideas reinforced early in the cohort seems simple on the surface, but it has far-reaching implications once you start applying it in practice:

Chats are disposable. Agents are systems.

That shift alone reframes how you think about AI. In most teams today, someone writes a prompt, tweaks it until the output looks acceptable, uses it once, and then repeats the process the next time they need something similar. It works, but it doesn’t scale, and more importantly, it doesn’t create institutional knowledge.

With Opal, you’re encouraged to step back and ask a different question: instead of solving the problem once, how do you design something that solves it consistently?

The workshop used a restaurant analogy to explain this, which actually holds up surprisingly well when you think about it more deeply. The prompt becomes your recipe, the instructions are your ingredients, the tools are your kitchen equipment, and evaluations act as your quality control. What you’re ultimately producing is not just an answer, but a repeatable outcome that can be delivered again and again with a predictable level of quality .

What’s often missed in the broader AI conversation is that this isn’t really about prompting anymore. It’s about system design, and that’s where Opal starts to feel meaningfully different.

The Agent Creation Experience: Fast, Structured, and Intentionally Imperfect

One of the more impressive aspects of the workshop is how quickly you can go from idea to working agent. The two-tab workflow—building in Opal University and then deploying in the Opal platform—removes a lot of the friction that typically comes with setting these things up.

In practice, this approach can save hours of manual effort, especially when compared to building something similar from scratch . But what stood out wasn’t just the speed—it was the expectation that speed alone isn’t the goal.

There’s a consistent message throughout the sessions: getting an agent to work is relatively easy; getting it to work well takes iteration.

That gap between 80% and 95% quality becomes very real once you start testing outputs. It’s where you begin to notice inconsistencies, edge cases, and subtle misalignments with your expectations. And it’s also where most of the real work happens.

The workflow itself reinforces good habits. You generate a structured prompt using a dedicated builder, validate the output before committing, export it as JSON, and then bring it into the Opal platform for testing and refinement . It’s not just efficient—it introduces a level of discipline that most teams don’t naturally apply when working with AI.

What Actually Makes Agents Work in Practice

As the sessions progressed, a pattern started to emerge. It wasn’t any single feature that made agents effective—it was how a few key components worked together.

Instructions: Where Consistency Lives

If prompts define what an agent does, instructions define how it behaves over time.

Opal allows you to establish both instance-wide instructions—things like brand voice or company guidelines—and more personal layers that reflect individual preferences. You can even generate these from an existing website, effectively turning your digital presence into a baseline for how your agents communicate .

This is one of those features that sounds operational, but it has strategic implications. It means you’re no longer relying on individuals to remember how to phrase things or maintain consistency across outputs. Instead, that consistency is embedded into the system.

That said, there’s an important caveat. When instructions conflict, outputs can become unpredictable. It’s a reminder that governance isn’t optional—it’s foundational.

Evaluations: Defining What “Good” Looks Like

If there’s one capability that feels underappreciated in most AI discussions, it’s evaluation. Not in the abstract sense, but as a structured, repeatable way to define quality.

Opal’s approach to evals is both simple and powerful. You link examples of what good output looks like, and the agent uses those examples both to score itself and to guide future responses. Over time, this creates a feedback loop that improves consistency and reliability .

What’s particularly useful is how this forces teams to be explicit. You can’t just say “this looks good”—you have to define it. And once you do, you can measure against it.

In practice, this also introduces nuance. Structured outputs might require higher thresholds—90% or more—while creative work needs more flexibility. That balance is something teams will need to learn, but having the mechanism in place is a significant step forward.

Workflow Agents: Where AI Becomes Operational

This is where things start to feel less like a feature set and more like a platform.

Workflow agents allow you to connect multiple agents together, passing outputs from one to the next and triggering them based on real-world events. You can initiate workflows through chat, webhooks, email, or scheduled runs, which opens up a wide range of possibilities .

What makes this particularly compelling is how it mirrors actual business processes. Instead of thinking about isolated tasks, you start thinking about sequences—how information flows, how decisions are made, and where automation can meaningfully reduce effort.

