M erit iew
Request access

For residency, fellowship, and admissions review committees

AI reads every applicant's file the same way. You still make the call.

Provable accuracy. Visible reasoning. Real ownership.

MeritView uses AI to read every letter, SLOE, and personal statement the same way for every applicant — surfacing the flag a tired reviewer might miss on file forty, and tracing it straight back to the sentence that triggered it. Independent reviewer rankings guard against anchoring before it can set in. Decision-support only: it never ranks or recommends a candidate for you.

Request access See it in action →
Built from firsthand committee experience Encrypted at rest Protected characteristics never scored
Knowledge Patient care Teamwork Communication Leadership Professionalism

Why committees choose it

Easy to roll out, easy to feel the difference

For administrators

Add your files, and go

Upload what your reviewers already have — no new candidate portal, no migration project, no IT ticket. Most committees are reviewing their first file within minutes of getting access.

For reviewers

Get your time back

Ratings, scores, and flags are extracted and organized automatically. Reviewers spend their time on judgment calls — not retyping numbers off a PDF or cross-referencing a scale by hand.

For everyone in the room

Bias reduction that isn't optional

Independent ranking, identity redaction, and protected-characteristic exclusion are enforced in how data moves through the system — not a setting a reviewer can forget to turn on.

See it in action

What your committee actually sees

Real screens from the live product, from an in-progress pilot dataset — not mockups.

MeritView dashboard showing a list of candidates with headline flags, letters, scores, and review status columns
One dashboard, every candidateHeadline flags at a glance, sortable and filterable — nothing important buried three clicks deep.
MeritView candidate summary showing a below-expectations flag, a letters-disagree warning, and strong and lukewarm flagged phrases
Every flag traced to its sourceDeterministic checks and AI-read phrases are labeled separately, so a reviewer always knows which is which.

From our pilot dataset

One flag, traced back to the sentence that raised it

A real screen from the live product, on a synthetic applicant from our own test dataset — not a real candidate.

MeritView flags panel showing a below-expectations flag on Communication Skills from Letter 1, directly next to the flagged phrase that triggered it: a lukewarm phrase reading a solid, capable student from Letter 1
Friendly words, flagged anyway "A solid, capable student" sounds like a compliment — MeritView still flags it lukewarm, because on this writer's own scale it's middling praise, and pairs it with the specific competency it dragged down: communication skills, rated below expectations.

Two seats at the table

Fairer review looks different depending where you're sitting

MeritView is licensed by the organization and used by the committee — but every mechanism below exists because of what it means for the candidate on the other side of the file.

For the organization & the committee

Defensible decisions, less second-guessing

  • A documented, consistent process you can stand behind if a decision is ever questioned.
  • Committee disagreement surfaces early, in the review, instead of in the post-decision debrief.
  • Nothing new to teach candidates — you're reviewing the same letters and files as always.
For the candidate

Your file, read on its own terms

  • Every reviewer ranks you independently before seeing a single other opinion — no one's first impression sets the tone for the room.
  • A strong, well-earned letter can't get quietly averaged down into "mediocre" because a reviewer misread the scale.
  • Race, ethnicity, disability status, and citizenship are never extracted or scored — not hidden after the fact, never touched at all.

What MeritView does

Structural bias resistance, not a UI toggle

Every mechanism below is enforced in how data is stored and shown — not a setting a reviewer can accidentally skip.

01

Independent ranking, first

Your committee ranking is locked in before you can see anyone else's — so the first opinion in the room isn't the one everyone anchors to.

02

Blind mode, on demand

Hide school and writer institution with one toggle when your committee wants to review on file content alone.

03

Every flag traces to a source

Deterministic checks and AI-read phrases are labeled separately, so a reviewer always knows whether a flag is a hard rule or a judgment call.

BELOW EXPECTATIONS STRONG AI-read
04

Disagreement, not a blurred average

Norm-referenced composite scoring flags outliers and reviewer disagreement instead of quietly averaging a strong letter into a mediocre one.

05

Protected characteristics: never

Race, ethnicity, disability, citizenship, and other protected characteristics are excluded at the schema level — not filtered after the fact.

06

Encrypted, with a real retention policy

Application materials are encrypted at rest. Set a retention window and flag stale files for deletion — reviewed by an admin, never automatic.

07

Rank list & side-by-side comparison

A real numeric rank order for your final decision, plus a facts-only comparison view for the 2–4 candidates your committee is weighing head-to-head.

08

Works alongside your process

Upload the reference letters and application files you already have. No new candidate portal, no change to how people apply.

Where it fits

Built for any structured, multi-reviewer file review

The mechanism is generic — independent ranking, identity redaction, and norm-referenced scoring don't care what the file is. Here's where it's proven today, and where it's headed next.

