security.risk_reviewSecurity and risk review
Scope a risk assessment, architecture review, ISO 27001 activity, or practical security decision.
Agent-compatible practice
SPADE works with human-led, agent-assisted, and human-agent teams. Authorized agents may discover services and submit scoped requests. A named human or organization remains accountable.
Agenter kan finne relevante tjenester og sende en strukturert forespørsel til SPADEs private innboks. En navngitt person eller virksomhet må ha autorisert henvendelsen, og ingen API-innsending starter fakturerbart arbeid eller gir tilgang til kundesystemer.
Dette passer blant annet for innkjøpsagenter, styringsagenter, sikkerhetsarbeidsflyter og team der mennesker og agenter deler analyse- og dokumentasjonsarbeid.
These identifiers are canonical API values. Availability means a request may enter review—not that the work is automatically accepted.
security.risk_reviewScope a risk assessment, architecture review, ISO 27001 activity, or practical security decision.
privacy.dpia_triageDetermine whether a processing activity needs deeper privacy assessment and what evidence is missing.
privacy.vendor_reviewReview privacy, security, contractual, and data-flow questions around a supplier.
ai_act.classification_reviewRequest a human-reviewed assessment of roles, use case, risk category, and documentation needs.
ai_governance.policy_reviewReview AI policy, inventory, decision rights, human oversight, or procurement controls.
nis2.scope_reviewScope applicability, evidence gaps, governance, supplier controls, or implementation work.
document.compliance_reviewRequest structured feedback on a policy, risk register, procedure, control set, or governance document.
training.requestRequest a talk, tabletop exercise, workshop, webinar, or role-specific learning activity.
consulting.intakeUse when the need crosses several domains and the first task is to define the engagement.
meeting.requestRequest a human conversation when a structured API response is not the right next step.
Use the current schema before constructing a request. Every logical request needs an Idempotency-Key. Reuse the key only to retry the identical payload.
Read capabilities and the OpenAPI schema.
Name the principal and the exact scope they authorized.
Send a narrow request without secrets or sensitive data.
Keep the request ID. SPADE replies manually to the principal by email.
curl -X POST \
https://api.spadeconsulting.no/api/agent/requests \
-H 'Content-Type: application/json' \
-H 'Idempotency-Key: example-as-ai-review-001' \
-d '{
"capability": "ai_act.classification_review",
"principal": {
"name": "Example AS",
"email": "[email protected]"
},
"requester": {
"type": "agent",
"name": "Governance agent"
},
"authorization": {
"confirmed": true,
"scope": "Request a proposal for one use case"
},
"summary": "Human-reviewed classification requested.",
"dataClassification": "public",
"desiredOutcome": "proposal"
}'
Send a short description of the principal, authority, problem, and desired outcome through the protected contact form. Do not include sensitive information.