The newsletter-to-LinkedIn example from the workshop illustrates this well. An incoming email triggers a workflow, which transforms the content, applies formatting improvements, and prepares it for distribution. It’s a relatively simple use case, but it captures the essence of what’s possible when you move beyond single-agent interactions .

Reusability Through Variables

Another detail that becomes increasingly important at scale is the use of variables.

By parameterizing inputs—things like URLs, languages, or datasets—you can reuse the same agent across different contexts without rebuilding it from scratch. This might seem like a small feature, but it’s what turns agents into reusable assets rather than one-off solutions.

The Use Cases That Actually Matter

What made the workshop particularly valuable was seeing how these capabilities translate into real work.

Some use cases were more obvious, like competitive analysis or lead generation, but others highlighted where agents can quietly drive significant value.

For example, transforming meeting notes into structured user stories is not glamorous, but it’s incredibly useful. It reduces manual effort, ensures consistency, and accelerates downstream work. Similarly, automating reporting workflows or translating strategic goals into measurable KPIs addresses very real operational bottlenecks.

More forward-looking use cases, like AEO and GEO optimization, point to where the industry is heading. As AI-driven search becomes more prevalent, understanding how brands appear in those environments—and how to improve that presence—will become a critical capability. Agents are particularly well-suited to this kind of analysis because they can combine research, evaluation, and recommendation into a single workflow.

What’s Actually Impressive (And What’s Not)

It’s easy to get caught up in features, but what stood out here was less about what Opal can do and more about how it encourages teams to think.

There’s a clear emphasis on iteration over perfection, which aligns with how real teams operate. There’s also a deliberate separation between different components—creation, instructions, evaluations—which reduces complexity as usage grows.

At the same time, it’s important to recognize that this isn’t a fully abstracted experience. You still need to think about how agents interact, how outputs are structured, and how workflows are designed. In other words, the platform gives you the building blocks, but it doesn’t remove the need for strategy.

Implementation Realities: Where Things Get Hard

If there’s one consistent theme that emerged, it’s that technology is only part of the equation.

From a people perspective, someone needs to take ownership of agent design and governance. Without that, it’s easy for things to become fragmented or inconsistent.

Process-wise, teams need to define when to use agents versus chats, how to evaluate outputs, and how to maintain and improve what they’ve built. These aren’t decisions that can be deferred—they shape how effective the system becomes over time.

On the technical side, integration and orchestration introduce their own challenges. Even something as straightforward as email triggers can have limitations that require workarounds, as seen during the workshop .

And then there’s governance. If agents are going to play a meaningful role in operations, there needs to be visibility into how they’re performing, control over what data they access, and clear accountability for their outputs.

The Bigger Picture: Why This Matters Now

What the Opal University Cohort ultimately highlights is not just a set of capabilities, but a shift in how AI fits into the MarTech ecosystem.

We’re moving from a world where AI is something you occasionally use, to one where it becomes part of how work gets done. That shift requires new ways of thinking about design, quality, and governance.

The organizations that adapt will find themselves operating differently. They’ll move faster, not just because they’re more efficient, but because they’ve reduced the friction between idea and execution. They’ll also be more consistent, because their processes are embedded into the systems they use.

And perhaps most importantly, they’ll be better positioned to adapt as the technology continues to evolve.

Final Thoughts

The experience of going through the Opal University Cohort makes one thing clear: the future of AI in marketing and digital experience is not about better prompts. It’s about better systems.

Opal is not trying to replace how teams work—it’s trying to reshape it in a way that makes AI usable at scale. That’s a much harder problem to solve, but it’s also the one that matters.

For teams willing to invest the time to understand and apply these concepts, the payoff is not just incremental improvement. It’s a fundamentally different way of operating—one where AI is no longer an experiment, but an integral part of the organization’s capability.

