Six agents. One evidence-backed shortlist.

Find professors whoactually fit you

Turn your résumé and research goals into explainable professor matches, a balanced shortlist, personalized outreach, and meeting-ready context.

Swipe horizontally to explore the full workspace

Interactive sample · no sign-in required
PhdFit
Alex MorganAM

Professors · Recommended

Professor match evidence

Every score is traceable to your profile and the professor's current work—not just shared keywords.

Sample workspace
SC

Dr. Sarah Chen

Strong fit

Stanford University · Trustworthy NLP & Human-Centered AI

91

fit score

Research overlap94
Methods fit91
Mentorship signal86
Lab trajectory90
Outreach potential93
Evidence from a recent paper

Calibrated Explanations for Language Models

ACL 2026 · Strong overlap

Auditing Fairness in Human-AI Decisions

FAccT 2025 · Methods overlap

When Confidence Should Defer

EMNLP 2025 · Trajectory signal

Sample lab facts

Openings
1 PhD position
Lab size
12 members
Citations
6,842
Contacts
2 mutual
Six-agent team
All online

Top programs in our database · faculty coverage

Princeton University
MIT
Harvard University
Stanford University
Yale University
University of Pennsylvania
Caltech
Duke University
Brown University
Johns Hopkins University
Northwestern University
Cornell University
University of Chicago
UC Berkeley
Dartmouth College
Vanderbilt University
University of Notre Dame
University of Michigan
Georgetown University
UNC Chapel Hill
Carnegie Mellon University
Emory University
Washington University in St. Louis
UC Davis
University of Florida
USC
Georgia Tech
NYU
UC Santa Barbara
University of Illinois Urbana-Champaign
Boston College
Rutgers University
Tufts University
University of Washington
University of Maryland
Boston University
The Ohio State University
Purdue University
Texas A&M University
Wake Forest University
From tabs to evidence

Stop searching for names. Start building an evidence trail.

PhdFit turns the work you already do—reading résumés, papers, lab pages, and recruiting signals—into one explainable workflow.

Current recruiting signals, not stale directories
Paper-level reasons behind every recommendation
One evidence trail from shortlist to outreach
Sample analysis

Traditional search

Forty tabs. No memory.

2h 18m
01Google "trustworthy AI professors"
02Open 40 faculty pages
03Guess who is accepting students
04Send a generic cold email

Agent-assisted discovery

One professor. Every reason visible.

23 sources checked
SC

Dr. Sarah Chen

Strong fit

Stanford University · Trustworthy NLP

Research overlap94

Recent papers align with trustworthy NLP

Methods fit91

Calibration and fairness evaluation

Recruiting signal86

1 PhD position published this cycle

Evidence grounded in recent papers, a current lab page, and this cycle's recruiting note.

Ready to shortlist, compare, or draft outreach
How the agents help

Six specialists. One shared understanding of you.

Each agent owns a real step in the Workspace, while the full team keeps your evidence, shortlist, outreach, and meeting context connected.

Current mission

Build Alex's trustworthy AI shortlist

Profile14 signals
Faculty corpus847 ranked
Evidence23 sources
Shortlist5 candidates
Shared agent memory

Sarah's paper evidence now powers both outreach and meeting prep.

Agent control room

Agent control room

Evidence pipeline · all context synchronized

Juno finishing meeting brief

Axel · Candidate Analyst

01

Profile signals extracted

Nova · Professor Researcher

02

24 professors researched

Echo · Match Explainer

03

Five-axis evidence ready

Atlas · Strategy Advisor

04

Reach / target / safer balanced

Lyra · Outreach Writer

05

Paper-grounded draft prepared

Juno · Meeting Prep Compiler

06

Meeting brief compiled

One shared evidence graphcontext synced
How it works

One score is a black box. Five axes is a conversation.

PhdFit doesn't hand you an opaque fit number. Every faculty match is ranked across five readable axes — so you can see where the fit is strong, where it's soft, and where to push back.

Fit evidence lab

The short version

4 steps · ~60s
1
Signals from your CV

The Candidate Analyst reads your résumé and extracts research interests, methods, publications, and trajectory.

2
Faculty profile corpus

The Professor Researcher indexes 40k+ faculty pages, recent papers, and recruiting signals.

3
Five-axis scoring

Each candidate is scored on topic, method, trajectory, open seats, and certainty — not one number, five.

4
Explained ranking

The Match Explainer writes the reasoning chain for every match so you can argue with it in chat and re-rank.

The five axes — click to inspect

01 / 05
Axis 01
Topic fit
What it answers

Does the professor work on the problems you want to work on?

Signals used

Paper abstracts and keywords for the last three years, matched against the interests parsed from your résumé plus anything you tell the agent in chat.

Presets — switch the weighting in one click

Balanced

Default — even weights across axes.

Research-fit

When you know your exact area and care most about topic & method overlap.

Methods-match

When you'd rather learn a new topic with tools you already own.

Practical-fit

When you're optimising for open seats and recruitment likelihood.

One connected workflow

Your advisor-fit pipeline keeps moving after the shortlist.

Compare professors, draft outreach, rehearse the interview, and walk into the meeting with the same evidence—not four disconnected tools.

