FERPA · COPPA · CIPA · SOPPA

AI safety + compliance for education

The eval + guardrail + red-team + audit platform for K-12, higher-ed, and EdTech vendors. Block FERPA-protected student-record leakage at the gateway, ship age-appropriate content scorers for under-13 surfaces, satisfy district + IRB audit obligations.

0
Scorers
0
LLM providers
0
Red-team plugins
0.00ms
Firewall p95

What ships today

Honest posture, not roadmap promises

Every checked item is in production today. In-progress items are flagged explicitly — no overclaiming, no vapor.

FERPA-aligned student record handling (PII firewall + minimum-necessary)
COPPA-compatible (no PII collection from <13 sessions)
CIPA-friendly content filter (per-district policy thresholds)
SOPPA (Illinois)-aligned data subject right intake
Age-appropriate toxicity + violence + adult-content scorers
IRB-ready audit trail for academic research using LLMs
GDPR Article 8 (consent for <16) compatible age-gate flow

Built for buyer reality

EdTech AI use cases we ship for

AI tutoring chatbot

Student asks the AI for help on a homework problem. Must not give the answer outright (cheating), must redirect appropriately when off-topic, must catch crisis signals (self-harm / abuse disclosures) and escalate.

EvalGuard features

  • Topic firewall: blocks queries asking for direct homework answers (Socratic-mode default)
  • Crisis-signal scorer: trained on self-harm + abuse disclosure patterns, routes to escalation
  • Age-appropriate content filter: per-grade-band thresholds for toxicity / violence / adult content
  • Audit log: privacy-preserving conversation log for IRB + parental review

Grading + feedback automation

AI drafts feedback on student essays. Must not leak prior students' work, must give substantive feedback grounded in the rubric, must satisfy FERPA on student-record handling.

EvalGuard features

  • PII firewall: student name + ID + grade-history auto-redacted from logs
  • Rubric-faithfulness scorer: every feedback line cited to a specific rubric criterion
  • Output toxicity scorer: catches dismissive or judgmental phrasing in essay feedback
  • Cross-tenant RLS: per-classroom isolation enforced at every DB query

Student-facing search + research

AI helps students find primary sources for a research paper. Must cite real sources (not hallucinate citations), must respect age-appropriate content filters, must catch academic-integrity red flags.

EvalGuard features

  • Citation-coverage scorer: blocks responses that name sources not in the verified corpus
  • Hallucination guard: faithfulness check against the institutional library
  • Academic-integrity scorer: catches direct-plagiarism + AI-detection-evasion patterns
  • Per-school BYOK keys: institutional encryption isolates research per university

District-IT chatbot for parents/staff

School-district chatbot answers parent + staff questions about enrollment, schedules, transportation. Cannot leak student records (FERPA), cannot give legal-style accommodation determinations.

EvalGuard features

  • FERPA firewall: student record fields redacted before any LLM call
  • Topic firewall: blocks queries asking for IEP / 504 / disability determinations
  • Per-district rate limits prevent enumeration attacks against the SIS API
  • Audit log: every interaction tagged with district + program for OIG audit recoverability

Wire it in 60 seconds

Wrap your OpenAI client. Scope to a district + grade band.

Per-district project IDs isolate FERPA boundary + age-appropriate scorer thresholds. Crisis signals fire an onOutputViolation callback that escalates to district counselor workflow.

typescript
import OpenAI from "openai";
import { wrapOpenAI } from "evalguardai-openai";

const openai = wrapOpenAI(new OpenAI(), {
  apiKey: process.env.EVALGUARD_API_KEY!,
  projectId: `tutor_${districtId}_${gradeBand}`,
  metadata: { vertical: "edtech", districtId, gradeBand },
  blockOnViolation: true,                  // student PII pre-egress block
  evalOnResponse: { failOnScore: 0.9 },    // age-appropriate + crisis gate
  onOutputViolation: (s) => escalateToCounselor(s, districtId),
});

await openai.chat.completions.create({
  model: "gpt-4o",
  messages: [{ role: "user", content: tutoringPrompt }],
});
Crisis-signal scorer + age-band thresholds + FERPA retention configured per project in the control plane — no SDK calls needed.
Same integration for Anthropic, Gemini, and 91+ providers — swap wrapOpenAI for wrapAnthropic.

Stack

Six surfaces, one platform

Eval, firewall, red-team, audit, BYOK, dashboard — every surface ships out of the box. No bolt-on vendors, no procurement cycle per capability.

Student-data firewall

FERPA-aligned redaction: student ID, grade, IEP/504 status, address, parent contact info.

Age + safety scorers

Age-appropriate toxicity + violence + adult-content + crisis-signal scorers per grade band.

Red-team (249 plugins)

EdTech pack: PII extraction, age-gate bypass, jailbreak-for-direct-answers, integrity-evasion attacks.

Audit log + IRB trail

Tamper-evident audit log + IRB-ready conversation logs for academic-research use cases.

BYOK + classroom isolation

Per-school encryption keys via Vault — district + classroom isolation enforced at the byte level.

Compliance dashboard

FERPA / COPPA / SOPPA control coverage with auto-generated evidence for district auditors.

Ship classroom AI that parents trust + districts approve.

Free trial includes FERPA firewall, age-appropriate scorers, crisis-signal detection, and the full audit log. District-level deployment + SOPPA evidence bundle on request.

Start free trialTalk to founders

Apache-2.0 source · SOC 2 Type II in progress · full trust center