Take this opportunity and join the waitlist to be a part of a Cohort: https://www.optimizely.com/ai-marketing-certificate/

Optimizely CMS 13: A Strategic Reset for Content, AI, and Composable Marketing

Tue, 14 Apr 2026 19:50:12 GMT

Optimizely CMS 13 is not just another version upgrade—it represents a deliberate shift toward a connected, AI-enabled, and API-driven content platform.

Released March 31, 2026, CMS 13 introduces:

A Graph-first architecture for content delivery
Embedded AI workflows via Opal
A Visual Builder for marketer-led content creation
A standardized approach to integrating external systems

This isn’t about improving the CMS editor, it is about redefining how content operates across your entire digital ecosystem.

Market Context: The CMS Is No Longer the Center

Most enterprise CMS platforms were built for:

Page-based publishing
Centralized content storage
Custom integrations for everything else

That model is increasingly misaligned with reality.

Today:

Content lives across CMPs, DAMs, commerce platforms, and PIMs
Experiences span websites, apps, marketplaces, and AI interfaces
Marketing teams need speed without engineering dependency
AI requires structured, accessible content across systems

The implication is clear:

The CMS is no longer the system of record—it’s the orchestrator of distributed content.

CMS 13 is Optimizely’s answer to that shift.

What Is Optimizely Graph?

Optimizely Graph is the central layer that connects, indexes, and delivers content across your ecosystem.

Think of it as a unified content engine that sits between your systems (CMS, DAM, commerce, etc.) and your channels (web, apps, AI).

Why this matters?

1. Content is no longer siloed
Graph enables content from multiple systems to be accessed and used together in a single experience.

2. It replaces legacy search and delivery models
CMS 13 deprecates Search & Navigation and positions Graph as the primary content delivery mechanism.

3. It powers AI across the platform
Opal’s AI capabilities—including content creation and optimization—depend on Graph indexing and understanding your content.

4. It improves performance and scalability
Graph acts as a high-performance delivery layer, enabling faster and more consistent content retrieval.

The Strategic Shift

Before: CMS → APIs → Channels

Now: Graph → unified content → channels + AI + integrations

This is not a technical distinction—it’s a platform-level change in how content is accessed and activated.

The Three Strategic Shifts in CMS 13

Optimizely frames CMS 13 around three outcomes:

Faster content creation
Better delivery capabilities
AI-powered workflows

Let’s break it down to what that means.

1. Visual Builder: Marketing Speed Without Developer Dependency

CMS 13 introduces a Visual Builder that enables marketers to create experiences directly.

Grid-based layout system (rows, columns, sections)
Real-time preview across breakpoints
Reusable templates (“blueprints”)
Governance through predefined styling controls

From a business perspective:

Campaigns launch faster
Less reliance on development teams
Brand consistency is maintained through guardrails

Existing CMS 12 content still works, teams can adopt this incrementally. (With some required updates and changes, e.g. Framework updated to .NET10.0, check DB compatibility, Optimizely Graph is needed to use CMS 13, among others)

2. Graph-First Delivery: The Foundation for Everything Else

Graph is no longer optional, it’s the backbone of CMS 13.

Powers search, APIs, and content delivery
Enables semantic search and AI use cases
Replaces legacy search infrastructure
Standardizes how content is accessed across channels

This aligns CMS 13 with modern architectures where:

Content is API-driven
Frontends are decoupled
Experiences are assembled dynamically

3. External Content: Composable CMS in Practice

CMS 13 introduces a new external content model, enabling content from other systems to be used directly.

Integrations with commerce, PIM, DAM, and more
Content remains in the source system (no duplication)
Real-time updates reflected in experiences
Standardized integration via Optimizely Connect Platform

This eliminates a long-standing problem: Custom integrations that become outdated and expensive to maintain.

4. Embedded DAM: From Asset Storage to Asset Strategy

CMS 13 includes an enterprise-grade DAM directly in the CMS experience.

Centralized asset management
Metadata, tagging, and renditions
Unified asset access across workflows

This reduces operational friction: fewer tools, fewer handoffs, and better governance.

