AI agents for access reviews

As of 19 Nov 2026, two vendors publish a named access review agent: Lumos and Veza. Lumos says its agent certifies safe access itself and escalates the rest, while Veza lists dual reviewer sign-off before certification completes. Keep a per-item record of the threshold that let the agent act and the person who saw the item.

An agent prepares or performs access certification: which entitlements are still needed.

Who owns the parts:

Reads (What an agent reads)

2 of 2 vendors quoted on what the agent reads

Does alone (What it does without a person)Supplier’s settingsYours

1 of 2 vendors let customers build or change the agent

Tools and permissions

If you buy: Inside the supplier’s settings. 1 of 2 vendors listed for this job state on their pages that customers can build or change the agent; for the other 1, none found on 19 Nov 2026.

Source

NIST AI RMF 1.0: “MAP 4: Risks and benefits are mapped for all components of the AI system including third-party software and data.”

If you build: You grant each tool and each credential.

Source

OWASP LLM06:2025 Excessive Agency: “Limit the permissions that LLM extensions are granted to other systems to the minimum necessary in order to limit the scope of undesirable actions.”

A person approves (Where a person approves)Where offeredYours

2 of 2 vendors describe an approval step

Approval rules

If you buy: Where the product offers them. 2 of 2 vendors listed for this job describe an approval step on the pages read 19 Nov 2026.

Source

OWASP LLM06:2025 Excessive Agency: “Utilise human-in-the-loop control to require a human to approve high-impact actions before they are taken.”

If you build: You write which actions wait for a person.

Source

OWASP LLM06:2025 Excessive Agency: “Utilise human-in-the-loop control to require a human to approve high-impact actions before they are taken.”

Evidence (What evidence it leaves)Product recordsYours

1 of 2 vendors describe an audit trail

Logs

If you buy: What the product records. 1 of 2 vendors listed for this job describe an audit trail on the pages read 19 Nov 2026.

Source

MITRE ATLAS mitigations: “When deploying AI agents, implement logging of the intermediate steps of agentic actions and decisions, data access and tool use, installation commands, and identity of the agent.”

If you build: You log every step where the agent cannot edit it.

Source

MITRE ATLAS mitigations: “When deploying AI agents, implement logging of the intermediate steps of agentic actions and decisions, data access and tool use, installation commands, and identity of the agent.”

Model choice

If you buy: The supplier picks and updates the model.

Source

NCSC, Guidelines for secure AI system development: “You support users to evaluate and respond to model changes (for example by providing preview access and versioned APIs).”

If you build: You pick the model and can swap it.

Source

Anthropic, Scaling Managed Agents: “This allows the implementation of each to be swapped without disturbing the others.”

The tables below carry the quotes. All read 19 Nov 2026; counts from the vendors directory.

What the agents do in a review campaign

An access review is the periodic check that each person or account still needs each entitlement. Microsoft's Entra documentation puts it this way: "User access can be reviewed regularly to make sure only the right people have continued access" (Microsoft Learn). Lumos describes an Access Review Agent that scopes and runs campaigns; its access review page says agents flag anomalies and separation-of-duties conflicts and route them to the right owner, with campaigns scoped by apps, owners and frameworks (Lumos agents, Lumos access reviews). Veza's Access Review Agent is part of Veza Access Agents: it surfaces high-risk identities and explains complex reviews in plain language, and the reviewer still decides (Veza agents).

Vendors with a published agent for this job, alphabetical, the same fields for each vendor, read 19 Nov 2026. Claims are the vendor's own. Dot: stated; ring: none found.

  • Agent named for this jobAccess Review Agent (with Albus)
    What the vendor says it doesVendor says the agent runs reviews end to end (vendor claim)
    Customer can build or change agentsYes
    Full text

    Yes. The homepage offers a marketplace of ready agents and says customers can create custom agents; the access review page says campaigns are scoped by apps, owners and frameworks.

    Limits stated, or none foundNone found on 19 Nov 2026: the access review page …
    Full text

    None found on 19 Nov 2026: the access review page states no exclusions or out of scope systems.

  • Agent named for this jobAccess Review Agent (part of Veza Access Agents)
    What the vendor says it doesVendor says the agent speeds reviews with AI-assisted recommendations (vendor claim)
    Customer can build or change agentsNone found on 19 Nov 2026
    Full text

    None found on 19 Nov 2026. Neither the Access Agents page nor the Access Reviews page describes customers building agents. The Access Reviews page says reviewer actions can be automated under predefined and custom policies.

    Limits stated, or none foundThe Access Agents page presents the product partly as a …
    Full text

    The Access Agents page presents the product partly as a control plane for agent identity, which is out of scope here; only the Access Review Agent is counted. None found on 19 Nov 2026 for an agent audit trail.

Who signs the certification

An access certification is a statement by a named person that access is still needed, so the first question is who makes that statement for low-risk items. Lumos's agent certifies safe access on its own and brings only the items that need a human call; the customer sets the policies, guardrails and approval thresholds, and reviewers approve, deny or delegate the flagged items. Veza lists support for multiple reviewers who must both sign off before an access review completes, and for reviewer actions automated for entities matching predefined and custom policies (Veza access reviews). The vendors' own wording is in the table.

