> For the complete documentation index, see [llms.txt](https://docs.veedna.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.veedna.com/unifai/missions/running-missions.md). # Running Missions UnifAI Agent — your AI companion runs guided, auto-executable workflows that get your security and compliance work done. When you pick a mission, the agent handles the steps, prompting you take action as needed. ## Starting a Mission To start a mission: 1. In UnifAI, select **Launch Mission Control**. 2. Choose a Mission type that matches your goal. 3. Click **Start** to run the mission. A specialized agent called the Policy Selector Agent automatically loads the relevant policy catalog for your mission context. For example, it loads the PII definition for a data security mission. The agent then maps your intent to specific policies and selects those appropriate for each type of AI asset in your environment. The AI agents, MCP servers, and models each receive policies tailored to their role. 4. UnifAI Agent displays a structured table labeled **Policies I will enable**. The table lists each policy, the AI asset types it applies to, and its category. Review the full set of proposed policies and select the **Approve** button to proceed. After you approve the policies, UnifAI activates each policy across your entire asset fleet. A progress bar shows real‑time enforcement. When the process completes, all policies show an active status. ### Consistent Enforcement The mission becomes active and remains in effect without additional configuration. Policies continue to apply, and newly created AI agents, models, or MCP servers are automatically added to the mission scope. You do not need to revisit settings or reapply controls as your environment grows. The Lineaje AI chat provides ongoing visibility by summarizing the current security posture in natural language. It explains which policies are active, which assets are in scope, and how the Mission is enforcing protection across your environment. To learn more, see [Lineaje AI Assistant](/unifai/lineaje-ai-ai-assistant.md)? --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.veedna.com/unifai/missions/running-missions.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.