5. Opal AI: Embedded, Not Bolted On

CMS 13 integrates Opal AI directly into editorial workflows. Opal enables:

Content creation and publishing directly within CMS
SEO & AEO optimization and automated recommendations
Content management operations (create, update, manage variations)

Additional capabilities include metadata and schema generation, content audits and refresh recommendations, and AI-assisted content modeling and page creation.

The key shift:

AI is no longer a side tool
It becomes part of how content gets created and optimized daily

How It All Fits Together?

CMS 13 operates across three coordinated layers:

1. Creation Layer

Visual Builder
CMP integration
Embedded DAM

2. Content Layer

Graph as the unified index
External content integration
Structured content models

3. Intelligence Layer

Opal AI agents
Semantic search and analytics
AI-driven optimization workflows

The implication is that content becomes structured, connected, and AI-readable by design.

What This Means for Different Stakeholders?

Marketing Leaders

Faster campaign execution
AI-assisted content production
Consistent brand governance

Digital Experience Managers

Unified content access across systems
Improved discoverability and reuse
Reduced operational complexity

Engineering Leaders

Less custom integration work
Standardized APIs via Graph
More focus on architecture, less on maintenance

Implementation Considerations

1. This Is a Replatforming Decision

While CMS 12 → 13 is described as an evolution, the reality is:

Graph adoption is required
Search must be migrated
Architecture changes impact delivery models

2. Content Modeling Must Evolve

To unlock value:

Move from page-centric to component-based design
Structure content for reuse and AI consumption

3. Cloud Becomes the Default

Graph is a SaaS service
Opal and DAM depend on cloud capabilities
Opti ID is required for key features

4. AI Governance Is Critical

Organizations must define:

Approval workflows for AI-generated content
Brand and compliance guardrails
Data access policies for AI agents

Risks and Trade-offs

Transition Complexity: New architecture, new workflows, new mindset.

Dependency on Graph: Graph is foundational, there is no fallback to legacy models.

Organizational Readiness: Success depends on people and process, not just technology.

Cloud Constraints: On-premise environments face limitations for full feature adoption.

Key Decisions

CMS 13 reflects a broader industry shift:

From CMS as a publishing tool → to CMS as a content orchestration platform

The real question for decision-makers is not: “Should we upgrade?”

It’s: “Are we ready to operate in a connected, AI-driven content ecosystem?”

Final Takeaway

CMS 13 is not incremental, it’s directional.

It aligns with where MarTech is going:

API-first architectures
AI embedded in workflows
Composable ecosystems over monolithic platforms

The organizations that win won’t just adopt CMS 13.

They’ll use it to rethink how content flows across their entire business.

References:

My Takeaway from Optimizely Opal Agents in Action 2026 - What Agentic AI Means for the Future of Digital Marketing

Fri, 06 Mar 2026 15:48:32 GMT

I would like to share with you what stayed in my head after this amazing virtual event organized by Optimizely. Agents in Action 2026, a live demonstration of Optimizely's AI assistant platform, Opal. The session showcased how AI agents embedded across the Optimizely ecosystem can conduct research, analyze documents, orchestrate tools, and automate operational workflows for marketing teams.

Artificial intelligence in marketing is entering a new phase. For the past two years, the focus has largely been on generative AI—tools that produce copy, images, summaries, and marketing ideas. But as organizations begin integrating these technologies into their workflows, a more powerful model is emerging: agentic AI. Agentic systems go beyond answering questions. They can plan tasks, call tools, retrieve data, analyze information, and execute multi-step workflows.

Optimizely's demonstration highlighted a shift that is beginning to reshape digital marketing operations: the move from isolated AI features to AI agents that perform work inside enterprise platforms.

Industry research suggests the timing is not accidental. Organizations are rapidly experimenting with AI but still struggle to integrate it deeply into operational workflows. According to McKinsey’s latest global survey on AI adoption, many companies have begun using AI widely but have not yet embedded it deeply enough into processes to generate full enterprise value (McKinsey).

