--- title: Get started with Optimizely Mark for administrators slug: agent-platform/docs/get-started-with-agent-platform-for-administrators docTags: createdAt: 2026-08-12T15:37:06.000Z --- Agent Platform is an agent orchestration platform that helps you work smarter across Optimizely One. Mark is automatically available and works by default, but you can configure it based on your organization's needs. You must add users to Mark before they can use it. ## Add users and set permissions Add and manage users and their permissions for Mark in the Opti ID Admin Center. See [manage users](docId\:afJzJCmm5TkQ4CDpUlXQh) for instructions. Give users one of the following roles: - **Mark Administrator** – Ability to manage and configure users, skills, tools, agents, and connected product instances in the Mark app. Can also access [Mark chat](../../use-opal/opal-chat/access-and-explore-opal-chat.mdx) within the Mark app and any connected Optimizely products. See [Get started with Mark for administrators](../../get-started/get-started-with-optimizely-opal-for-administrators.mdx). - **Agent Builder** – Ability to create skills, build agents, and access the Agent Directory. Can also access [Mark chat](../../use-opal/opal-chat/access-and-explore-opal-chat.mdx) within the Mark app and any connected Optimizely products. See [Get started with Mark for agent builders](../../get-started/get-started-with-optimizely-opal-for-agent-builders.mdx). - **Mark Brand Manager** – Ability to create and manage Brand Packs. - **Virtual Teammate Manager** – Ability to manage enabled Virtual Teammates. - **Mark User** – Ability to use Mark from individual Optimizely products, with access to [Mark chat](../../use-opal/opal-chat/access-and-explore-opal-chat.mdx) within the Mark app and any connected Optimizely products. See [Get started with Mark for users](../../get-started/get-started-with-optimizely-opal-for-users.mdx). If the available system roles do not provide the specific access you want to grant users, you can create a [custom role](docId\:pe0pbUJveWrG8ewvZWDRE) in the Opti ID Admin Center. See [Custom roles for Mark](docId\:pe0pbUJveWrG8ewvZWDRE) for what roles are available. ## Access the Mark app The Mark app is Mark's configuration dashboard, accessible through the product switcher in the global navigation. 1. Log in to [Optimizely](https://home.optimizely.com). 2. Select your organization. 3. Click **Mark**. ::Image[]{src="https://api.archbee.com/api/optimize/BrbvVORKJ5iIeSMZye5kI/CaFcFgRnVHnymozOdoTUN_access-opal-app.png" size="100" alt="Optimizely home with Opal highlighted." isUploading="false" width="2190" height="1378" darkWidth="2190" darkHeight="1378" showCaption="false" indent="1"} ## Customize Mark Customize Mark to tailor its behavior, responses, and integrations to your organization's goals. Configure skills, agents, and tools to shape how Mark works with your team. This gives you a personalized experience tailored to your needs. Customizations ensure that Mark understands your brand voice, can access the right data, and performs actions that align with your workflows. ### Ways to customize Mark Mark supports several customization options, depending on the level of control you need. - **Connections** – Link Mark to your Optimizely product instances so it can take action using real data and features. See the [Product connections](docId\:pe0pbUJveWrG8ewvZWDRE) section. - **Skills** – Provide context that tells Mark how to behave and when to run. Skills guide how Mark interprets requests and ensures consistent results. See [Skills overview](docId:1HTjxW2J-ZOkYEZMwnasU). - **Agents** – Build and add agents tailored to your organization’s unique processes. You control which tools they use, how they respond, and what workflows they execute. See the [Agent directory overview](docId\:Xlo4rbSLRP_fxF5NlMLgG), [Specialized agents overview](docId\:WyA1gsk6tWr84Hum7a1Nx), and [Workflow agents overview](docId:2HD0fUsIsfdek516VtN9l). - **Custom tools** – Extend Mark’s capabilities by connecting it to your internal systems or third-party services through tools your organization creates. See [Tools overview](docId:-j4zNs-l3kIKD0n58bVPt). ### Why customize Mark Customizing Mark is optional but provides more control and makes the platform more effective. The following are ways that customizing Mark empowers you: - Ensures Mark understands your organization’s terminology, tone, and priorities. - Automates common tasks with consistent, repeatable outcomes. - Connects to the exact systems and products your team uses. - Scales workflows without adding manual steps or complexity. ## Mark app UI The Mark app provides a centralized interface where you can access Mark's capabilities in one place. The Mark app UI supports everything you need to configure, customize, and use Mark effectively. Each page helps you focus on outcomes while Mark handles the technical details behind the scenes. ### Mark chat ![Screenshot of Mark where the chat view displays with the left