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

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.