Skip to content
PROBB AI
NewNative MCP: use it in Claude & ChatGPT
Who are you hiring for?

AI resume screening and AI interviews for tech hiringSubmit candidates you can stand behind.

ProBB AI checks each resume against the job, runs a short AI voice interview, and flags what you should look at before the candidate goes to your client.

Try it freeSee a sample report

500 resume reports free · No card needed · Try the AI interview yourself

Built by a former technical screener · Our story

Aarav Mehta

Senior Backend Engineer · Bengaluru

Experience

Paycore · Senior Backend Engineer · 2020–2024

Led the payments API move to Go; p95 latency down 38%

EvidenceOwned it and measured it

Owned on-call and incident reviews for 14 services

EvidenceRan it in production

Finlytics · Staff Engineer · 2019–2021

CheckOverlaps Paycore by a year

Skills

Go · Kafka · PostgreSQL · gRPC · Terraform

Kubernetes, Kubernetes, cloud-native Kubernetes microservices

CheckKeywords with no project

Mixed evidence · 7.4/10Worth a 15-minute AI interview. Ask about the overlap.

Already part of the workflow at

  • SilversonDevelopers
  • omotenashiTechlabs
  • rejolutAI & Web3
  • scalenowMedia

01The problem

AI makes every resume read well.1

A confident answer can still be thin.2

Your senior people pay for it in first-round calls.3

  1. 1Candidates polish every bullet with AI, so keyword overlap stops telling you much.
  2. 2Sounding fluent about a system isn't the same as having built and run it.
  3. 3Usually the engineers you most need on the product.

Why we built it

HR people with technical knowledge are very hard to find.
Arvind Kumar, CEOFormer technical screener for recruitment agenciesLinkedIn (opens in a new tab)Read our story

02How it works

From job post to shortlist in four steps.

You set up the job and invite candidates. ProBB AI screens the resumes, runs a first-round AI interview and writes the candidate report.

01

Add the job

Paste a job description. The JD coach scores it and suggests fixes for vague or missing requirements before you screen anyone.

JD coach

Screening reads only the description text. Suggestions edit it and can be undone.

Could match better

Match readiness 64/100 · AI-reviewed

Requirements 6/10 · Specificity 5/10 · Structure 8/10

Reviewed

Affects matching

  • Make the experience requirement testable

    “Strong backend experience” can’t be checked against a resume. Name the stack and the level.

    Strong backend experience

    4+ years building and running Go or Java services in production

    DismissApply

What screening will look for

MustGo or Java servicesPayment APIsOn-call ownership
NiceCard networks

7 checks passed

Fig. 1 · JD coach · app.probbai.com/job-descriptionsSample · fictional data

02

Drop in the resumes

Upload them in bulk. Each resume is checked against the job's requirements, with the supporting evidence and the gaps listed for every criterion.

Reports

Review your team’s candidate analyses and interviews.

Search candidate, role, email, or job description

Priya Nair

For Senior Backend Engineer

8.4/10Overall evidence

Final

Evidence summary

Owned Go payment services end to end, with a measured, zero-mismatch ledger migration.

Interview

Proceed88% readiness

Proceed to a final conversation about system design trade-offs.

Confirm how on-call scaled as the team grew.

2 hours ago

By Sana Iyer

Review evidence →
Fig. 2 · Reports · app.probbai.com/reportsSample · fictional data

03

Invite to an AI interview

Invite one candidate or a whole shortlist. They take a voice interview of about 15 minutes in their browser, with questions based on their resume and your job.

Try it as a candidate

Interview in progress

Answer naturally from your own experience.

6:42

Speaking

Walk me through how you prevented duplicate charges in the payments API.

Mute End interview
Fig. 3 · Live AI interview · app.probbai.com/interviewSample · fictional data

04

Share the report

You get a report with the transcript, strengths, gaps and follow-up questions, and you choose which parts to share with a client or hiring manager.

Hiring manager debrief

Priya Nair

Senior Backend Engineer

Share
8.4/ 10

Overall evidence

Strong Evidence

Final

Executive Summary

Owned Go payment services end to end with measured results. Interview answers were specific and consistent with the resume.

Fig. 4 · Share dialog · app.probbai.com/reports/priya-nairSample · fictional data

03AI assistants

Native MCP

Your hiring, inside Claude and ChatGPT. Natively.

ProBB AI now speaks MCP. Not a wrapper: a real recruiting MCP server. Ask your AI assistant about your candidates and jobs, and let it take the routine steps while you stay in charge.

