Agent report card
Can an agent use AWS Cloud through API resource management?
Grade B+: Only some material eligibility conditions are decidable before commitment.
AWS / active
Five-stage assessment
Where agent autonomy holds and where it breaks
- EvaluateLimited
- Sign upReady
- PayReady
- ProvisionReady
- OperateLimited
Only some material eligibility conditions are decidable before commitment.
The exact service and stable evaluation or access entrypoints are publicly discoverable.
Applicable terms are stable, readable, retrievable, and materially complete.
Price or no-charge status, variables, currency, and material conditions are explicit.
Evidence and actions6 signals
Can an agent decide every material eligibility condition before commitment?
supported: freshOnly some material eligibility conditions are decidable before commitment.
AWS Service Terms disclose specific eligibility rules for certain regional and account offerings, such as AWS UK switching addendum eligibility and AWS GovCloud (US) registration and eligibility verification requirements.
Can an agent estimate cost or confirm no-charge status before commitment?
supported: freshPrice or no-charge status, variables, currency, and material conditions are explicit.
AWS provides explicit pricing details and mechanisms before commitment, including the AWS Price List API catalog of products and prices and a pay-as-you-go pricing approach where users pay only for consumed services.
Can an agent find the exact service and its stable entrypoints?
supported: freshThe exact service and stable evaluation or access entrypoints are publicly discoverable.
AWS Cloud Control API provides a standardized set of APIs and AWS CLI commands (e.g., create-resource, delete-resource, get-resource, list-resources, update-resource) to discover and perform CRUD-L operations on supported AWS resources.
Are verified structured discovery artifacts available?
missing: unknownCurrent admissible evidence does not resolve this finding.
Can an agent retrieve and understand the applicable commitment terms?
supported: freshApplicable terms are stable, readable, retrievable, and materially complete.
The applicable AWS Service Terms are retrievable, readable, and publicly accessible online.
Does the vendor deliberately describe access for web agents?
missing: unknownCurrent admissible evidence does not resolve this finding.
What would improve this stage
- State every material eligibility condition and required input explicitly.
A stable canonical route begins the required access bootstrap.
Scoped revocable credentials or delegated authorization have explicit consent and resumption boundaries.
Evidence and actions5 signals
Can an agent operate the access controls and safe handoffs deterministically?
supported: freshCurrent admissible evidence does not resolve this finding.
The sign-up endpoint evidence contains metadata and a page title ('AWS Console - Signup'), but does not contain sufficient information to determine whether access controls and safe handoffs can be operated deterministically.
Is there a stable route to begin obtaining service access?
supported: freshA stable canonical route begins the required access bootstrap.
A stable canonical route to begin obtaining service access exists via the 'Sign up for AWS' page and AWS account registration instructions provided in the AWS Account Management User Guide.
Can an agent obtain access without an unsupported CAPTCHA boundary?
supported: freshCurrent admissible evidence does not resolve this finding.
Current admissible evidence across all target surfaces does not explicitly state whether an unsupported CAPTCHA boundary is required or bypassed during access.
Can an agent obtain scoped, revocable authority for this service?
supported: freshScoped revocable credentials or delegated authorization have explicit consent and resumption boundaries.
AWS STS operations such as AssumeRole and AssumeRoleWithWebIdentity provide temporary, scoped, and revocable security credentials in exchange for valid credentials or web identity tokens.
Can required phone verification be completed through a supported boundary?
supported: freshCurrent admissible evidence does not resolve this finding.
Documentation states that a phone number is required for identity verification during sign-up to receive automated calls or SMS codes, but it does not specify an explicit, supported agent handoff mechanism.
Charge or no-charge status, currency, recurrence, and material conditions are disclosed.
A documented direct purchase path reaches paid access without a vendor decision point.
Evidence and actions4 signals
Can an agent construct checkout, hand off approval safely, and resume?
supported: freshCurrent admissible evidence does not resolve this finding.
The retained evidence describes adding payment methods and completing account sign-up, but it does not establish a deterministic API or flow for agent-constructed checkout, approval handoff, and resumption.
Is the exact commercial commitment disclosed before authorization?
supported: freshCharge or no-charge status, currency, recurrence, and material conditions are disclosed.
AWS discloses its pricing models, including pay-as-you-go, flat-rate, and Savings Plans commitments, and provides catalog prices via the AWS Price List APIs and service pricing pages.
Can payment be authorized within scoped agent or explicit human authority?
supported: freshCurrent admissible evidence does not resolve this finding.
The evidence outlines account creation requirements and payment method management in the console, but it does not document a payment authorization rail supporting scoped agent delegation or human authorization with receipts.
Is a direct self-service path to paid access documented?
supported: freshA documented direct purchase path reaches paid access without a vendor decision point.
