Skip to content
Medallions tangled into one pink knot, and one free medallion with its own amber thread.

Identity

Agentic IAM: identity and access management for AI agents

The short answer

Agentic IAM is identity and access management for AI agents. Every agent gets its own identity, proves who it is without a shared key, holds short-lived credentials scoped to one job, and acts on authority you can trace back to the person who gave it. Then you can revoke it in one place.

Written byBrian GagneCo-founder and CTO, Kief Studio
Technical review byAmelia GagneCo-founder and CEO, Kief Studio

Published

Activity log listing staff and team actions newest first, such as finished hand-offs, approvals and denials, each with a time stamp.
Agentic IAM pays off in the log: every action names the AI teammate or the person who took it, so nothing hides behind a shared login.

What is agentic IAM?

Identity and access management, IAM for short, is how a business decides who can get into what. It's the logins, the passwords, the permission groups and the person who turns an account off when someone leaves. Agentic IAM applies the same discipline to AI agents, the software that reads your inbox, updates records and drafts replies on its own.

Here's the short version I give owners. An agent is a new kind of user. It works fast, it never gets tired, and it can be talked into things by a sentence hidden in an email. So it needs its own account, only the access its job calls for, a way to prove who it is, and a clear line back to the person it's working for. That's agentic IAM, and none of it requires a security department.

Most of this is older than AI. What changed is who holds the access. When the user can be persuaded by what it reads, the identity rules around it have to assume it will be fooled sometimes, and the damage has to stay small when it is.

Staff keycards on lanyards hang on a wall with pink-lit edges, and one plain black keycard rests on an amber-lit badge reader.

Why agentic IAM matters now

Agents need credentials to reach your tools, and those credentials pile up faster than anyone tracks them. The 2026 Identity Security Landscape (opens in a new tab) from Palo Alto Networks counts 109 machine identities for every human one. Each of those is a login that agentic IAM has to account for.

The cost shows up in breach data. In IBM's Cost of a Data Breach Report 2026 (opens in a new tab), among organizations that reported an AI-related breach, 92% lacked proper AI access controls, as IBM's analysts explain here (opens in a new tab). That's an agentic IAM problem before it's an AI problem.

The standards people are on it too. NIST's National Cybersecurity Center of Excellence published a concept paper in February 2026 on software and AI agent identity and authorization (opens in a new tab), and in September 2026 it reported feedback (opens in a new tab) from more than 600 commenters. The summary of those comments (opens in a new tab) lands where we did: most commenters favored building on the identity standards you already have over starting from scratch, and one put it as applying existing standards to agents rather than creating a parallel identity stack.

In the same study, 21% of breached organizations reported a security incident involving an AI model or application, up from 13% the year before, as IBM's analysts note (opens in a new tab).

A towering helix of pink-edged tags with one amber tag at its heart.

Breached organizations is highest in 2026 report at 21%.

Among breached organizations in IBM's study, the share reporting a security incident involving an AI model or application rose from 13% to 21% in a year. Source: IBM, Every AI agent followed the rules. The data still leaked
Breached organizations
Previous year13
2026 report21
Among breached organizations in IBM's study, the share reporting a security incident involving an AI model or application rose from 13% to 21% in a year. Source: IBM, Every AI agent followed the rules. The data still leaked (opens in a new tab)

The four parts of agentic IAM

When I lay out agentic IAM for an owner, it comes out as four parts. Get these four right and most of the scary scenarios turn into small, recoverable mistakes.

AI agent identity: one agent, one account

Every agent gets its own identity. It never borrows an employee's login, and two agents never share one key. The joint guidance from the US, UK, Australian, Canadian and New Zealand cyber agencies, Careful adoption of agentic AI services (opens in a new tab), says developers should construct each agent as a distinct principal with its own unique keys or certificates.

For an owner, this means that when something goes wrong you can see which agent did it, and you can switch that one off without breaking the other five. An identity for AI agents is also how you keep the agent's actions separate from the person's in the log, which is the first question anyone asks after a mistake.

Agent authentication without shared secrets

Agent authentication is how the agent proves who it is to each tool it calls. A static API key pasted into a config file is the weakest form of agentic IAM, because anyone who copies the file becomes the agent. The joint guidance names the risk plainly: attackers can steal secret keys or tokens when organizations keep them static, share them across multiple agents, or protect them poorly.

The better pattern is the one the MCP authorization spec (opens in a new tab) uses for agents talking to tools. A protected server acts as an OAuth 2.1 resource server, the client names the exact server it wants a token for, and the server checks that the token was issued for it. A token for the calendar tool doesn't open the file share.

