Let AI agents work.
Keep your team in control.

The governance layer for enterprise AI agents.

Workspace/Approvals
Example values

Approval queue

4All approvers
Needs reviewRecent decisions
Awaiting approval4
Rejected automatically1
Earlier today4
APR 2406Send weekly summaryApprovedMC1h
×APR 2405Export exceeds budgetRejectedPR1h
APR 2404Deploy reporting serviceApprovedJL2h
APR 2403Export pipeline reportApprovedPR3h
APR 2410 · Analytics

Export customer records

Read and export 2,400 customer records from a CRM through crm.contacts.export.

Status
Awaiting approval
Agent
Aanalytics_01
Approver
PRPriya Raman
Capability
crm.contacts.export
Budget
$10.00 of $50.00
Registered identity
Capability in scope
Approval required

Approval applies to this request only, with approvers chosen by your policy.

Designed for the stack you already use

Microsoft EntraOktaGoogle WorkspaceSlackHashiCorp VaultSplunk
Why now

Agents are already acting inside
the enterprise. 87% of studied
organisations report no AI-risk governance.1

Over 40%

of agentic AI projects will be canceled by the end of 2027, a Gartner forecast rather than an observed outcome, citing escalating costs, unclear business value, inadequate risk controls.

Gartner, press release forecast, 2025
$670,000

higher average breach cost for organisations with high levels of shadow AI, in IBM's 2025 study of 600+ breached organisations. 97% of those that suffered an AI-related breach lacked proper AI access controls (an association in that study population).

IBM, Cost of a Data Breach, 2025
109 : 1

machine and AI identities per human identity, and 61% of privileged access requests still fulfilled with standing privilege. The figures come from Palo Alto Networks' 2026 Identity Security Landscape Report, a survey of 2,930 cybersecurity decision-makers.

Palo Alto Networks, Identity Security Landscape Report, 2026

1 IBM, Cost of a Data Breach 2025: 87% of the studied organisations reported no governance policies or processes to mitigate AI risk (an association in that study population, not a causal measure).

Why AAES

Enforced controls on actions routed through AAES. Clearly labelled records for what AAES can only observe.

AI agents need access to your applications, data, and systems to be useful. Ungoverned, that access can read, change, spend, or delete a whole database, without anyone approving the action. AAES is pre-launch; the controls below describe intended behavior, not generally available functionality. For supported enforced paths, AAES is being designed to deny dispatch or withhold the authority the action needs. It would not control credentials or execution routes outside that boundary. On supported observed paths, AAES would record the telemetry it receives but could not block the action.

Permissions

Each request checked
through AAES.

Named approvers

Accountable employees approve
when policy requires it.

Spending limits

Planned accounting rule: each approved request would reserve its amount against the configured budget, and reservations are not released until the work item closes. This caps commitments recorded through AAES, not final vendor charges or spending outside AAES.

Sealed records

Planned for enforced paths: one signed record per action, and AAES would refuse dispatch if it cannot durably record the decision. Observed paths cannot be blocked; their records may be incomplete.

How it works

Control what agents can do.

Check agent requests routed through AAES against permissions, approval requirements, and spending limits before execution.
Keep employee access in your existing identity provider.

How will you set up approval routing?

Name the approvers.

Agent useChecks before action

AgentRequests a capability
AAESBefore use
Approval

Named approvers

Named in AAES.

No directory import.

At each use

Check each request

Keys in your vault.

Requests through AAES.

Apps and dataApplications, data,
and other systems
Review and revoke access

Employee accessOutside AAES

Employees
Request access
Entra / Okta / your existing IAM
Employee access stays here.
Apps and data
Applications, data, files

AAES can block an action when it controls the required credentials and the agent cannot bypass that path.Observation-only is not enforcement.

Agent request

Follow an agent action
from request to record.

EXAMPLE · EXPORT 2,400 RECORDS01 / 06

The agent requests an action.

The agent names the capability it wants to use. On the enforced path, the destination and credential come from the registration, never from the agent.

Actoranalytics_01
Capabilitycrm.contacts.export
Requested data2,400 records
Identity & approvals

Every registered agent
has someone accountable.

Every registered agent has at least one accountable human manager. Name the approvers in AAES.
The approval policy determines who must decide each request.

Authority, by designIllustrative product preview
Accountable manager
Priya RamanData Operations Manager
Owns this agent
analytics_01Analytics agent
Registered
crm.contacts.readcrm.contacts.exportreports.read
For each requestApproval policy

Determines who must decide.

May be required by policy
Named approver
Maya ChenClient Operations Manager
Named in AAES
Through AAES, only permitted capabilities are visible

An identity, not a shared key

Know which agent is acting and who is accountable.

