Skip to content

Registry specification

AI agent inventory

An AI agent inventory is the record of every autonomous or semi-autonomous AI system operating in your organisation, what each one is permitted to do, and who is accountable for it. The hard part is not the storage — it is deciding what counts as an agent and keeping the record true a month later. Both are addressed below, with a full field specification.

The scoping problem: what counts as an agent

Every agent inventory project stalls in the same place. Someone asks whether a scheduled script that calls a model API counts, and the conversation consumes a fortnight. The definition that survives contact with a real estate is not about autonomy or architecture:

If it can take an action with a consequence outside its own process, and a model output influences whether or how it takes that action, it is an agent.

That is deliberately broad, and broad is correct at the inventory stage. The inventory's job is to be complete; the risk register's job is to be selective. Applying the test:

SystemIn scope?Why
Chat assistant that drafts text for a human to sendYes, low autonomyConsequence outside the process, mediated by a human. Record it; score it low
Nightly script that classifies tickets and sets priorityYesWrites to a system of record with no human in the loop
Model call that returns a sentiment score to a dashboardNoNo action; it produces a reading
Coding assistant that opens pull requestsYesCreates artefacts in a system others act on
Vendor product with an embedded AI featureYesYou are the deployer. The obligations attach to you
Recommendation ranking inside a product you ownYes, if it changes what a user is offeredConsequence outside the process, at scale

The vendor row is the one most inventories get wrong. Teams inventory what they built and omit what they bought, which is usually the larger population. Under EU AI Act Article 26, deployer obligations for high-risk systems — human oversight, use in line with instructions, log retention — land on the organisation using the system, not only on the provider who built it.

The field specification

Twenty-one fields in five groups. The first group alone is a usable inventory; add the rest in order as the population grows past what a person can hold in their head, which is about fifteen agents.

Identity (5) — the minimum viable inventory

FieldNotes
agent_idStable, never reused. Referenced by logs, incidents and the risk register
nameWhat people actually call it, not the repository name
purposeOne sentence, business-readable. If it takes a paragraph, it is probably several agents
ownerA named person accountable for its behaviour. Not a team
statusProposed / in development / monitored / live / retired. Drives which review applies

Technical (5)

FieldNotes
modelProvider and model identifier, with version where pinned. Unpinned is itself a finding
hostingProvider API, self-hosted, or embedded in a vendor product
frameworkAgent framework or SDK, or none. Determines what telemetry is available to you
toolsEvery tool, function or MCP server it can invoke. The most operationally important field on this list
triggersWhat starts it: user request, schedule, webhook, another agent

Access and data (5)

FieldNotes
identity_usedService account, delegated user identity, or shared credential. A shared credential is a finding on its own
systems_accessedSystems it can reach, each marked read or write
data_classesClassifications it can encounter: public, internal, confidential, personal, special-category
egressWhere data goes — which provider, which region, and whether the provider's terms permit training on it
human_in_loopNone / approval before action / review after action. The single strongest control on this list

Risk posture (3)

FieldNotes
autonomy_level1–4: suggests, proposes for approval, acts within bounds, acts unbounded
blast_radiusWorst credible consequence of it acting wrongly at full rate until noticed
reversibilityCan its actions be undone, and by whom, and how quickly

Governance (3)

FieldNotes
approved_by / approved_onWho let it go live. The agent equivalent of a decision log entry
last_reviewedDrives the staleness report
evidence_locationWhere the logs are and how long they are kept. Asked for during every incident, and by Article 26

tools is the field that pays for the whole exercise. During an incident, the question is never "which model was it" — it is "what could this thing reach". An inventory that records the model but not the tool surface answers the wrong question at the worst moment.

Where the data comes from

An inventory maintained by asking people is stale on arrival. Each field has a source that can be automated to some degree, and the ones that cannot be should be few enough to keep current by hand.

SourcePopulatesAutomatable
Repository and config scanningmodel, framework, tools, triggersFully — MCP configs and SDK imports are machine-readable
Identity provideridentity_used, systems_accessedFully, via service principals and OAuth grants
API gateway / egress logsegress, actual tool usage vs declaredFully, and it is the only check on drift
Procurement and vendor recordsVendor-embedded agentsPartly — needs an AI question in the questionnaire
The ownerpurpose, blast_radius, reversibility, human_in_loopNo. These are judgements

The pattern that works: discover technically, attribute manually, verify continuously. Machines find the agents and record what they can reach; humans supply purpose and consequence; egress telemetry checks whether the declared tool surface matches the observed one. That third step is what distinguishes an inventory from a spreadsheet of good intentions.

Why inventories drift, and the two fields that catch it

An agent inventory decays faster than a software asset inventory, because an agent can change materially without any code changing. Four mechanisms:

  1. Tool surface expands. Someone adds an MCP server to a configuration. The agent's name, owner and purpose are unchanged; what it can reach has doubled.
  2. The model moves under it. An unpinned model identifier gets a new version with different behaviour, and no change was made on your side.
  3. Prompt and instruction changes. Frequently held outside version control, frequently edited by people who do not consider it a code change.
  4. The vendor ships a feature. An approved product becomes an AI deployment on a release note you did not read.

Mechanisms 1 and 2 are detectable and should be alarmed rather than reviewed. A declared-versus-observed comparison on tools, and a version check on model, catch the majority of real drift — and both are cheap if you have the egress logs already.

