SDK Quick Start — Higher Education

Getting started: Higher Education

This guide takes you from install to your first attributed governance record in higher education. You will install the SDK, configure a provider, instrument a workflow step with the real OTel attribute vocabulary from this vertical, and have a reviewable evidence record in your portal within an afternoon. There is no scaffolding project — just your API key and the three steps below.

Why this matters right now. As of March 2026, agentic AI in higher education is deployed across: AI-driven student success platforms (early alert, academic coaching, intervention routing), autonomous admissions screening and application scoring (flagged as high-risk under EU AI Act Annex III para 3(a)), AI tutoring and adaptive learning systems (LTI Advantage integration with LMS), AI-generated course content and syllabus drafting, academic integrity detection and AI-assisted work disclosure enforcement, AI grant writing assistants and post-award compliance monitoring (2 CFR 200), autonomous financial aid verification and satisfactory academic progress (SAP) monitoring, AI-powered institutional research and IPEDS reporting automation, accessibility accommodation workflow automation (ADA/Section 504), and AI-driven enrollment forecasting and tuition revenue modelling. The EU AI Act Annex III para 3 explicitly classifies AI systems used to determine access to educational institutions, assess students, and evaluate learning outcomes as high-risk — requiring conformity assessment, logging, human oversight, and transparency measures before deployment. EU AI Act Annex III para 3 makes AI systems used in admissions decisions, student assessment, grading, and academic integrity evaluation high-risk AI as of August 2, 2026. US institutions deploying such systems for EU students or in EU operations must comply with the full EU AI Act Title III Chapter 2 obligations (risk management, data governance, transparency, human oversight, accuracy, logging). FERPA 34 CFR 99.31 governs all AI agent access to student education records — AI vendors receiving education records must execute a FERPA-compliant data sharing agreement (School Official exception or written consent). The 2024 proposed updates to FERPA's definition of 'education records' to include AI-generated academic assessments are under active ED rulemaking as of early 2026.

How the layering works

You are not adopting a separate product surface for this vertical. You are adding a market-specific vocabulary layer on top of the same core session model used everywhere in VeriProof.

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

Step 1 — Install

TypeScript / Node.js

npm install @veriproof/sdk-core

Python

pip install veriproof-sdk

.NET

dotnet add package Veriproof.Sdk

Step 2 — Configure

Call the configuration helper once, before any AI framework initialises. After that call, every OTel span in the process — whether emitted by your code or by a framework adapter — is exported automatically to VeriProof.

Your API key comes from the VeriProof portal. Try a live demo to see the portal before you register, or start a free Builder account and use the environment variable pattern above directly.

Need a production credential path rather than sandbox exploration? Get API access for a Builder account, or contact the team if you need an architecture or compliance review alongside implementation.

Step 3 — Instrument your workflow

The governance vocabulary for this vertical lives in the Higher Education reference. Use the OTel attribute names below — they are the same names the portal uses in evidence records and the same names your policy engine will evaluate. Consistency here is the point.

TypeScript example

import { configureVeriproof, VeriproofClient, VeriproofSdkOptions, SessionMetadata } from '@veriproof/sdk-core';
import { StudentSuccessRiskLevel, StudentSuccessRiskLevelMeta, EarlyAlertTriggerCategory, EarlyAlertTriggerCategoryMeta } from '@veriproof/sdk-core/verticals/higher-education';

// Call once at application startup
configureVeriproof(
  VeriproofSdkOptions.createProduction({
    apiKey: process.env.VERIPROOF_API_KEY!,
    applicationId: 'higher-education-app',
  }),
  { serviceName: 'higher-education-app', setGlobal: true },
);

// Instrument a governed workflow
const client = new VeriproofClient(
  VeriproofSdkOptions.createProduction({ apiKey: process.env.VERIPROOF_API_KEY! }),
);

const session = client
  .startSession('higher.education.review')
  .withSessionMetadata(SessionMetadata.forTransaction('txn-001').withEnvironment('production'))
  .addStep('evaluate', { output: { status: 'completed' } })
  .withMetadata(StudentSuccessRiskLevelMeta.otelAttribute, StudentSuccessRiskLevel.on_track)
  .withMetadata(EarlyAlertTriggerCategoryMeta.otelAttribute, EarlyAlertTriggerCategory.attendance_absence_threshold)

await session.complete();

Python example

import os
from opentelemetry import trace
from veriproof_sdk import VeriproofClientOptions, configure_veriproof
from veriproof_sdk.verticals import higher_education as he

# Call once at application startup
configure_veriproof(
    VeriproofClientOptions(
        api_key=os.environ["VERIPROOF_API_KEY"],
        application_id="higher-education-app",
    ),
    service_name="higher-education-app",
    set_global=True,
)

tracer = trace.get_tracer(__name__)

# Instrument a governed workflow
with tracer.start_as_current_span("higher_education.review") as span:
    span.set_attribute(he.StudentSuccessRiskLevel.__otel_attribute__, he.StudentSuccessRiskLevel.on_track.value)
    span.set_attribute(he.EarlyAlertTriggerCategory.__otel_attribute__, he.EarlyAlertTriggerCategory.attendance_absence_threshold.value)
    span.set_attribute(he.InterventionOutcome.__otel_attribute__, he.InterventionOutcome.student_engaged_retained.value)
    ...

.NET example

using Veriproof.Sdk;
using Veriproof.Sdk.Core.OpenTelemetry.Verticals.HigherEducation;

// Configure once at application startup
builder.Services.AddVeriproof(options =>
{
    options.ApiKey = builder.Configuration["VERIPROOF_API_KEY"]!;
    options.ApplicationId = "higher-education-app";
});

// Instrument a governed workflow step
using var activity = ActivitySource.StartActivity("evaluate");
    activity?.SetTag(StudentSuccessRiskLevel.Metadata.OtelAttribute, StudentSuccessRiskLevel.on_track);
    activity?.SetTag(EarlyAlertTriggerCategory.Metadata.OtelAttribute, EarlyAlertTriggerCategory.attendance_absence_threshold);
    activity?.SetTag(InterventionOutcome.Metadata.OtelAttribute, InterventionOutcome.student_engaged_retained);

How teams use this in production

• 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 advanced session-builder options, batch export, and Merkle verification.
• Review Python SDK core for decorator-based annotations and framework adapter options.
• Review .NET SDK core for Semantic Kernel, AutoGen, and Activity-based instrumentation.
• 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 if you need the commercial and workflow framing behind the same vocabulary.