Approval and evidence wording from each vendor's own pages, read 19 Nov 2026. These are descriptions, not test results.
VendorApproval point, in the vendor's wordsEvidence kept, in the vendor's words
Lumos"You set the policies, guardrails, and approval thresholds.""every decision is stored as audit evidence"
Veza"Support for multiple reviewers who both must sign-off on an access review prior to completion and certification.""Be audit-ready and meet your SOX, NIST, and other regulatory requirements"

Three points the pages leave open, each to put to the vendor in writing:

  • The threshold below which Lumos's agent certifies without a person, and whether it can be set to zero. Lumos publishes no default threshold on its agents page or its access reviews page: the page says "You set the policies, guardrails, and approval thresholds."
  • Whether Veza's automated reviewer actions always get human review. The page does not say.
  • Whether an auditor accepts an agent's certification or only a person's. That is for your auditor; Lumos says decisions are stored as audit evidence with reports formatted for SOC 2, SOX and ISO 27001, and Veza mentions an API for certifications. Ask the auditor which items they will sample and what must exist for each (see the record below).

The guide on human approval design covers what an approver should see, and the checklist item on human approval points lists the questions to settle before go-live.

The record to keep for each certified item

Microsoft's Entra agents page, although it lists no access review agent, describes the shape of a useful record: "Each agent provides the context, reasoning, and activity history for how it came up with the suggestion" (Microsoft Learn). Ask for that per item, not a bare decision. The fields in the evidence and audit trail check apply; for this job:

Access certification record, one per item

  • Campaign name, scope (apps, owners, frameworks), open and close dates
  • Entitlement, the person or account, and the last-used date
  • Agent decision, and the policy or threshold that allowed it
  • Whether a person saw the item, and who
  • Reviewer action: approved, denied, delegated, or overrode the agent
  • Second reviewer name, where dual sign-off applies
  • Revocation ticket, and the date access actually ended

Download the template: .docx PDF CC BY 4.0

Worked example: a quarterly campaign from 1 to 30 Oct 2026

The organisation is constructed: the dates are real calendar dates and every count is invented, so none is a vendor result. The example combines features from two products: agent self-certification is Lumos's, dual sign-off is Veza's, and neither vendor describes both. A campaign opens 1 Oct 2026 and closes 30 Oct 2026 over 1,200 entitlements. The previous campaign closed 31 Jul 2026, and reviewers revoked 84 of its 1,200 items (7.0%).

  1. Before go-live, replay the 31 Jul campaign through the agent. Suppose its safe set is 900 items and 9 of the 84 revoked items are inside it: 9 of 84, or 10.7%, of the revocations the agent would have certified without a person.
  2. Weight the replay by entitlement type. Suppose 60 of the 1,200 entitlements are privileged (administrator roles), 12 of the 84 revocations were privileged, and 3 of those 12 sit inside the safe set; the other 6 misses are among the 72 non-privileged revocations (8.3%). Set the tolerance for privileged items at zero, so take all privileged items out of the safe set (45 of the 60 were in it), leaving 855. The replay now misses 6 of 84 (7.1%), none privileged. Accept that rate in writing for the rest and sample.
  3. On 1 Oct the agent certifies the 855 items inside policy and sends 345 (28.75%) to reviewers. Reviewer workload falls from 1,200 items to 345.
  4. By 16 Oct a named person re-reviews a 10% sample of the agent's certifications, 86 of 855 (rounded up). Any revocation found in the sample sends that whole entitlement class back to human review. The workload is then 345 plus 86, or 431 items (35.9% of 1,200), before the second signature in step 5.
  5. For each of the 345, two reviewers sign where dual sign-off is configured (a Veza feature; Lumos describes thresholds and reviewer approval instead), and both names go in the record. The campaign cannot close until both have. That doubles the signatures on the 345 items to 690, so the reviewer actions are 690 plus the 86 sample re-reviews, or 776, against 1,200 items in a campaign with no agent.
  6. On 30 Oct, check that every revoked item has a ticket and the date access ended. Keep what the auditor's sample needs for any item they draw: the full population list (1,200 items, matching the entitlement export), the agent's decision and the policy that allowed it, the name and date of the person who saw the item or the sample re-review, and the revocation ticket with the end date.

The case where the usual answer is wrong: a smaller review load is not the aim if the missed revocations are privileged accounts. Weighting by entitlement type turned 9 misses into 3 that matter, and the safe set shrank by 45 items to remove them.

Risk: an agent holding certify and revoke tools

MITRE ATLAS lists the technique AI Agent Tool Invocation (AML.T0053): "Adversaries may use their access to an AI agent to invoke tools the agent has access to." (MITRE ATLAS). For an access review agent the tools are certify, deny and revoke, so give the agent a role that can touch only the review system, and log each call with the identity of the agent.

Sources

  1. lumos.com/products/identity-agent-force, read 19 Nov 2026
  2. lumos.com, read 19 Nov 2026
  3. lumos.com/products/access-reviews, read 19 Nov 2026
  4. veza.com/product/veza-access-agents, read 19 Nov 2026
  5. veza.com/product/access-reviews, read 19 Nov 2026
  6. learn.microsoft.com/en-us/entra/security-copilot/entra-ag..., read 19 Nov 2026
  7. MITRE ATLAS data, ATLAS.yaml (techniques and mitigations), read 19 Nov 2026
  8. learn.microsoft.com/en-us/entra/id-governance/access-reviews-overview, read 19 Nov 2026

Last reviewed 19 Nov 2026