For the complete documentation index, see llms.txt. This page is also available as Markdown.

Introduction to Agents

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.

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

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).

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

Add agents one by one in the BalkanID UI

Import or update many agents in bulk

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.

Last updated

Was this helpful?