Permission shapes discovery

Through AAES, agents only see the capabilities they are permitted to use. Anything else is a request for approval, not a grant of employee access.

A person decides

On an enforced path, a capability the operator registers as irreversible always requires approval by an authorized person. No policy can switch that off, and an agent can never approve itself. Each action approval covers exactly one request, exactly as reviewed, and it expires. AAES does not automatically recognize irreversibility; the operator’s registration and classification are declarations.

Budgets & policy

Spending through AAES.
Not a spending alert.

On requests through AAES, the amount is committed when the decision is made.
Over the ceiling, the request is blocked. Other vendor bills such as LLM tokens and cloud are not capped here.

Control before executionIllustrative product preview
Budgets/Analytics operations
Illustrative
Committed at decision time
$10.00of $50.00
Committed$40.00 available
MONTUEWEDTHUFRISATSUN
$45.00 export rejected. Requested amount exceeds the $40.00 remaining.
No call dispatched
AgentCommittedCeilingUtilizationDecision
analytics_01$10.00$50.00
Within budget
support_02$3.20$20.00
Within budget
data_04$44.50$45.00
Near ceiling
research_07$12.00$30.00
Within budget
Regulation

Nine jurisdictions.
Not one compliance answer.

Requirements for AI agents differ across these nine jurisdictions. AAES produces records to support compliance reviews, showing how it brokers credentials on enforced paths, requires human approval for irreversible actions, and applies spending limits.
Start with your jurisdiction.

Explore the Evidence Library
  1. 01 / HK

    Hong Kong

    PDPO (Cap. 486)
  2. 02 / SG

    Singapore

    PDPA · MAS FEAT
  3. 03 / AU

    Australia

    APRA CPS 230 / 234
  4. 04 / EU

    European Union

    EU AI Act (staged application)
  5. 05 / JP

    Japan

    AI Basic Plan · APPI
  6. 06 / CH

    Switzerland

    Revised FADP
  7. 07 / AE

    United Arab Emirates

    Federal PDPL · DIFC / ADGM
  8. 08 / UK

    United Kingdom

    UK GDPR · Critical Third Parties
  9. 09 / US

    United States

    EO 14365 · state AI laws

Evidence supports compliance review, not a compliance determination.

Integrations

Connect governance
to your existing stack.

Keep your identity provider, collaboration tools, vault, and monitoring. AAES connects them to agent permissions, approvals, and action records.

Microsoft Entra

Identity & directory

Operator sign-in via OIDC. Not an agent action path; without an IdP configured, operators use a client-set bearer token.

Okta

Identity & directory

Operator sign-in via OIDC. Not an agent action path; without an IdP configured, operators use a client-set bearer token.

Google Workspace

Directory & collaboration

Directory and surface registration. An agent holding its own workspace credential bypasses AAES; that path is observational at best.

Slack

Enterprise communication

Capability pack, enforced: the bot token stays in your vault and AAES injects it per call. Bypass: a token issued directly to the agent.

HashiCorp Vault

Secrets & key custody

The enforced path's credential source: AAES holds a reference and fetches at use. Bypass: material distributed outside the referenced path.

Splunk

Evidence & monitoring

Record export for your monitoring. Observational: it receives evidence and prevents nothing.

Tested against simulated vendor APIs. Compatibility with your live environment is validated during the design partnership.

Check your stack.

Tell us which tools your agents need to use. We’ll confirm what AAES supports, explain any limitations, and define what needs validation in your environment.

Discuss your integrations
Deployment

Your boundary.
Your control.

Deploy on your infrastructure and control your keys, storage,
and availability. Start on a single VM or deploy in your enterprise environment.

SINGLE VMCLIENT OPERATED
YOUR INFRASTRUCTURE
AAES · Docker Compose
Local data volume
Your keys or vault

Start with a single VM.

Run AAES with Docker Compose. Records live on your host. You create and control the keys.

docker compose up

You operate keys, storage, and availability; no availability SLA is offered.

Records

Verify your action records. Offline.

Check exported records for integrity without connecting to an AAES service.

Read the Evidence Library
From decision to offline verificationIllustrative example
Action record #4182Sealed
Registered actoranalytics_01
Actioncrm.contacts.export · 2,400 records
ApproverPriya Raman
Policyallow_export · R3
Budget committed$10.00 / $50.00
EnforcementEnforced
#4180e94d…f7c0
#418177b1…03aa
#41823f9c…8e21
SHA256 · 3f9ca41d…8e21Hash-chained
Offline verifier · example output
Verify exported record bundle
Record integrityPASS
Hash chainPASS
Signature checkPASS
Network calls0
✓ Record #4182 verified
Integrity checked against the supplied public key.

What the record establishes

Check offline that the sealed record, including its authorization, scope, and named approver, has not changed. Use a public key you already trust or verify separately. A key included with the export does not, by itself, prove where the record came from.