menu and Agent Library at the bottom](https://api.archbee.com/api/optimize/BrbvVORKJ5iIeSMZye5kI/3GzZfhmgdgvhHu1EUKMwc_get-started-with-agent-platform-for-agent-builders-chat0.png) **Chat** is the conversational interface for Mark. It lets you interact with Mark using natural language to complete tasks, get insights, and automate workflows without needing to know the underlying systems or commands. Ask Mark questions, make requests, or give instructions. Mark determines the right tools and agents to use to deliver accurate, actionable results. Whether you need to generate content, analyze data, or manage experiments, Mark chat provides a simple, intuitive way to work directly within Mark. See [Access and explore Mark chat](../../use-opal/opal-chat/access-and-explore-opal-chat.mdx) for information. ### Skills ![Screenshot of Context where the Skills tab displays](https://api.archbee.com/api/optimize/BrbvVORKJ5iIeSMZye5kI/Zd4aT5Nl9Wd9sCaCiVSTc_mark-chat-reusables-context-skills0.png) ![Screenshot of Context where the Skills tab displays](https://api.archbee.com/api/optimize/BrbvVORKJ5iIeSMZye5kI/0yS7gURnwZq7Ri5Kk9VQw_optimizely-agent-platform-for-admins-context-skills-configuration0.png) **Skills** are the foundational context, rules, and behavioral guidelines that shape how Mark creates output and tailors it to your organization's unique needs. See the [skills overview](../../skills/instructions-overview.mdx) for information. ### Agents ![Screenshot of the Mark left menu where the Agents option displays](https://api.archbee.com/api/optimize/BrbvVORKJ5iIeSMZye5kI/7azFoOMOw_lQKQY4w9G5y_mark-chat-reusables-agents0.png) ![Screenshot of the left menu where Agents displays under Configurations](https://api.archbee.com/api/optimize/BrbvVORKJ5iIeSMZye5kI/DuSwCtHSRDynW9sicmaa5_optimizely-agent-platform-for-admins-agents-configuration0.png) **Agents** complete tasks for you in Mark. They interpret your requests, decide which tools to use, and deliver consistent results. The **Agents** page of the Mark App is where you can browse and install agents from the [Agent Directory](../../directory/agent-directory/agent-directory-overview.mdx) or create and manage [specialized](../../agents/specialized-agents/specialized-agents-overview.mdx) and [workflow](../../agents/workflow-agents/workflow-agents-overview.mdx) agents tailored to your organization’s needs. By configuring the right agents, you can streamline workflows and automate common tasks across your connected Optimizely products and external services. See [Agent overview](../../agents/agent-overview.mdx) for information. ### Tools ![Screenshot of Connectors where the Tools tab displays](https://api.archbee.com/api/optimize/BrbvVORKJ5iIeSMZye5kI/IlqJna4olP_jCGMGcNdK5_mark-chat-reusables-connectors-tools0.png) ![Screenshot of Connectors where the Tools tab displays](https://api.archbee.com/api/optimize/BrbvVORKJ5iIeSMZye5kI/D4zcwoIEiTeE8qneY_TKL_optimizely-agent-platform-for-admins-agents-connectors-tools0.png) **Tools** are the actions Mark uses to get work done. Each tool performs a specific task, such as creating a campaign, generating content, or uploading files. View the tools available to your organization, including [system tools](../../tools/system-tools/system-tools-overview.mdx) built by Optimizely and [custom tools](../../tools/custom-tools/custom-tools-overview.mdx) created by your team. Connect and configure the right tools to let Mark act on your behalf and integrate with your systems and workflows. See [Tools overview](../../tools/tools-overview.mdx) for information. ## How tools, skills, and agents work together In Mark, tools, skills, and agents work together to complete tasks. - Skills define how Mark shapes its output and how Mark uses tools. - Tools provide the capabilities, such as accessing data or performing actions. - Specialized agents combine tools and skills into a packaged, specialized capability that can carry out tasks on its own. - Workflow agents stitch together multiple agents into a complex workflow that a trigger starts. Understanding how these pieces connect helps you design effective workflows and get the most out of Mark. ### Smart home automation analogy Imagine Mark as a sophisticated smart home system that intelligently manages and automates various functions within a house. Each part of Mark can be divided into different parts of this smart home system. **Skills** – The smart home's core programming and user preferences. Skills are the fundamental rules, underlying code, and user-configured preferences that govern the entire smart home system. They dictate how all devices and routines behave, ensuring consistency, security, and personalization across the whole house. - **Smart home example** – The system's default security protocols, the user's preferred temperature settings, or the general rules for when lights should be on or off. - **In Mark** – These are the meta-level guidelines that shape Mark’s overall behavior, tone, and how it process and