Eklipse Verifi
Try the demo

Verification over detection

Know what your students can explain.

Eklipse Verifi adds a short, submission-specific conversation to essays and discussion posts, then links each explanation to the claims, sources, replies, and rubric criteria faculty need to review.

Try a 90-second verification See the faculty evidence

Faculty decide. Verifi organizes the evidence.

Submission-specific questions

Grounded in the student's own words

Faculty-controlled decisions

No AI verdict, ever

Audio, typed & faculty-led

Equal response modes

Designed for LTI 1.3

Blackboard & Canvas first

Try it — no signup

Paste a paragraph. See what Verifi would ask.

Verifi reads the text, maps the claims, and shows the exact question a student would answer — and how the answer becomes evidence for you.

Peer reply from Maya: But doesn't high redundancy also waste energy the system could use to grow faster in stable conditions?

Verifi's claim map — pick one to verify

Anchor question Verifi would ask

You wrote: “I think biodiversity strengthens ecosystem resilience because species respond differently to disturbance, so the syst…” — walk me through why you reached that rather than an alternative explanation.

Adaptive follow-up: “Maya replied that redundancy wastes energy in stable conditions. How would you answer her?”

Choose a sample student answer

Choose an answer to see the linked evidence.

Sample data, illustrative output. Verifi does not judge authorship, and nothing you type here is retained.

The broken assumption

A polished submission is no longer proof of understanding.

A student can paste a prompt into a generative tool, submit the result, and never read it. Detection tools guess authorship and misfire on the students least able to defend themselves. Neither tells you what the student actually understands.

Verifi asks a different question. Not “did AI write this?” but “can the student explain the specific claims they made?”

Detection asks: did a machine write this?

Probabilistic. Biased against non-native writers. Unappealable.

Verification asks: can the student explain it?

Evidence-based. Fair across response modes. Faculty decide.

The discussion-board wedge

Keep the discussion. Verify the understanding.

Other tools replace the discussion board with a spoken exam or a video ticket. Verifi keeps the written LMS thread exactly as it is and adds a short, claim-specific verification to it.

Without Verifi

  1. 1Instructor posts the discussion prompt
  2. 2Student pastes the prompt into a generative tool
  3. 3A polished post and two replies appear
  4. 4Instructor has no evidence of comprehension

With Verifi

  1. The written post stays in the LMS thread
  2. Verifi selects one specific claim and a peer connection
  3. The student answers a 90-second verification
  4. Faculty get linked evidence — and decide

Adopt it without redesigning the course. Measurement, not policing.

The evidence chain

One chain. Every conclusion inspectable.

The gold line is not decoration — it is the product. Every observation traces both directions, from a rubric criterion back to the exact spoken words and the claim in the submission.

Rendered from the actual Verifi faculty workbench — no mockups, no stock footage.
  1. 01

    Submission

    The student's exact written claim

    “…species respond differently to disturbance…”

  2. 02

    Claim

    One specific statement, mapped to a source

    Linked: Holling 1973.pdf

  3. 03

    Question

    Grounded in that claim — never a trick

    “Why does redundancy speed recovery?”

  4. 04

    Explanation

    Spoken or typed, in the student's words

    0:48 · transcript aligned

  5. 05

    Evidence

    Observation citing the exact excerpt

    Names the mechanism, not a restatement

  6. 06

    Faculty decision

    The human outcome of record

    Understanding confirmed

The student experience

Students know exactly what happens.

What is recorded, why it is used, and when it is deleted — disclosed before anything starts. Every path has an equal alternative.

Preflight disclosure

Modality, data, time, retention — shown up front

Private practice

Rehearse without faculty ever seeing it

90-second conversation

One anchor question, one adaptive follow-up

Low-bandwidth audio

The normal mode — video is never required

Typed accommodation

A fully equal path, not a fallback

Completion & retry

A status, never an accusation

The faculty experience

Create, review, decide, learn.

The evidence workbench is the product — not a decorative report.

Build a verification

Paste instructions. Approve the plan.

Import an assignment or discussion from your LMS, or paste the prompt. Verifi drafts a claim map and a short question plan grounded in the rubric. You edit every question before it goes live.

  • AI-use policy is an assignment setting, not fine print
  • One anchor question + one adaptive follow-up by default
  • Audio, typed, and faculty-led are equal response modes

Verification plan · draft

1Explain why redundancy speeds the recovery pathAnchor
2Respond to Maya's energy-cost replyFollow-up
Time budget90 seconds

What Verifi is — and is not.

Evidence of explanation and application
An AI-writing detector
Submission-specific
A generic chatbot
Faculty-controlled
An automatic misconduct judge
Transparent about data
Covert proctoring
Accessible across response modes
A confidence, gaze, or accent scorer

Research & validation

Method, not a badge.

Verifi is built on the Multi-Modal Verification Framework (MMVF). We publish our method and validation plan, and we label every claim with its evidence state rather than calling ourselves “research-backed.”

Framework

The MMVF method

Five modalities — temporal, linguistic, interactive, visual, contextual — verifying comprehension, not authorship.

Planned

Validation plan

Agreement with blinded faculty review, inter-rater reliability, false-escalation and missed-gap rates, fairness across accents and languages.

Published

Model limitations

Where the system should not be used, and why misconduct decisions stay outside automated evaluation.

A peer-reviewed validity study is in progress. We will not publish accuracy numbers before it completes.

Trust & accessibility

Built for a procurement review.

Every state is labelled precisely. We never write “certified” when we are planning an audit.

FERPA posture

In place

Student-consented context only; no scraping

Data ownership

In place

The institution owns its data

Model-training policy

In place

Student data is not used to train models

Retention & deletion

In place

Recordings temporary by default; configurable

Accessibility target

In progress

WCAG 2.2 AA; equal typed / audio / faculty-led paths

SOC 2

Planned

Type II audit — planned, not yet certified

LTI 1.3

Built

Blackboard & Canvas launch, roster (NRPS) and grade passback (AGS) — built; institutional validation pending

Encryption

In place

In transit and at rest

Institutional SSO / SAML

Planned

Not built yet

Audit & human control

In place

Immutable faculty decisions; full provenance

Integrations

Honest about what is live.

Available
  • —Secure share links
  • —CSV roster import
  • —Evidence export
  • —Private cloud media storage (S3-compatible)
  • —Automated transcription & question generation
Built
  • —Blackboard & Canvas LTI 1.3 launch
  • —Roster sync (NRPS)
  • —Grade passback (AGS)

Institutional validation pending — no completed round-trip inside a customer LMS yet.

Planned
  • —SSO / SAML
  • —SOC 2 Type II audit

We do not display an LMS logo until that integration is live and documented.

Built for whoever carries the risk.

Faculty

Verify one assignment. Keep your course.

Departments

Templates, calibration, outcome coverage.

Institutions

Policy, retention, SSO, audit, LTI.

Secondary schools

FERPA-first, district-DPA path.

Start small

Verify one assignment before changing your whole strategy.

A one-assignment pilot: one course, one section, one semester. You collect the evidence; you decide whether it earns a wider rollout.

Try the demo

Request a one-assignment pilot

Preview build — no marketing email is sent.