Delegated authority: acting on behalf of a person

Most agents work for someone. The sales agent drafts follow-ups for one rep, and the office agent books meetings on the owner's calendar. That's delegated authority, and the record should show both names: the agent that acted and the person it acted for.

The identity world already has words for this. The OAuth token exchange standard, RFC 8693 (opens in a new tab), separates delegation from impersonation. With impersonation, the agent becomes the person and the log can't tell them apart. With delegation, the agent keeps its own identity and its actions are recorded as the agent representing the person. In agentic IAM, pick delegation every time. It's the difference between "Sarah sent this" and "the follow-up agent sent this for Sarah, and Sarah approved it."

Short-lived, scoped credentials

A credential that never expires keeps working for whoever holds it, long after the job it was made for is done. The joint guidance asks you to replace static, long-lived secrets with ephemeral credentials that expire when the job is complete, and to require just-in-time credentials for high-impact or privileged actions. Short-lived credentials mean a leaked token is worth very little by the time anyone finds it.

Scope matters as much as lifetime. The agent that summarizes your inbox needs to read it and nothing more. NIST's Cybersecurity Framework 2.0 (opens in a new tab) asks for exactly this in PR.AA-05: permissions defined in a policy, enforced, reviewed, and built on least privilege and separation of duties.

Agentic IAM for a 5 to 50 person business

You don't need an identity team to do agentic IAM well. You need a system where each agent's account, permissions and log come built in, plus one person who knows which agents exist and what each one is for. A business with an owner, an office manager and an outside IT provider can run this, because the decisions are made once, at setup, and the system enforces them after that.

One agent, one account

Every agent gets its own identity and never borrows an employee's login or shares a key.

Authentication without shared secrets

Each agent proves who it is with a token issued for the one tool it calls.

Delegated authority

The record shows both the agent that acted and the person it acted for.

Short-lived, scoped credentials

Credentials expire when the job is done and carry only the access the job needs.

Four stone quadrants close into one disc, the last clicking into place in amber.

How agentic IAM fails, step by step

The joint guidance walks through a procurement agent that was given broad access to finance, email and contracts, with permissions checked only once at setup. An attacker compromised a low-risk tool the agent relied on and used the agent's privileges to modify contracts and approve payments. Because everything ran under a trusted agent identity, the audit logs looked legitimate. Security people call that a confused deputy. Here's the same chain with the control that breaks each link.

  • The agent holds more access than its job needs. The control: least privilege per agent and per task, reviewed on a schedule.
  • A shared or static key gets copied. The control: one identity per agent, short-lived credentials, and keys that never sit in code or chat.
  • A token issued for one tool gets replayed at another. The control: tokens bound to one audience, and servers that refuse anything else. The MCP spec says servers must not accept or transit any other tokens.
  • The agent is talked into a payment or a contract change. The control: anything that moves money or leaves the business waits for a named person's approval.
  • Nobody can tell afterwards who did what. The control: delegation recorded with both names, and a log the agent can't edit.

Too much access

Least privilege per agent and per task, reviewed on a schedule, keeps the agent's reach small.

Key gets copied

One identity per agent and short-lived credentials make a copied key worth little.

Token replayed elsewhere

Tokens bound to one audience are refused by every other server.

Agent talked into it

Anything that moves money or leaves the business waits for a named person's approval.

Nobody can tell

Delegation recorded with both names and a log the agent can't edit show who did what.

A tiny pink thread tugs a massive lever while an amber collar holds the pivot still.

How agentic IAM maps to the standards

You don't have to invent a framework for this. Agentic IAM sits inside the ones you may already answer to, which is good news when an auditor or a customer's security questionnaire shows up.

NIST CSF 2.0 PR.AA

The Protect function's identity category covers users, services and hardware. PR.AA-01 says identities and credentials for authorized users, services and hardware are managed by the organization, and PR.AA-03 says they are authenticated. An AI agent is a service in that language, so it falls under the rules you already have.

OWASP ASI03 and the NHI list

OWASP's Top 10 for Agentic Applications for 2026 (opens in a new tab) lists Identity and Privilege Abuse as ASI03. OWASP's own first quarter round-up (opens in a new tab) tags several real incidents with it, including one where the central failure was privilege abuse through a service agent's identity. The OWASP Non-Human Identities Top 10 (opens in a new tab) covers the keys underneath: insecure authentication (NHI4), overprivileged identities (NHI5) and long-lived secrets (NHI7).