What it does not establish

A configured independent witness or timestamp authority can provide external evidence about a signed head, within that service’s scope. Neither is connected by default. That evidence does not attest to capture completeness, policy correctness, enforcement effectiveness, or regulatory compliance. Work outside mediated paths is not captured; caller-submitted reports are recorded as claims, not verified execution. A recorded dispatch does not prove the outcome, and observation-only records do not establish enforcement.

FAQ

Questions about AAES.

Have something else in mind?
Talk to us

What is AAES, exactly?

AAES (Autonomous Agentic Enterprise Systems) is the governance layer for enterprise AI agents. It applies permissions, approvals by authorized persons, and spending limits to actions routed through AAES, and records each decision. An action whose decision cannot be recorded does not proceed. Each registered agent has at least one accountable human manager. Employee access stays in your existing identity provider.

Does this replace our identity provider?

No. Keep employee access in Microsoft Entra, Okta, or your existing identity provider. Name the agent’s first approver in AAES. A directory integration can supply additional approvers where required; live tenant compatibility is validated during the design partnership.

Which actions require approval by an authorized person?

On an enforced path, a capability the operator registers as irreversible always requires approval by an authorized person; no policy can switch that off. Policies can require approval for other requests too. Each approval covers exactly one request: the intent and the exact request content the approver reviewed. If anything in the request changes, the approval no longer applies, and every approval expires. Actions through alternate paths are not prevented by this. An action approval applies only to the bound request; an access approval instead authorizes the specific entitlement requested, which may permit multiple requests within its scope and lifetime, each still subject to its action-level controls. The API also records agent-manager decisions and automated approval paths; these are distinct from approvals by authorized persons. They can never satisfy the mandatory authorized-person approval for a capability registered as irreversible, and an agent cannot approve its own request. A named approver recorded on a record is an attribution field; it does not by itself establish that the person was authenticated and authorized. The approver is the person authorized to decide that request; an agent cannot approve itself.

Can we observe before we enforce?

Yes. A capability can be registered as observed, with every record labeled accordingly. AAES can block an action when it controls the required credentials and the agent cannot bypass that path. While the agent retains its own direct credentials, AAES can record reported activity but cannot stop the call.

How do agents get data on a brokered-execution path?

The agent authenticates to AAES and requests a registered capability. AAES evaluates policy, obtains any required approval, journals the decision, and executes the permitted call using the configured customer-controlled credential path. The broker returns the permitted result rather than handing the downstream credential to the agent. This describes brokered execution, not observation-only integrations. Credential exposure through downstream responses, errors, logs and records remains a deployment test requirement. Credential isolation is not data isolation: AAES does not control arbitrary subsequent use of data already delivered to an agent.

What happens if AAES is unavailable?

Requests requiring a new AAES decision fail closed if AAES is unavailable or the required decision journal cannot be written: no new grant or brokered execution is authorized through that path. Previously issued grants can remain usable until expiry, for up to 15 minutes. This does not cancel work already authorized or undo downstream effects. Observation-only and bypass paths are not stopped by AAES’s unavailability. Employee access remains governed by your identity provider. You operate availability on your infrastructure; no availability SLA is offered today.

What do we keep if we stop using AAES?

You retain your exported records and the offline verifier supplied with your deployment. Check exported records for integrity without connecting to an AAES service. A configured independent witness or timestamp authority can provide external evidence about a signed head, within that service’s scope. Neither is connected by default. That evidence does not attest to capture completeness, policy correctness, enforcement effectiveness, or regulatory compliance.

Why not just use the native control planes from Microsoft, Google, or AWS?

If your agents live on one vendor’s cloud and that vendor’s tooling satisfies your reviewers, those tools are a reasonable answer. AAES is designed for estates that need customer-controlled custody of third-party credentials, approval as a precondition of dispatch, per-action ceilings on business spend through your own payment credentials, and exported records designed for offline integrity verification, across agents on any platform. AAES is pre-launch; the differences are stated as claims with dated sources on the comparison page, which also credits what the vendors genuinely offer.

Design partners

Build this with us.
On your stack.

Bring one real agent workflow, a named operator, and weekly feedback.
Here is what we bring to the design partnership.

We will test your stack

We test native adapters against your live tenants during the design partnership. You get a coverage matrix showing what works and where gaps remain.

Your priorities, on the roadmap

Help set what gets built next. Your agent workflow becomes a reference case we test the product against.

Founding terms, direct support

The design-partner license is $40,000 for 6 months. It includes a named engineer and a direct channel to the AAES team.

Start with a short introduction about your workflow and stack.

AAES

Start with one governed workflow.

Agree on the approval, evidence, and acceptance criteria before a design partnership.

Now inviting design partners.