Live today
FlagshipResidency & fellowship selection
Natural next steps — not built yet
Academic admissions Grant & fellowship panels Hiring committees Board & panel review

What MeritView doesn't do

The boundaries are as deliberate as the features

Decision-support tools earn trust by being honest about their limits.

—
It doesn't rank or recommend candidates on its own.Every score and flag is meant to be checked against the source document — MeritView surfaces facts and disagreements, your committee makes the call.
—
It doesn't extract or score protected characteristics.Race, ethnicity, disability status, citizenship, and similar categories are never pulled from a document, even if present in the source file.
—
It isn't a replacement for your existing application system.MeritView reviews the files you already have — it doesn't manage applications, scheduling, or the downstream logistics of your process.
—
It doesn't silently delete anything.Retention flags a record for review; deleting it always takes a deliberate, logged confirmation from an administrator.
—
It's proven in one domain first.Residency and fellowship selection is where MeritView has real reviewers and real cycles behind it today. Fit for a new committee type is confirmed with you directly — never assumed.

How it works

Four steps, the same ones your committee already runs

01

Upload what you have

Reference letters and application files, per candidate — combined files are fine, MeritView sorts out the rest.

02

Structured extraction

Competency ratings, exam scores, and narrative flags are pulled out and cross-checked against the letter's own rating scale.

03

Independent committee review

Each reviewer ranks and comments before seeing anyone else's — anchoring only happens after everyone's already weighed in.

04

Your committee decides

Disagreements, rank lists, and side-by-side comparisons inform the conversation. The final call is always human.

Trust & security

Security your records office can actually verify

No vague assurances — here's exactly what protects your applicants' data today.

01

Encrypted at rest

Every applicant record and letter is stored in an encrypted database, not just protected in transit — the data on disk is encrypted, full stop.

02

Role-based access, enforced

Admins manage uploads, accounts, and deletions. Reviewers can view files and comment — they can't touch the account list or delete a record. It's built into the schema, not a setting.

03

A full audit trail

Every upload, role change, and deletion is logged. When a record is deleted, that history survives — who, when, why — even though the applicant's own data does not.

04

Retention with a human in the loop

Set a retention window and MeritView flags exactly which records are past it. Nothing is ever deleted automatically — an admin reviews the list and confirms before anything is permanently removed.

05

Your own deployment, not a shared database

Each institution runs its own instance with its own database. Your applicant data never sits in the same table as another institution's.

06

Account security built for real threats

Passwords are salted and hashed (PBKDF2, 390,000 iterations) — never stored in plain text. An account locks automatically after repeated failed logins.

Why we built this

"We're GME committee members ourselves. We know what it's like to be hours and a dozen files into a review session — tired, aware our attention wasn't what it was for the first applicant, and increasingly sure our own read was being swayed by whoever on the committee had spoken first. That didn't feel like a fair evaluation for every candidate, and we didn't think it had to be this way. We built MeritView because we believed there was a better way to run this process — one that catches what a tired read misses and protects every reviewer's independent judgment before the room starts talking."

— The founders, GME committee members

Early feedback

What early reviewers are telling us

MeritView is in active pilots now. Real quotes from real committees are coming as programs finish their first cycle — nothing fabricated, nothing placeholder-dressed-as-real.

"

Quote from a pilot reviewer — coming soon.

RESERVED FOR A REAL QUOTE
"

Quote from a program administrator — coming soon.

RESERVED FOR A REAL QUOTE
"

Quote from a committee chair — coming soon.

RESERVED FOR A REAL QUOTE

Piloting MeritView and willing to be quoted? Tell us — we'd rather have three real sentences than thirty invented ones.