AWS documents a direct self-service path to create an account, enter billing information, select a Support plan, and complete sign-up to activate services without vendor intervention.
Provisioning is machine-triggerable or follows deterministically from an allowed handoff.
Credentials, grants, or configuration are delivered through a documented agent-usable flow.
A synchronous success response returns a usable created resource or access material; otherwise asynchronous work exposes progress, terminal state, reconciliation, and a documented bound.
Evidence and actions3 signals
Can usable access material be delivered securely to an authorized agent?
supported: freshCredentials, grants, or configuration are delivered through a documented agent-usable flow.
AWS STS API operations create temporary security credentials that include an access key ID, a secret key, and a session token, which applications or users can use to access resources.
Can an agent determine successful provisioning completion and reconcile asynchronous failure?
supported: freshA synchronous success response returns a usable created resource or access material; otherwise asynchronous work exposes progress, terminal state, reconciliation, and a documented bound.
AWS Cloud Control API provides get-resource-request-status to poll request progress using a RequestToken, returning an OperationStatus set to SUCCESS upon successful completion.
Can provisioning be initiated within supported agent authority?
supported: freshProvisioning is machine-triggerable or follows deterministically from an allowed handoff.
AWS Cloud Control API provides a CreateResource operation to initiate resource creation programmatically.
Only part of the credential lifecycle is agent-operable.
Every essential target has a stable documented agent-usable interface alternative.
Request-time authentication is documented and usable under scoped agent authority.
Essential operations have stable readable request, response, and effect semantics.
Applicable limits, errors, retry, idempotency, cancellation, and reconciliation semantics are documented.
Evidence and actions6 signals
Is an agent-native protocol interface verified against the essential targets?
missing: unknownCurrent admissible evidence does not resolve this finding.
Can an agent manage credential expiry, rotation, revocation, compromise, and recovery?
supported: freshOnly part of the credential lifecycle is agent-operable.
AWS STS documentation establishes that agents can request temporary credentials with specified validity durations using operations like GetFederationToken or AssumeRole. However, the evidence does not detail complete agent-executable revocation, compromise response, or recovery procedures.
Can an agent handle applicable failure modes safely?
supported: freshApplicable limits, errors, retry, idempotency, cancellation, and reconciliation semantics are documented.
AWS Cloud Control API documents idempotency via client tokens (valid for 36 hours), retries, and detailed HTTP status codes and error types (such as ThrottlingException, ConcurrentOperationException, and HandlerFailureException). Status tracking is supported via GetResourceRequestStatus using a RequestToken.
Can an agent authenticate service operations with scoped authority?
supported: freshRequest-time authentication is documented and usable under scoped agent authority.
AWS STS operations allow requesting temporary security credentials (access key ID, secret key, session token) and applying session policies to scope permissions programmatically for service requests.
Are essential operation inputs, outputs, and effects stable and decidable?
supported: freshEssential operations have stable readable request, response, and effect semantics.
Essential operations and pricing endpoints across Cloud Control API, IAM STS, and AWS Price List have stable request/response schemas, JSON/HTTP parameters, and defined operational effects.
- cloud-control
- public-pricing
Can an agent perform every essential assessment target through a usable interface?
supported: freshEvery essential target has a stable documented agent-usable interface alternative.
All evaluated targets provide documented programmatic interfaces, including HTTP APIs, AWS CLI commands, and SDK implementations.
- cloud-control
- public-pricing
What would improve this stage
- Provide scoped expiry, rotation, revocation, compromise, and recovery operations.
What works
- Sign up: A stable canonical route begins the required access bootstrap.
- Pay: Charge or no-charge status, currency, recurrence, and material conditions are disclosed.
- Provision: Provisioning is machine-triggerable or follows deterministically from an allowed handoff.
What blocks agents
- Evaluate: Only some material eligibility conditions are decidable before commitment.
- Operate: Only part of the credential lifecycle is agent-operable.
Startup offers
AWS on the startup-offers board
- Up to $200,000 in AWS creditsAWS Activate Portfolio credits
- Up to $200,000 in AWS Activate creditsAWS Activate Credits
- Up to $5,000 in AWS credits for selected Founders participantsAWS Activate Founders
- More than $200,000 in AWS creditsAWS credits for AI startups
Improve the report
Correct it, rerun it, or improve the funnel.
- Profile
- arp_01kzez1rxy9f1wce0r3p6yd35y
- Projection
- sha256:b39cc094dae8836d18a1de7af28c175b23975923db55fc94215687d0f3606f6b
- Policy
- service-use-2026-08-20-public-evidence-r9 · sha256:57bf95fd6d0fe6fe9173a68b60e8d8dc2179b357c88ff4349675a72d0e1d4139
Every request carries these exact identifiers.How report cards are assessed →View the exact declaration