> For the complete documentation index, see [llms.txt](https://docs.balkan.id/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.balkan.id/agents/introduction-to-agents.md). # Introduction to Agents {% hint style="info" %} **Early Access:** Agents is available as an Early Access capability. To enable Agents (Early Access) for your tenant, contact Customer Support or your BalkanID customer success representative. {% endhint %} ### What is an agent? In BalkanID, an **agent** is a governed automation actor — for example an AI agent, bot, workflow, or other non-human automation — that can use tools, credentials, and application access on behalf of your organization. Unlike a human employee, an agent typically: * Operates continuously or on a schedule * Authenticates with credentials rather than interactive login * May call tools, APIs, or MCP servers to take action * Can hold broad access across applications if misconfigured Agents extend **IGA for Non-Human Identities (NHI)** so you can govern automation with the same rigor you apply to people and traditional service accounts. ### Why Agents matter Automation increasingly holds powerful access: API keys, vault secrets, MCP tool servers, and application permissions. Without a dedicated agent inventory, that access is hard to find, own, and investigate. Common governance questions Agents help you answer: * Which automation actors exist in our environment? * Who is accountable for each agent? * Which identities and credentials does the agent have access to? * What resources can the agent reach, and what is its blast radius? * Which agents were discovered from an application versus registered manually? ### Core concepts #### Owner The **owner** is the employee in BalkanID who is accountable for the agent — its purpose, access, and lifecycle follow-up. Ownership is about accountability. It is not the same as saying the agent “is” that person as an identity. #### Access associations Agents can be associated with **identities** and **credentials** that they **have access to**. | Concept | Meaning | | ----------------------------------------- | -------------------------------------------------------- | | **Owner** | Employee accountable for the agent | | **Identity / credential → Agent mapping** | Which identities and credentials the agent has access to | {% hint style="info" %} Identity and credential mappings to an agent are an **access** relationship used for governance and blast-radius analysis. This is different from mapping an application identity to an employee for ownership (**Map to employee**). {% endhint %} #### Extracted vs registered agents | Source | Meaning | | ----------------------------- | ------------------------------------------------------------------------------------------------------------------ | | **Extracted** | Discovered automatically from a supported application integration. Most fields stay read-only and refresh on sync. | | **Manually registered / CSV** | Created in BalkanID. You control the inventory fields and can edit or delete them according to your role. | ### How agents enter BalkanID Agents can enter your tenant in three ways: | Method | When to use | | ------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------- | | [**Manual registration**](/agents/onboarding-agents/manual-registration.md) | Add agents one by one in the BalkanID UI | | [**Uploading Agents by CSV**](/agents/onboarding-agents/uploading-agents-by-csv.md) | Import or update many agents in bulk | | [**Discovering Agents from Integrations**](/agents/onboarding-agents/discovering-agents-from-integrations.md) | Extract agents automatically from a supported application | See Adding Agents for an overview of all three methods. ### What you can do with Agents Once Agents (Early Access) is enabled, BalkanID lets you: * Inventory agents under **Configure → Agents** * Assign an employee owner for accountability * Associate the identities and credentials an agent has access to * Inspect an agent’s access footprint and blast radius * Discover agents from supported application integrations To learn how the Agents UI works day to day, continue to [Viewing Agents](/agents/viewing-agents.md). ### Related Documentation 1. [Viewing Agents](/agents/viewing-agents.md) 2. [Onboarding Agents](/agents/onboarding-agents.md) 3. [Mapping Identities and Credentials to Agents](/agents/mapping-identities-and-credentials-to-agents.md) 4. [Unmapping Identities and Credentials from Agents](/agents/unmapping-identities-and-credentials-from-agents.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 dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.balkan.id/agents/introduction-to-agents.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. 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.