What Optimizely showed with Opal agents points toward the next stage of AI maturity—where marketing teams work alongside AI agents that automate research, analysis, and operational tasks.

The Rise of Agentic AI in Marketing

Most early generative AI tools behaved like conversational assistants. You ask a question, yhe system produces an answer.

That model has proven useful for content generation, brainstorming, and summarization, but enterprise environments require more than output generation. They require systems that can execute processes.

Agentic AI systems are designed for that purpose. Instead of generating a single response, they can:

Execute multi-step research
Retrieve external information
Call APIs or tools
Analyze documents
Trigger workflows
Coordinate multiple systems

This shift reflects a broader trend in enterprise AI adoption.

McKinsey research shows that AI is increasingly used across multiple business functions—including marketing and sales—where generative AI can support activities such as knowledge synthesis, content generation, and strategic analysis (McKinsey ). But many organizations still struggle to scale these capabilities across their workflows.

The opportunity lies not in adding more AI tools, but in redesigning operational processes so AI becomes embedded within them. This is where agentic platforms begin to matter, instead of interacting with AI occasionally, teams interact with systems that continuously assist, automate, and coordinate operational tasks.

The Optimizely Opal demonstration illustrated how such systems might work in a marketing technology environment.

What Optimizely Demonstrated at Opal Agents in Action 2026

The event focused on Opal, Optimizely’s AI assistant platform integrated across its product suite, including CMS, experimentation tools, analytics capabilities, and content marketing workflows.

At its core, Opal operates as a conversational AI interface embedded directly inside the Optimizely ecosystem. Users interact with the system through a chat interface that maintains persistent conversation history and contextual awareness.

Before each interaction with the underlying language model, the platform executes a multi-step enrichment process.

This pipeline loads contextual information such as:

organizational instructions and brand guidelines
available agents and tools
operational prompts or system rules

Organizations can configure these instructions at multiple levels.

Instance-level instructions apply across the entire organization—for example, defining brand voice or communication guidelines. Personal instructions allow individual users to tailor how the system responds to their requests.

Role-based permissions control who can modify these instructions, which helps maintain governance in enterprise environments.

The demonstration showed how this contextual layer ensures AI interactions remain aligned with organizational policies and brand requirements.

Key Capabilities of Opal Agents

The most interesting aspect of the event was not the conversational interface. It was the demonstration of specialized AI agents capable of executing complex operations.

Specialized agents

Agents in Opal are created with defined roles, instructions, and tool access. When an agent runs, it operates in an isolated context. This prevents large multi-step processes from overwhelming the main conversation.

During the demonstration, a research agent was configured to analyze companies. The agent accepted a topic parameter and automatically executed multiple research passes.

In another example, the agent performed several research queries about Toyota, gathering information about company background, news, and financial performance. The system automatically executed a chain of operations:

search → scrape → analyze → summarize
The process generated a detailed report after approximately 234 seconds and involved roughly 44,000 tokens across multiple tool calls.
Execution logs displayed the reasoning cycle in real time, including predicted tool calls and returned outputs.

The demonstration highlighted how AI agents can handle research tasks that typically require multiple manual steps.

Tools and extensibility

A second important capability is Opal’s tool framework. Developers can create custom tools using the Opal Tools SDK, which supports Python and FastAPI. Functions can be exposed as tools through simple annotations, allowing the AI system to invoke them during task execution. The demonstration included a simple tool that generated random numbers based on user parameters. While trivial in itself, the example illustrated how tools return structured responses that can render as interactive user interface elements. More advanced tools are provided directly by Optimizely product teams.

Examples demonstrated during the session included:

Web search integration that performs Google searches and scrapes relevant websites
PowerPoint processing that converts slides into analyzable formats
Product-specific tools for CMS and experimentation features

The system determines when to call these tools based on their descriptions and parameter schemas. The result is an AI system capable of chaining together multiple operations without manual intervention.

Enterprise document analysis

In the event it was also demonstrated document processing capabilities.