Open your workspace One workspace · every stage
Advisor-fit pipeline

Advisor-fit pipeline

Alex's Fall 2027 search

72% ready

Profile

Résumé + preferences

Professors

Ranked with paper evidence

Shortlist

Reach / target / safer

Outreach

READY TO REVIEW

Personalized draft ready

Prep

Interview + meeting context

Outreach workspace

Dr. Sarah Chen

Target · Stanford University

Evidence attached

Personalized email draft

Calibrated explanations and trustworthy NLP

v2 · saved

Dear Professor Chen,

Your recent work on calibrated explanations connects directly to my fairness-audit research and the evaluation gap I found…

Recent paper citedProfile signal usedSpecific question

Interview prep

6 tailored questions + mock response scoring

Meeting prep

Papers, talking points, risks, and next steps

PhdFit Pro

Unlock the full advisor-fit workflow.

Move from basic discovery to unlimited matching, professor research, outreach drafts, and meeting prep. Pick the runway that matches your application timeline.

Application Season Pass

Recommended

One application season. One payment. No renewal to manage.

$269.91/9 months paid monthly
$169one-timeSave 37%
Save $100.91 vs monthly
  • 9 months starting on your purchase date, through the application journey
  • Unlimited matching, professor research, and fit explanations
  • Full outreach history, interview and meeting prep, and exports
Open your workspace

Monthly Plan

Recommended for active PhD applicants.

$39.99/month
$29.99/monthSave 25%
You save $10.00/mo
  • Unlimited matching and professor research runs
  • Outreach Writer with version history
  • Meeting prep sheets for shortlisted professors
Open your workspace

Weekly Plan

Short sprint access when you need a focused push.

$19.99/week
$14.99/weekSave 25%
You save $5.00/week
  • Full agent access for 7 days
  • Unlimited matching during the active week
  • Good for validating a shortlist before deadlines
Open your workspace

Compare access

Free is the starting access level, not a fourth purchasable plan.

FeatureFreeWeeklyMonthlySeason Pass
AI resume and profile analysisBasicUnlimitedUnlimitedUnlimited
Professor match rankingOne-time personalized Top 3UnlimitedUnlimitedUnlimited
Academic Fit explanationsTop 3 summaryFullFullFull
Research Scout signalsNot includedIncludedIncludedIncluded
Outreach WriterNot includedDrafts + historyDrafts + historyDrafts + history
Meeting prep sheetsNot includedUnlimitedUnlimitedUnlimited
Shortlist exportNot includedCSV + notesCSV + notesCSV + notes
Application trackingManualManual + AI actionsManual + AI actionsManual + AI actions
Applicant reviewsFictional composites

Review previews from common applicant journeys.

Fictional composite profiles shown for layout preview. Replace them with verified, authorized testimonials before launch.

1 / 20
Fictional sample
The fit breakdown helped me separate labs that shared my keywords from labs that actually matched the methods I want to use.
Maya R.
Prospective PhD · Computational Biology
Fictional sample
I stopped treating every highly ranked program as an equal target and built a shortlist I could explain to my recommenders.
Ethan W.
Prospective PhD · Machine Learning
Fictional sample
The paper evidence made it much easier to write specific outreach instead of sending another generic introduction.
Olivia B.
Prospective PhD · Human-Computer Interaction
Fictional sample
I could compare research direction, lab activity, and competitiveness without losing my notes across a dozen tabs.
Liam T.
Prospective PhD · Biomedical Engineering
Fictional sample
PhdFit gave my advisor search a repeatable process and showed me where my profile needed stronger evidence.
Sofia M.
Prospective PhD · Neuroscience
Fictional sample
The match axes caught a methods mismatch I had missed and surfaced two labs that were much closer to my actual work.
Noah K.
Prospective PhD · Robotics
Fictional sample
I finally had one place to connect faculty research, my shortlist, and the next outreach action I needed to take.
Ava C.
Prospective PhD · Public Health
Fictional sample
The comparison view made tradeoffs visible instead of letting prestige dominate every decision on my school list.
Jackson H.
Prospective PhD · Economics
Fictional sample
Meeting prep turned scattered reading notes into a concise set of questions that sounded like my own research interests.
Isabella P.
Prospective PhD · Cognitive Science
Fictional sample
I used the recent-paper summaries to check whether a professor's current direction still matched the lab description.
Lucas D.
Prospective PhD · Materials Science
Fictional sample
The workflow kept me focused on research alignment and mentoring context instead of collecting an endless list of names.
Amelia S.
Prospective PhD · Education Policy
Fictional sample
It helped me explain why each professor belonged on my shortlist, which made feedback from my mentors much more useful.
Benjamin L.
Prospective PhD · Computer Vision
Fictional sample
I could see which faculty matched both my topic and fieldwork approach, not just one phrase from my statement.
Harper N.
Prospective PhD · Environmental Science
Fictional sample
The structured shortlist made weekly application planning feel manageable, especially when priorities changed.
Henry G.
Prospective PhD · Chemical Engineering
Fictional sample
Research Scout gave me a faster starting point for reading, while the evidence links kept the final judgment in my hands.
Evelyn A.
Prospective PhD · Political Science
Fictional sample
The match explanation showed exactly where my background was strong and where I was making an assumption without evidence.
Samuel J.
Prospective PhD · Applied Mathematics
Fictional sample
I replaced a broad spreadsheet with a smaller, defensible set of labs and a clear reason for contacting each one.
Camila F.
Prospective PhD · Bioinformatics
Fictional sample
The profile analysis helped me translate interdisciplinary experience into signals that were easier to compare across departments.
Daniel V.
Prospective PhD · Sociology
Fictional sample
I liked being able to move from a promising match to papers, notes, and meeting questions without rebuilding the context.
Grace O.
Prospective PhD · Mechanical Engineering
Fictional sample
PhdFit made the search less about finding more professors and more about making better decisions with the evidence I had.
Matthew E.
Prospective PhD · Information Science