The staleness metric worth reporting: proportion of live agents whose last_reviewed predates their most recent configuration change. Not "how many have we reviewed this quarter", which measures activity, but "how many are described by a record that was true before the thing changed", which measures whether the inventory is load-bearing.

Inventory, registry, catalogue

Three words used interchangeably for three different artefacts, which causes real confusion when a vendor sells you one and you needed another.

AnswersAudienceCompleteness bar
InventoryWhat exists, including what we wish did notRisk, security, auditMust include unapproved and vendor-embedded agents, or it is not one
RegistryWhat is approved and how to invoke itEngineeringOnly approved agents, by definition
CatalogueWhat is available to useThe businessA curated subset, presented for discovery

The failure is using a registry as an inventory. A registry contains what teams chose to register — which by construction excludes everything the governance exercise exists to find. If a record is populated by voluntary submission, it is a registry, whatever it is called, and it cannot answer a risk question.

Which fields a tool can keep true, and which stay yours

The specification above is twenty-one fields. Roughly two thirds can be populated and kept current automatically; the rest are judgements and no product supplies them. Being clear about the split is the difference between an inventory that stays true and one that is accurate on the day it is compiled.

FieldsKept true by
model, framework, tools, triggers, hosting Discover reads them from configuration, so they update when the configuration does — this is what catches silent scope expansion
identity_used, systems_accessed Agent identity and non-human identity management, from service principals and grants rather than from declarations
egress, observed vs declared tool use Runtime gateway — the only source that can contradict the record, which is the point
evidence_location Audit ledger, with retention set once rather than per agent
agent_id, name, status, approved_by, last_reviewed The registry holds them; you supply the approval
purpose, owner, blast_radius, reversibility, human_in_loop, data_classes You. These are judgements about consequence and accountability, and anything that claims to infer them is guessing

For reference, the fields Agent Trust Cloud states it holds per agent are owner, purpose, model, framework, tools, MCP servers, data sources, permissions and secrets, plus ten lifecycle statuses from Discovered through Quarantined to Retired. Against the twenty-one above, that leaves blast_radius, reversibility, human_in_loop and autonomy_level for you to add — which is the right division, because all four are judgements about consequence rather than facts about configuration.

One row does the work that justifies tooling at all: observed versus declared. Every other field can be maintained by a diligent person with a spreadsheet. Only runtime telemetry can tell you that an agent's real tool surface stopped matching its record three weeks ago, and that is the failure mode this artefact exists to catch.

The one field this page has called the most operationally important — tools — is also the one that drifts fastest. The free Discover plan is enough to populate it from configuration and see whether your existing record survives contact with the estate.

What the inventory is evidence for

Three separate demands land on this artefact, and knowing which one you are serving decides which fields you cannot skip.

Incident response

At 02:00, the question is which agents could reach the compromised system and what they were permitted to do with it. That is systems_accessed, tools, identity_used and evidence_location. This is the use that justifies the inventory on its own, regardless of regulation.

EU AI Act deployer obligations

Article 26 requires deployers of high-risk AI systems to use them in accordance with instructions, assign human oversight to competent persons, and keep logs under their control for a defined period. You cannot demonstrate any of that for a system you have not recorded — and human_in_loop, owner and evidence_location are the fields that speak to it directly.

Access review

Agents hold credentials and are systematically missed by joiner-mover-leaver processes, because they never leave. identity_used and owner are what lets an access review include them — and an agent whose owner has left the organisation is one of the most common and least detected findings in the whole category.

Common questions about AI agent inventory

What is an AI agent inventory?

An AI agent inventory is a record of every autonomous or semi-autonomous AI system operating in an organisation, capturing what each one does, which systems and tools it can reach, which identity it acts under, who is accountable for it and what evidence of its behaviour is retained.

What counts as an AI agent for inventory purposes?

A practical test: if it can take an action with a consequence outside its own process, and a model output influences whether or how it takes that action, it is in scope. That includes scheduled scripts calling model APIs and AI features embedded in vendor products; it excludes systems that only produce a reading with no action attached.

What fields should an AI agent inventory contain?

At minimum: identifier, name, purpose, named owner and status. A full specification adds model and version, hosting, framework, callable tools, triggers, identity used, systems accessed, data classes, egress destination, human-in-the-loop mode, autonomy level, blast radius, reversibility, approver and date, last reviewed, and evidence location.

What is the difference between an agent inventory and an agent registry?

An inventory records what exists, including unapproved and vendor-embedded agents, and serves risk and audit. A registry records what has been approved and how to invoke it, and serves engineering. A registry populated by voluntary submission cannot answer a risk question, because it excludes exactly what the exercise is looking for.

Why do AI agent inventories go out of date so quickly?

Because an agent can change materially with no code change: its tool surface expands when a configuration gains a new server, an unpinned model identifier moves to a new version, prompts are edited outside version control, and vendors ship AI features into approved products. Declared versus observed comparison on tools and models catches most of it.

Do we need an agent inventory for the EU AI Act?

Article 26 places obligations on deployers of high-risk AI systems — using them per instructions, assigning competent human oversight, and retaining logs. Those duties cannot be demonstrated for systems that have not been recorded, so an inventory is a practical prerequisite even though the Act does not name the artefact.

The field specification is a practical composite drawn from how these records are used in practice: incident response, access review, and demonstrating deployer obligations. It is not a published standard.

Last reviewed 2026-09-23. Published by Agent Trust Cloud, a Globixera company — globixera.com.