PowerPoint files can be uploaded and converted into a structured Canvas format, allowing the system to analyze slides individually.
A code execution tool—similar to those used in other advanced AI systems—will enable analysis of spreadsheets and other Office documents through generated Python scripts.

This allows agents to read, manipulate, and extract information from enterprise files, so organizations can also attach reference documents or knowledge sources to agents. These materials become searchable through retrieval-augmented generation workflows using Optimizely’s content graph.

Workflow automation

For me the most operationally significant feature demonstrated during the event was multi-agent workflow orchestration. Agents can be chained together sequentially, passing outputs and parameters between steps.

Workflows can be triggered in several ways:

Direct chat input
Email-based triggers
Webhook integrations
Scheduled automation

One demonstration showed a research agent analyzing a topic and passing its results to an email agent. The second agent transformed the research findings into a formatted HTML email and automatically delivered it to recipients. Other enterprise use cases discussed during the event included automated market research, competitive intelligence monitoring, and recurring insight reports.

Why Agentic Marketing Matters for Digital Teams

For marketing teams, the operational implications of agentic AI could be substantial. Modern digital marketing involves a constant flow of analysis, reporting, and information gathering. Many tasks follow similar patterns:

Collect information → Analyze it → Generate output → Share results

AI agents can automate much of this process instead of manually conducting research or assembling reports, teams can initiate workflows where agents gather information, analyze it, and deliver structured insights. This does not remove human involvement, instead, it shifts where humans spend their time.

MIT Sloan research suggests that AI is most effective when it complements human work rather than replacing it, enabling people to focus on higher-value tasks such as interpretation and decision-making (MIT Sloan Management Review ). For marketing organizations, that means less time spent on operational preparation and more time spent on strategy.

Industry Validation

Several industry studies reinforce the potential impact of AI in marketing operations.

McKinsey estimates that generative AI could generate significant economic value across industries, with marketing and sales among the functions that stand to benefit the most from productivity improvements (McKinsey). The firm’s research suggests that generative AI could increase marketing productivity up to 15 percent of total marketing spend through improvements in content creation, personalization, and knowledge synthesis.

At the same time, organizations are still learning how to operationalize AI effectively. McKinsey’s latest global AI survey notes that many companies have adopted AI tools but have not yet embedded them deeply into their workflows or processes (McKinsey). This gap between experimentation and operational integration is precisely where agentic platforms may deliver value.

By embedding AI into enterprise systems and allowing agents to execute tasks, organizations can move from isolated experiments to operational transformation.

Strategic Implications for CMOs and Digital Leaders

For marketing leaders evaluating AI platforms, several strategic considerations emerge from the Opal demonstration.

First, governance becomes critical. AI systems embedded in operational workflows must operate within brand, legal, and compliance boundaries. Opal’s instruction framework illustrates how organizations can define these constraints.

Second, the ecosystem around AI matters as much as the AI itself. Platforms that support tool integration, APIs, and workflow orchestration will likely deliver more long-term value than standalone assistants.

Third, marketing operating models may evolve. As agent-driven workflows mature, teams may increasingly focus on oversight, strategy, and decision-making rather than manual research or analysis.

Finally, human supervision remains essential. The demonstration itself acknowledged that large language models can occasionally drift off topic during complex research tasks, requiring prompt refinement and oversight. Agentic systems should therefore be viewed as collaborators, not replacements.

My Final Takeaways

The Optimizely Opal Agents in Action event offered an early look at how AI agents might reshape marketing operations. Rather than presenting AI simply as a content generator, the demonstrations positioned Opal as a system capable of executing research, analyzing documents, orchestrating tools, and automating workflows across marketing platforms. This approach reflects a broader industry shift. As organizations move beyond isolated AI experiments, the focus is shifting toward operational integration—embedding AI into everyday workflows. For digital marketing teams, this may represent the next stage of platform evolution, not just tools, not just assistants, but ecosystems of AI agents working alongside human teams to execute the operational layer of marketing.