The MCP authorization spec

When agents reach tools through the Model Context Protocol, the authorization spec is the agentic IAM rulebook for that connection. Authorization is optional in the protocol, and when a server over HTTP uses it, the spec builds it on OAuth 2.1 and requires resource indicators under RFC 8707 so every token names the one server it's for, and least-privilege scope requests, with more scope asked for step by step when a task needs it.

An amber block slides into an open slot in an existing steel lattice.

What we've learned running agentic IAM ourselves

We run Kief Studio on LTFI, so these aren't hypotheticals for us. My wife and partner Amelia handles how agents get added and retired on the operations side, and I handle what each one can touch. A few things we'd tell anyone.

  • Name every agent after its job. "Follow-up agent for sales" tells you what access it should have, and "the AI" tells you nothing.
  • Delegation beats impersonation every time. The first time you need to answer a customer's question about an email, you'll want both names on the record.
  • Permission creep often starts at setup, when someone grants broad access to get a demo working and nobody narrows it afterwards. Review agent access thirty days in.
  • The approval step does more for agentic IAM than any clever detection does. A fooled agent that can't send, pay or delete without a person's yes can waste some time, and it can't do lasting harm.
Loose pink-lit keys spill across a walnut tray, and a single key on an amber tag sits apart on a brass ring.

How LTFI handles agentic IAM

LTFI is the agentic business operating system Kief Studio makes and runs. These are the identity and access controls it ships with today.

  • Each AI teammate owns one job, and you talk to one chief of staff, which hands out the work.
  • Anything that sends, posts, publishes or spends waits for the person who owns it.
  • Rules, permissions, credentials, deleting and money stay with people. An AI teammate can't change them.
  • Standing approvals are given for one kind of work and taken back at any time.
  • The activity log records every action by the staff and the team, newest first, with who approved it.
  • Your company runs on its own dedicated server, and your AI runs on keys you own, with spend caps you set.
A walnut front desk with an amber-lit brass desk bell, and a wall of cubbies behind it each holding one pink-edged folder.
Lower half of the Waiting on you queue with a spend request, a free site ready to publish, standing approvals and decision history.
Standing approvals and past decisions sit in one place, so the authority each agent holds is visible and easy to take back.

What to do about agentic IAM this month

Two lists: one for the person who owns the business, one for whoever runs its systems.

If you own the business

  1. List every AI tool or agent that can log in to company email, files, the CRM or the bank, and write down whose behalf each one works on.
  2. Make sure no agent uses a person's login. If one does, that's the first thing to fix.
  3. Decide which actions need your yes: sending, paying, deleting and changing permissions are a good start.
  4. Ask any AI vendor to show you its agentic IAM on screen, including how to switch off one agent without affecting the others.

If you run the systems

  1. Give every agent its own service identity, and retire shared keys and borrowed user accounts.
  2. Issue short-lived, audience-bound tokens scoped to the task, with just-in-time elevation for privileged actions.
  3. Use delegation, never impersonation, so logs record the agent and the person it acts for.
  4. Require resource indicators and audience checks on MCP servers, and refuse token passthrough.
  5. Review agent permissions on a schedule and after every change to the agent's job.

Key takeaways

  • Agentic IAM is ordinary identity discipline applied to a user that can be talked into things.
  • Every agent needs its own identity, its own way to authenticate, and credentials that expire.
  • Delegated authority should name both the agent and the person, so accountability never blurs.
  • Least privilege plus a person's approval on high-impact actions keeps a fooled agent's mistake small.

Where this lines up with the standards

The frameworks and rules this page maps to, with the exact item and what it asks of you.

FrameworkItemWhat it asks
OWASP Top 10 for Agentic ApplicationsASI03 Identity and Privilege Abuse (opens in a new tab)Prevent identity and privilege abuse by giving each agent narrow, separate identity and privileges.
OWASP Non-Human Identities Top 10NHI4 Insecure Authentication; NHI5 Overprivileged NHI; NHI7 Long-Lived Secrets; NHI10 Human Use of NHI (opens in a new tab)Use strong authentication, cut overprivilege, replace long-lived secrets, and keep people off machine identities.
NIST CSF 2.0PR.AA-01, PR.AA-03, PR.AA-05 (opens in a new tab)Manage and authenticate identities for services, and enforce least privilege and separation of duties.
MCP authorization specOAuth 2.1, RFC 8707, token handling (opens in a new tab)Bind each token to one server, request least-privilege scopes, and refuse token passthrough.
Joint agency guidanceCareful adoption of agentic AI services (opens in a new tab)Make each agent a distinct principal, use ephemeral credentials, and limit permissions to the task.
Massachusetts201 CMR 17.00 (opens in a new tab)Control user IDs, assign unique identifications, and restrict access to personal information to those who need it.

