SDK Quick Start — Higher Education

Getting started: Higher Education

Control what your AI can do. The core SDK checks policy before your workflow runs an action and again before its result is released. Denied actions stop. Actions that need human review stay paused until a signed outcome arrives.

Catalog context. For an admissions or student-support workflow, record the decision stage and review outcome. Avoid copying student records into traces when metadata is sufficient. Assess privacy, accessibility, and decision-review requirements for the institution and intended use. A student's location alone does not determine every applicable obligation.

Use industry fields with the core SDK

Industry vocabularies supply typed values that the SDK sends as policy fields and evidence attributes with one governed call. Choose values that describe the actual workflow. Adding a vocabulary does not activate rules or assign regulatory requirements.

If you need the cross-industry baseline first, open the core SDK reference, Python core, or .NET core before continuing here.

Step 1 — Install the approved packages

In the customer portal, open Tools and SDKs. Select your language and adapters, then follow the installation instructions shown there.

VeriProof SDKs are distributed through customer-gated GitLab packages, not public registries. See SDK access for workstation and CI guidance.

VeriProof packages used here: @veriproof/sdk-core (TypeScript), veriproof-sdk (Python), Veriproof.Sdk.Core (.NET).

Step 2 — Configure

Store the application SDK key as VERIPROOF_API_KEY and create one client when the application starts. Publish the policy you want to enforce, then confirm its field contract against the facts and industry values your application supplies.

Copy the application ID and key from Set up SDK. The application ID is not its display name. Try a live demo  to see a governed workflow, or request an evaluation  if you need a workspace.

Step 3 — Govern the action

Put the protected business action inside govern. The SDK checks policy before it calls the action and before it releases the result. Deny and human-review decisions stop execution here.

import { Veriproof } from '@veriproof/sdk-core';
import type { GovernedResult, IndustryFact, JsonValue } from '@veriproof/sdk-core';

const veriproof = Veriproof.fromEnv();

export async function runProtectedAction<TInput extends JsonValue, TValue>(
  request: TInput,
  action: (input: TInput, signal: AbortSignal) => Promise<TValue>,
): Promise<GovernedResult<TValue, TInput>> {
  // Catalog values for this vertical. Replace them with facts from the current workflow.
  const industry: IndustryFact[] = [
    { attribute: "education.student.success_risk_level", policyInput: "education_student_success_risk_level", value: "on_track" },
    { attribute: "education.early_alert.trigger_category", policyInput: "education_early_alert_trigger_category", value: "attendance_absence_threshold" },
    { attribute: "education.intervention.outcome", policyInput: "education_intervention_outcome", value: "student_engaged_retained" },
  ];

  // Policy runs before action() and again before the result is released.
  // A deny or review decision means action() never runs.
  return veriproof.govern(
    "higher.education.evaluate",
    request,
    ({ input, signal }) => action(input, signal),
    { industry },
  );
}

Only completed, completed_with_warning, and transformed results carry a released value. Handle every other status with its safe message, reason code, and evidence reference. For review decisions, save the checkpoint and continue through the human review workflow.

Add typed industry values

Each core SDK ships this vertical's vocabulary as generated types. A typed value becomes one policy field and one evidence attribute when you pass it to the governed call. Use application facts for values that are specific to your workflow.

Find this workflow's vocabulary in the Higher Education reference. Use the attribute names below and verify their policy-field mapping before using them in a rule. Sample values show the format; they are not recommended outcomes for your application.

TypeScript

import { Industry } from '@veriproof/sdk-core';
import { StudentSuccessRiskLevel, StudentSuccessRiskLevelMeta, EarlyAlertTriggerCategory, EarlyAlertTriggerCategoryMeta, InterventionOutcome, InterventionOutcomeMeta } from '@veriproof/sdk-core/industries/higher-education';

// Replace sample values with facts from the current workflow.
// Each value becomes one policy field and one evidence attribute.
const industry = [
  Industry.fact(StudentSuccessRiskLevelMeta, StudentSuccessRiskLevel.OnTrack),
  Industry.fact(EarlyAlertTriggerCategoryMeta, EarlyAlertTriggerCategory.AttendanceAbsenceThreshold),
  Industry.fact(InterventionOutcomeMeta, InterventionOutcome.StudentEngagedRetained),
];

const result = await veriproof.govern(actionName, request, runWorkflow, { industry });

Python

from veriproof_sdk.verticals.higher_education import StudentSuccessRiskLevel, EarlyAlertTriggerCategory, InterventionOutcome

# Replace sample values with facts from the current workflow.
# Each value becomes one policy field and one evidence attribute.
industry = (
    StudentSuccessRiskLevel.on_track.fact(),
    EarlyAlertTriggerCategory.attendance_absence_threshold.fact(),
    InterventionOutcome.student_engaged_retained.fact(),
)

result = await vp.govern(action_name, request, run_workflow, industry=industry)

.NET

using Veriproof.Sdk.Core.Industries.HigherEducation;

// Replace sample values with facts from the current workflow.
// Each value becomes one policy field and one evidence attribute.
var options = new GovernOptions
{
    Industry =
    [
        StudentSuccessRiskLevel.OnTrack.Fact(),
        EarlyAlertTriggerCategory.AttendanceAbsenceThreshold.Fact(),
        InterventionOutcome.StudentEngagedRetained.Fact(),
    ],
};

var result = await veriproof.GovernAsync(actionName, request, RunWorkflowAsync, options);

Workflow examples from the catalog

• Student Success & Early Alert: Student Success Risk Level. AI student success agent computes risk level nightly from LMS engagement, grade data, and attendance. Advisors receive daily caseload sorted by risk level. OPA policy requires that 'high_risk' students cannot have their risk score used for adverse actions (e.g. scholarship removal) without human review and student notification. (Eu AI Act Annex3 3b: EU AI Act Annex III para 3(b), High-risk AI: systems that assess or evaluate students. Requires human oversight, logging, transparency disclosure to students, and conformity assessment.)
• Student Success & Early Alert: Early Alert Trigger Category. Every early alert generated by the AI student success agent is tagged with its trigger category. This enables advisors to prioritise outreach type and ensures students can request explanation of why they received an alert. (Eu AI Act Art13: EU AI Act Article 13, Transparency: students must receive meaningful information about which trigger categories drove their AI risk assessment)
• Student Success & Early Alert: Intervention Outcome. AI success agent closes the intervention loop by recording outcome when the semester ends or the student's status changes. Outcome data feeds back into the AI risk model training pipeline, subject to FERPA deidentification requirements before model training use.
• Admissions & Enrollment Management: Admission Consideration Level. AI admissions screening agent references consideration level for each factor (test scores, GPA, essays, extracurriculars) to correctly weight its evaluation. 'Required' factors cannot be waived by the AI, missing required data must trigger human review, not a default score imputation.

Next steps

• Open the full Higher Education governance reference for all 22 enum categories, policy patterns, and source standards.
• Review TypeScript SDK core for stop handling, human review continuation, and the OpenAI Agents adapter.
• Review Python SDK core for stop handling, human review continuation, and the Microsoft Agent Framework adapter.
• Review .NET SDK core for stop handling, human review continuation, and the Microsoft Agent Framework adapter.
• Browse all vertical references to understand how the core governance vocabulary layers underneath vertical-specific attribute sets.
• Compare this guide with the public industry pages  for a business overview of the same workflows.