present information. **Tools** – Device interfaces, communication protocols, and core functions. The tools are the "things" that smart devices and agents use to get things done. These are the capabilities that let devices perform their tasks and interact within the smart home ecosystem, and with external services. - **Smart home example** - Wi-Fi or Bluetooth. - Connecting to a music provider API for music playback. - Connecting to a local weather service for temperature data. - Light emission for a bulb. - Temperature sensing for a thermostat. - Motor activation for blinds. - Brew for a coffee maker. - **In Mark** – These are the basic capabilities or resources that specialized agents use to execute their tasks, often involving connecting to and leveraging external systems. **Specialized agent** – An individual smart device. A specialized agent is like an individual smart device (a smart light bulb, a smart thermostat, a smart coffee maker, or a smart lock). Each device has a specific, well-defined function it performs. It receives a command (input) and performs its action (output). - **Smart home example** – Each item performs a single, focused task. - A smart light bulb turns on or off or changes color - A smart thermostat adjusts the heating or cooling - A smart lock secures a door. - **In Mark** – A specialized agent performs a specific, well-defined task that often involves interacting with external systems or executing complex, encapsulated logic, with a clear input and output schema. **Workflow agents** – A smart home "routine" or "scene". A workflow agent is like a smart home "routine" or "scene". This is a pre-programmed sequence of actions designed to achieve a larger, multi-step goal. It orchestrates multiple individual device actions in a specific order. - **Smart home example** – A "Good Morning" routine with the following steps: - Gradually brightening the bedroom lights. - Opening the smart blinds. - Starting the coffee maker. - Adjusting the thermostat to a comfortable temperature. - **In Mark** – A workflow agent orchestrates specialized agents to achieve a larger, more complex goal, interpreting natural language input to manage a sequence of actions. ## Get started Start customizing Mark by connecting your Optimizely products on the **Product Connections** page. 1. [Access the Mark app.](docId\:pe0pbUJveWrG8ewvZWDRE) 2. Click **Settings > Product Connections**. 3. Expand the Optimizely product. 4. Select the Optimizely instance checkbox. 5. Click **Save**. 6. Repeat steps 3 through 5 for your other Optimizely products. See the [Product connections](docId\:pe0pbUJveWrG8ewvZWDRE) section for more information. ### Next steps When connections are in place, you can complete the following in Mark: - [Access and explore Mark chat](../../use-opal/opal-chat/access-and-explore-opal-chat.mdx). - Add [skills](../../skills/instructions-overview.mdx) to define how Mark should behave. - Review [system tools](../../tools/system-tools/system-tools.mdx) and create [custom tools](../../tools/custom-tools/create-custom-tools.mdx) to integrate Mark with your external systems. - Configure and run [specialized agents](../../agents/specialized-agents/specialized-agents-overview.mdx) to execute tailored, complex tasks. - Configure [workflow agents](../../agents/workflow-agents/workflow-agents-overview.mdx) to stitch together agents into a workflow. ## Mark settings Click **Settings** to configure your organization's Mark instance. ### Appearance Go to **Settings > Appearance** to configure the **Font Size** and **Theme** in Mark. Adjust these settings to improve readability or match your visual preferences. Changes apply to your Mark instance only and do not affect other users in your organization. **Adjust the font size** 1. Click the **Font Size** drop-down list. 2. Select a font size. - **Default** – Standard font size for Mark chat. - **Comfort** – Larger font size and line height for easier reading. ![Screenshot of Appearance where the Font size drop-down list displays](https://api.archbee.com/api/optimize/BrbvVORKJ5iIeSMZye5kI/Vfs8Vqj56Th7_Uli_OJYQ_mark-chat-reusables-appearance-font-size-setting0.png) **Adjust the theme** 1. Click the **Theme** drop-down list. 2. Select a theme. - **Light mode** – Light background with dark text. - **Dark mode** – Dark background with light text. ![Screenshot of Appearance where the Theme drop-down list displays](https://api.archbee.com/api/optimize/BrbvVORKJ5iIeSMZye5kI/ABZLUkeEe17SqIMntx1r6_mark-chat-reusables-appearance-theme-setting0.png) ### Notifications Go to **Settings > Notifications** to configure your preferences. For a description of each setting, see [Notification settings](../../notifications/notification-settings.mdx). ### Chat Go to **Settings > Chat** to configure Mark chat for all users in your Mark instance. ### Default model provider The default model provider determines which AI model family Mark uses to generate responses in Mark chat. This default model provider is also