Key terms

Machine identities for every human oneSource: paloaltonetworks.com
109
Organizations with an AI-related breach that lacked proper AI access controlsSource: ibm.com
92%
Commenters on NIST's software and AI agent identity concept paperSource: nist.gov
More than 600

Questions

Agentic IAM

What is agentic IAM?

Agentic IAM is identity and access management for AI agents. Each agent gets its own identity, authenticates without a shared key, holds short-lived credentials scoped to its job, and acts on delegated authority that traces back to a person.

How is agentic IAM different from regular IAM?

The tools are the same: accounts, credentials, permissions and logs. The difference is the user. An agent can be persuaded by text it reads, so agentic IAM assumes the agent will sometimes be fooled and keeps its access small enough that the mistake stays small.

Should an AI agent use my login?

No. An agent on your login can do everything you can, and the log can't tell its actions from yours. Give it its own identity and record that it acts for you.

What is delegated authority for AI agents?

Delegated authority means an agent acts on behalf of a person while keeping its own identity. The record shows the agent that acted and the person it acted for, which is how you keep accountability clear.

How do AI agents authenticate?

Agent authentication should use credentials issued to that one agent, for one tool, for a short time. Where an MCP server uses authorization, the spec does this with OAuth 2.1 tokens bound to a single server.

Does agentic IAM apply to a small business?

Yes. Agentic IAM for a small business is mostly choosing a system where each agent has its own account, narrow access and a log, then naming the person who owns each agent.

Does 201 CMR 17.00 cover AI agents?

It applies to anyone who owns or licenses personal information about Massachusetts residents. It doesn't mention AI, but its requirements for control of user IDs, unique identifications and access limited to those who need it apply to agents as users.

Can agentic IAM stop prompt injection?

No. Agentic IAM doesn't stop an agent from being fooled by what it reads. It limits what a fooled agent can reach, and an approval step on sending, paying and deleting stops the harmful action before it runs.

Who owns agentic IAM in a small business?

The owner does, even when an IT provider does the setup. Name one person who keeps the list of agents, approves new access and switches an agent off when its job ends.

Where do I start with agentic IAM?

List every agent and AI tool with access to company systems, and note whose behalf each one works on. Then give each its own identity, cut its access to the job, and put a person's approval on sending, paying and deleting.

Is agentic IAM the same as non-human identity management?

They overlap. Non-human identities cover every service account, key and token a business runs. Agentic IAM is the part of that work for AI agents, which can be persuaded by what they read, so agentic IAM adds delegated authority and a person's approval on risky actions.

How often should agentic IAM access be reviewed?

Review it on a schedule you keep, and again whenever an agent's job or tools change. Each agentic IAM review checks that the agent still has an owner, still needs every permission it holds, and still uses credentials that expire.

Keep reading

  • A heavy threshold gate lets one cleared path through while dozens of pink trails stop at it.

    Start here

    Agentic AI security

    Agentic AI security explained for owners: identity, least privilege, approvals and an audit trail for AI agents, from the team that runs them in Massachusetts.

    Brian Gagne

  • A blurred hub drowns in pink cables while a clean hub in front holds one amber line.

    Identity and access

    AI agent permissions

    AI agent permissions decide what an agent can read, change and send. How to scope its tools, catch permission drift and run an access review.

    Brian Gagne

  • A sprawling swarm of small pink-lit tags, with one sealed and glowing amber inside a single capsule.

    Identity and access

    Non-human identities

    What a non-human identity is, why AI agents multiply them, and how to vault, scope and rotate API keys, tokens and service accounts before one leaks.

    Brian Gagne

  • Many pink cables converge on one hub, and every connection passes through its amber iris.

    Threats

    MCP security

    MCP security for businesses running AI agents: what the Model Context Protocol's authorization rules require, and how to vet servers and stop tool misuse.

    Brian Gagne

  • A capsule travels through a line of rings and exits cleanly through an amber one.

    Identity and access

    AI agent lifecycle

    The AI agent lifecycle, run like staffing: who requests and owns an agent, what it gets on day one, how access is reviewed, and how to retire it cleanly.

    Amelia Gagne

  • Reference

    Glossary

    An agentic AI glossary in plain words: AI agents, agentic IAM, non-human identities, prompt injection, shadow AI, MCP and more, each with a short definition.

Most MSPs are resellers. Kief Studio is the manufacturer.

A reseller sends your problem to the company that made the software. We are that company: we build LTFI and run it, so the people you talk to can change it. Book a walkthrough and see it on your own business.

Nothing plays until you press play.