FAQ

Questions committees actually ask

Is the AI making the selection decision?+
No. MeritView is decision-support only — it never ranks or recommends a candidate on its own. Every extracted fact and flag is meant to be checked against the source document by your committee.
Does this touch protected-characteristic data?+
No. Race, ethnicity, disability status, citizenship/visa status, and other protected characteristics are excluded at the schema level, so they're never extracted or scored — even when present in the source document.
Where does our data go? Is it appropriate for regulated data?+
Application and letter data are encrypted at rest, and you control a retention window with admin-reviewed deletion. Document text is sent to Anthropic's Claude API to run extraction — we'll walk you through exactly what that means for your organization's data agreements before you upload anything real.
What specialties or fields does it support?+
In residency and fellowship selection today, MeritView's competency schema and rating scales are configurable per specialty, not hard-coded to one program type. Tell us your field when you request access and we'll confirm fit before you commit to anything.
Can one reviewer try it, or does my whole committee need to sign on?+
Either. A single reviewer or small pilot committee can try MeritView on a handful of candidates, or an organization can roll it out for a full committee and cycle. Tell us which when you reach out.
How is it priced?+
MeritView is priced per institution, per admissions cycle. There's no public price list yet — request a quote and we'll scope it to your committee size and applicant volume.
I'm a candidate, not a reviewer — does this affect me?+
If an organization you're applying to uses MeritView, it means your letters and application file are reviewed by a committee where every reviewer ranks you independently before seeing anyone else's opinion, your file's flags are traceable back to the actual source text, and protected characteristics are never extracted or scored. MeritView doesn't accept applications directly — you'll still apply the normal way, through whatever system your target organization already uses.
Is this only for residency and fellowship selection?+
That's where it's live and proven today — see "Where it fits" above for what's built versus what's a natural next step. The underlying mechanism (independent-ranking gating, on-demand identity redaction, ambiguity-aware AI extraction, norm-referenced composite scoring) is patent-pending and general enough to apply to any structured, multi-reviewer selection process.
Who's behind MeritView?+
MeritView is built by GME committee members who lived this process from the reviewer's seat — see "Why we built this" above. It's built from that vantage point first — a tool for reviewers, not a generic hiring platform repurposed for someone else's process.

Get in touch

Request access

Tell us a little about your committee or your own review — we'll follow up directly to set up an account and walk through your data questions.

hello@meritview.app

Opens your email client with this pre-filled — nothing is sent until you hit send there.

Sign-in isn't public yet

MeritView is currently available to pilot partners only. Request access below and we'll set up your account directly.

Request access

Privacy Policy

MeritView is an early-stage, pilot-phase company. This policy describes how we handle information today; it will evolve as we grow, and we'll update this page when it does.

What we collect from this website

If you use the "Request access" form, we collect the name, email, organization, specialty, and message you provide. We use it only to respond to your inquiry and follow up about MeritView — we don't sell it, rent it, or share it with third parties for their own marketing. This site does not use tracking cookies or third-party analytics.

Applicant and reviewer data, once an institution is using MeritView

If your institution runs MeritView, the applicant files, letters, and reviewer activity your committee uploads belong to your institution — we process it on your behalf, we don't use it for our own purposes, and we don't share it across institutions. Specifics, matching what's described in the Trust & Security section above:

  • Application and letter data is encrypted at rest.
  • Each institution runs its own instance with its own database — your data is never stored alongside another institution's.
  • You control a retention window, and deletion always requires an explicit, logged confirmation from an administrator — nothing is ever purged automatically.
  • Document text is sent to Anthropic's Claude API to run extraction. We'll walk through exactly what that means for your data agreements before you upload anything real.

Your rights

You can ask what we hold about you, ask us to correct it, or ask us to delete it, by emailing hello@meritview.app. For applicant data inside an institution's own MeritView instance, that institution controls access and deletion directly through the product.

Questions

Email hello@meritview.app and we'll respond directly — this is a small team, not a support queue.

Last updated September 2026. A general summary, not a substitute for legal advice — an institutional pilot is governed by its own signed agreement, which we'll provide before any real applicant data is involved.

Terms of Service

MeritView is an early-stage, pilot-phase product. These terms cover use of this website and general use of the product; an actual institutional pilot is governed by its own signed agreement, not just this page.

What the product is — and isn't

MeritView is decision-support only. It extracts facts and surfaces flags from letters and application files for your committee to review — it never ranks or recommends a candidate on its own, and every flag is meant to be checked against the source document. Your committee makes every decision; MeritView never does.

Pilot-stage service

As an early-stage product, MeritView is provided "as is," without uptime guarantees or a formal service-level agreement, unless your institution's signed pilot agreement says otherwise. Features, pricing, and this general policy may change as the product matures.

Your responsibilities

  • Your institution remains responsible for complying with FERPA and any other law that applies to the applicant data you choose to upload — MeritView is a tool you use, not a substitute for your own compliance obligations.
  • You won't use MeritView to extract or infer protected characteristics that the product itself is designed to exclude, or otherwise attempt to circumvent its bias-resistance mechanisms.
  • Accounts are for your committee's use — don't share admin credentials outside your organization.

Ownership

We own the MeritView software. You and your institution own your applicant data, letters, and committee records — we're processing it on your behalf, not acquiring rights to it.

Liability

MeritView is provided without warranty of any kind during this pilot stage. To the extent permitted by law, we aren't liable for indirect or consequential damages arising from use of the product. Nothing here limits liability where the law doesn't allow it to be limited.

Contact

Questions about these terms: hello@meritview.app.

Last updated September 2026. A general summary, not a substitute for legal advice — governing law and jurisdiction will be specified in each institution's signed pilot agreement.