the default for specialized agents, which can override it with their own provider. To change the LLM provider, click the **Default Model Provider** drop-down list. Each provider has different strengths: - **Google Gemini** – Fast, cost-effective responses and creative writing. - **Anthropic Claude** – Complex tool orchestration and code generation. ### Advanced URL safety checks Advanced URL safety checks is a built-in security feature that screens every URL before Mark browses it, protecting your organization from malicious websites, including malware, phishing, and unwanted software. Mark browses webpages on your behalf to summarize articles, extract data, or research topics. Before any content loads, the requested URL passes through a safety check. This check runs automatically on every browse request. Your end users take no action. As a Mark administrator, choose one of two safety levels per instance, depending on the protection your organization requires. URL Safe Browsing operates at two levels: - [Standard](docId\:pe0pbUJveWrG8ewvZWDRE) – Always active and cannot be turned off. - [Advanced](docId\:pe0pbUJveWrG8ewvZWDRE) – Adds a secondary deep scan on top of the Standard check. Opt-in per instance. ### Standard The Standard level checks every URL against [Google Web Risk](https://cloud.google.com/security/products/web-risk), a continuously updated database of known threats. It screens for the following threat categories: - **Malware** – Sites that distribute malicious software. - **Social engineering** – Phishing sites that impersonate legitimate services to steal credentials or personal information. - **Unwanted software** – Sites that distribute software that behaves in deceptive or unexpected ways. Standard checks complete quickly and add minimal latency. Mark enables this level by default for every instance. ### Advanced The Advanced level adds a [Cloudflare Radar deep scan](https://radar.cloudflare.com/scan) in addition to the Google Web Risk check. If either check flags a URL as unsafe, Mark blocks it immediately. The deep scan provides enhanced detection for sophisticated threats that may not yet appear in Google's database. For URLs that Cloudflare has not scanned recently, the deep scan adds up to 30 seconds of latency. ### Safety level comparison | Capability | Standard | Advanced | | ---------------------------------------- | -------- | ----------------------------- | | Google Web Risk check | Yes | Yes | | Cloudflare Radar deep scan | No | Yes | | Malware detection | Yes | Yes | | Social engineering or phishing detection | Yes | Yes | | Unwanted software detection | Yes | Yes | | Enhanced detection for new threats | No | Yes | | Typical added latency | Minimal | Up to 30 seconds for new URLs | | Result caching | Yes | Yes | | Redirect screening | Yes | Yes | | Default setting | Yes | No (opt-in) | ### How it works 1. **URL validation** – Mark validates the requested URL. Only `http` and `https` URLs are accepted. URLs using other protocols (such as `javascript:` or `data:`) are blocked immediately. 2. **Safety check** – Mark sends the URL to the configured provider or providers for evaluation. At the Standard level, this is Google Web Risk. At the Advanced level, Google Web Risk and Cloudflare Radar run concurrently. 3. **Redirect screening** – After the initial page loads, if the page redirects to a different URL, Mark screens the redirect target before returning any content. This prevents circumvention through open redirects. ### What happens when a URL is blocked When a URL is flagged as unsafe, Mark does not load or return any content from the page. Instead, the browse request returns a message that explains the block and names the threat category detected, such as `MALWARE` or `SOCIAL_ENGINEERING`. Blocked URLs do not produce partial results. Mark stops the entire request before any page content is rendered. ### Screen email links Advanced URL safety checks also applies to links found in email bodies processed through Mark's email trigger system. Mark validates links in incoming emails before the email event is processed, providing an additional layer of protection against phishing and malware delivered by email. ### Configure the safety level Configure the safety level for each Mark instance. The setting applies to the entire instance, so all users within the instance share the same safety level. 1. Go to **Settings > Chat**. 2. Locate the **Advanced URL safety checks** toggle. 