Optimizely Opal overview

  • Updated

Optimizely Opal is an agent orchestration platform that helps you work smarter across Optimizely One. Whether you create content, manage experiments, or analyze data, you can use Opal to automate tasks, surface insights, and guide decision-making. Opal uses a flexible system of AI agents. Agents are software components that understand your intent and help you reach your goal.

See Optimizely Opal Essentials in Optimizely Academy for information.

AI background

AI refers to software that performs tasks typically requiring human reasoning, such as learning from data, making decisions, or solving problems. These systems identify patterns, generate content, and offer insights. They use large language models (LLMs) and other algorithms trained on vast datasets.

Advances in computing power, data availability, and model design have changed how people use AI across industries. Optimizely embeds AI into the platform to help you move faster, automate repetitive work, and make more informed decisions.

AI agents

AI agents are software systems that act on your behalf. Agents analyze information, interact with the platform or other tools, and adapt their behavior based on feedback. Unlike traditional tools that only respond to direct input, agents manage goals and take steps to accomplish them.

Optimizely classifies AI agents into the following three broad types:

  • Simple assistants – Help with straightforward tasks such as generating content, formatting it into a structure, or offering ideas based on a prompt.
  • Specialized agents – Focus on a domain or tool. These agents use expert-level context to analyze data, predict outcomes, or recommend next steps.
  • Workflow and autonomous agents – Coordinate and perform multi-step processes, often by integrating with other tools. These agents handle tasks across systems and adapt workflows over time.

These agents improve productivity by reducing manual work, increasing accuracy, and providing tailored experiences. They also support scalability, helping teams achieve more without growing headcount.

Optimizely Opal

Optimizely Opal is your AI assistant across Optimizely One. It responds to natural language questions, generates insights, and lets you complete tasks faster.

Optimizely Opal uses Opal credits.

What you can do with Opal

Most interactions happen through Opal Chat, which is available across the Optimizely One platform in the global navigation bar and on opal.optimizely.com.

Screenshot of Optimizely Web with Ask Opal highlighted in the global navigation bar
Ask Opal highlighted in the global navigation bar of Web Experimentation

Whether you are launching a campaign or fine-tuning an experiment, Opal adapts to your role and needs. Use natural language to ask questions, generate content, or request help. Opal responds in real-time and remembers threads so you can pick up where you left off.

Screenshot of Opal Chat with a request from the user and a response from Opal.

The following are some examples of what Optimizely Opal can help with:

  • Use tools – Ask Opal to complete tasks using tools, such as creating a campaign, drafting content, analyzing images, or suggesting flag variations. See Tools overview.
  • Analyze files – Upload a document, image, or spreadsheet and ask questions about it. See Optimizely Opal Chat.
  • Answer questions – Ask Opal about Optimizely features, capabilities, or concepts. Opal explains terms, walks you through configuration steps, and points you to relevant documentation.

See Products with Opal features for a list of Opal features.

How Opal works

Behind the scenes, Opal follows this sequence each time you send a prompt:

  1. Your prompt – You enter a request in natural language. Your prompt can be a simple question, a complex task, or a creative brief. Opal analyzes your intent, extracting key information to guide its next steps.
  2. Skills – These foundational guidelines define Opal's persona, approach, tool usage, evaluation criteria, and response formatting, influencing every step of its operation.
  3. Contextual intelligence – Opal adds context using content knowledge, Optimizely platform data, and your workspace context. This ensures Opal's responses are informed by your specific environment and goals.
  4. Strategic tool selection – Opal selects the right tools for your task based on your request and the enriched context. Tools let Opal perform a wide range of tasks from data analysis to content generation.
  5. Agent input generation and validation – Opal collects the specific inputs (parameters) it needs to run a tool or agent. For example, a search_query for a web search, a start_date and end_date for a report, or recipient_email_addresses for an email.

    Opal validates these inputs before continuing:
    • If the input is valid – Opal proceeds to the LLM interaction.
    • If the input is invalid – Opal goes directly to step 7 (Execute and refine) and asks you for clarification. This prevents unnecessary LLM engagement.
  6. LLM interaction – Opal uses advanced AI models to process complex information, generate creative content, and derive actionable insights. This is where raw data transforms into intelligent solutions. Opal uses foundational LLMs through business accounts. Your data is never used to train the model or shared across customers.
  7. Execute and refine – Opal executes the planned actions (calling agents and tools as needed), and iterates. If the initial output is not perfect, Opal re-evaluates. This continuous feedback loop ensures optimal results and measurable impact. If clarification is needed, Opal asks you for more information.
  8. Tailored response – Opal delivers a clear, concise, and actionable response. Opal often presents the response in the Opal Canvas or UI, where you can interact with and manage generated content or executed actions.
diagram of Opal's eight-step prompt-to-response process

Benefits of Opal and AI agents

Opal helps you with the following:

  • Work faster – Eliminate repetitive tasks and reduce manual configuration.
  • Scale content and insights – Get more done with fewer handoffs.
  • Improve personalization – Tailor output based on your brand, audience, and goals.
  • Make informed decisions – Use data-backed recommendations without digging through dashboards.
  • Simplify complexity – Let Opal manage workflows so you can focus on strategy.

See Optimizely Opal and AI features for a list of all available Opal, generative AI, and machine learning features.

Data residency

Optimizely hosts Opal in US and EU regions. You select your region on your order form when you contract with Optimizely, and Optimizely provisions your data to the corresponding regional instance.

The app URL is the same for all customers (opal.optimizely.com). Optimizely routes you to the correct regional instance behind the scenes, so you do not need to configure anything.

Next steps

If you use Opti ID, administrators can turn off generative AI in the Opti ID Admin Center. See Turn generative AI off across Optimizely applications.