3. Do one of the following: - Toggle the setting **on** to enable the Advanced level (Google Web Risk + Cloudflare Radar). - Toggle the setting **off** to use the Standard level (Google Web Risk only). ![Screenshot of Chat configuration where the Advanced URL safety checks option is turned off](https://api.archbee.com/api/optimize/BrbvVORKJ5iIeSMZye5kI/SR1m_0PgZoTKK9EyF-Lci_optimizely-agent-platform-for-admins-chat-configuration0.png) ### Inference level The inference level controls which AI model Mark uses and how deeply the model reasons before responding. Higher inference levels pair more powerful models with deeper thinking to produce higher-quality output, but take longer and use more credits. Lower levels respond faster and use fewer credits, making them ideal for straightforward tasks. See [Inference level](../../get-started/inference-level.mdx). To change the inference level used in [Mark chat](docId\:dtNBEttEGVvkhNkwNypLM) for your organization, click the **Inference Level** drop-down list. ![Screenshot of Chat Configuration where the Inference level setting is the third row and offers a drop-down list](https://api.archbee.com/api/optimize/BrbvVORKJ5iIeSMZye5kI/WjtBAf9ZciRcCzYB0zLR6_optimizely-agent-platform-for-admins-chat-configuration-inference-level00.png) ### Email domain Go to **Settings > Email Domain** to set the email subdomain prefix Mark uses when it sends emails. Only one email domain is supported per Mark instance. :::hint{type="danger"} **Warning** When you set the email domain, you cannot change it. ::: To configure the email domain, complete the following: 1. Enter a valid subdomain prefix. Only lowercase letters, numbers, and hyphens are accepted. The subdomain must contain at least two characters and not start or end with a hyphen. 2. Review the email address listed in the **Preview**. The **Preview** displays how emails are sent by this Mark instance. 3. Click **Save Domain**. ### Product connections Go to **Settings > Product Connections** to manage where Mark is activated in your specific Optimizely products and instances. These connections let Mark access the data, tools, and features it needs to take action on your behalf. If a product instance is not connected, it cannot use Mark features. Configure your connections first to ensure you can customize and fully use Mark across your Optimizely organization. To add product connections, complete the following: 1. Click on an Optimizely product to expand it. 2. Select the product instances you want to connect. 3. Click **Save**. ![Screenshot of Product connections where the connection settings display](https://api.archbee.com/api/optimize/BrbvVORKJ5iIeSMZye5kI/vqhmZP7YKYHJoDjBIO_tx_optimizely-agent-platform-for-admins-chat-configuration-product-connections00.png) 4. Repeat steps 1–3 for your other Optimizely products. :::hint{type="info"} **Note** Each Mark instance supports only one email domain. To connect an instance that is disabled, disconnect it from its current Mark instance first. ::: ### Enable RAG in Chat Go to **Settings > RAG Configuration** to control whether Retrieval-augmented generation (RAG) is used in direct messages in [Mark chat](docId\:dtNBEttEGVvkhNkwNypLM). Agents can use RAG regardless of this setting. RAG lets Mark access, understand, and query knowledge sources. With RAG enabled, Mark draws on data such as campaigns, content, and tests to provide more contextual and accurate responses. See [Retrieval-Augmented Generation (RAG) overview](docId:5dyJMwH-dhrFxihyYTNb3) for more information. To change whether RAG can be used in Mark chat, toggle **Enable RAG in Chat** on or off. ![Screenshot of RAG configuration where the Enable RAG chat toggle displays in the top banner](https://api.archbee.com/api/optimize/BrbvVORKJ5iIeSMZye5kI/Bt0Hd_lBf46Rrx-_mI26a_optimizely-agent-platform-for-admins-chat-configuration-rag-configuration-enable-in-chat00.png) ## Allowlist Mark (optional) If your firewall or security settings block Mark from scanning your URLs, add the following IP address to your allowlist: **Mark non-EU instances** - `34.172.226.216` - `34.16.94.149` - `34.45.48.109` - `34.123.77.224` - `35.184.91.0` **Mark EU instances** - `34.38.40.216` - `34.62.179.50` - `34.140.23.27` - `34.79.153.13` :::hint{type="warning"} **Important** If you use the Variation Creation agent, you must add additional IPs to your allowlist. See the [Variation Creation agent](docId\:Uwv1wPE1bWRRNRpu01Fd2) documentation for details. ::: ### Best practices - Confirm with your network or security team before making changes. - Apply these IPs only to environments where Mark needs scanning access. - Review your allowlist periodically to ensure it matches current Mark requirements. ## Turn Mark on or off (optional) Mark is enabled by default. To disable Mark, see [Turn generative AI off across Optimizely applications](docId\:X5U0kKD2azV5cIdNqwGNj). :::hint{type="warning"} **Important** If you toggle **Enable Gen AI** off, you must contact Optimizely Support to re-enable it. ::: ## View Mark usage View Mark usage across your organization in the usage and billing dashboards. See the [Mark credits](docId\:NR4At0IGrDJGq2AUK2j3Y) section in the Usage and billing dashboards documentation. ## View Mark agent usage View Mark agent usage by agent ID (@name) in the Mark agent usage dashboard. See the [Optimizely Reporting for Mark](docId:1PjCoGsKlrWuluwJdrHA_)documentation. :::hint{type="info"} **Note** 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](docId\:X5U0kKD2azV5cIdNqwGNj). :::