Works with Claude, ChatGPT, Cursor and any assistant that supports custom MCP connectors.

  • 15 hiring tools. Find candidates, shortlist, compare, read interview evidence, record decisions, save jobs and more.

  • Anything that costs credits asks first. You see the cost and say yes, every time. Standing approvals don't count.

  • Ignores instructions hidden in resumes. Text in resumes and transcripts is treated as data, never followed. Contact details stay out unless you ask.

  • In the official MCP Registry. Listed as com.probbai/probb. Included in every plan, with admin controls to switch assistants off.

Connect in three steps

  1. 01

    Copy one address

    From Settings → AI assistants.

  2. 02

    Add it as a connector

    In Claude, ChatGPT, Cursor or similar, then sign in.

  3. 03

    Choose permissions

    Reading is always on. Saving changes and spending credits can be switched off.

Try it freeRead the setup guide
Your AI assistantProBB connected

Shortlist the top candidates for Senior Backend Engineer

Here are the strongest candidates for Senior Backend Engineer.

Priya Nair

Owned Go payment services end to end; zero-mismatch ledger migration.

8.4/10Interview completed

Aarav Mehta

Specific Go and payments evidence; two employment dates overlap.

7.4/10Interview pending

Invite Priya Nair to an AI interview

Inviting Priya Nair to an AI interview uses credits.

AI interview

1 candidate · about 15 minutes

100 credits

$1.00

Waiting for your yes

Fig. · Inside your AI assistant · app.probbai.com/api/mcpSample · fictional data

04Integrity checks

Signals worth a second look.

Integrity checks on the resume and the AI interview note things you may want to check yourself.

Resume signals

Keyword stuffing, hidden text, timeline inconsistencies and claims without supporting detail are noted for review.

Skills

Python · Airflow · dbt · Snowflake · Spark

expert senior staff principal python spark kubernetes ml ai llm

Hidden text possibleKeyword stuffing

Also checked: timeline inconsistency · unsupported claim density · duplicate content · formatting anomaly.

Speaker continuity

If more than one voice seems to be answering during the interview, the report mentions it so you can follow up.

Voice 1

Voice 2

Speaker checkConsistent

Claims that need a follow-up

Answers that may not hold up technically are marked as questionable, with a short, neutral reason.

Interviewer

How did you avoid duplicate payments when consuming from Kafka?

Candidate

Kafka gives exactly-once delivery end to end by default, so duplicates were never a concern for us.

QuestionableExactly-once needs idempotent producers and transactional reads; worth a follow-up question.

Answers that miss the question

Generic or rehearsed answers that don't address the question are noted.

Interviewer

Tell me about a time you pushed back on a technical decision.

Candidate

I'm a strong team player and always focus on delivering value to customers through collaboration and best practices…

Didn't address the question

Integrity checks are advisory and never reject a candidate. A person makes the call.

For your candidates

Fair to the people being interviewed.

Your candidates are your reputation. Here's what the AI interview looks like from their side.

  • Consent comes firstNothing is recorded until the candidate reads the notice and agrees. If they decline, no assessment is created.
  • About 15 minutes, in the browserNo app to install. The interview never runs past 22 minutes, and they can stop at any time.
  • Scored on what they say, not how they say itAccent, grammar, pauses, nervousness and non-native phrasing aren't penalised. Protected characteristics, emotional state, voice stress and voiceprints aren't used to score anyone.
  • A person stays reachableCandidates can ask the recruiter for human review, a reasonable accommodation or an alternative assessment.
Try the interview yourselfRead the candidate guide

AI voice interview

This structured interview targets 15 minutes, may use additional recovery time, and never exceeds 22 minutes.

The conversation will be transcribed and audio recorded for hiring review. The recording is available only to authorized members of the hiring organization.
I have read the notice and consent to recording, transcription and AI-assisted evaluation for this interview.

Read T&C and privacy notice

Start interview
Fig. 5 · Before the interview · app.probbai.com/interviewSample · fictional data

05Candidate report

The report your client or hiring manager reads.

The same layout as the report in the app, shown here with a fictional candidate. Switch tabs to see each part.

  • 01An overall score with the reasoning written out
  • 02Marked final or provisional, so a resume-only score isn't mistaken for a final one
  • 03A short executive summary at the top
  • Share any report with a link you control

Hiring manager debrief

Priya Nair

Senior Backend Engineer

Interview: Completed
Review interview

Candidate context

Extracted identity and resume signals used for this debrief.

priya@example.com 6 years Bengaluru, India Backend Engineering
8.4/ 10

Overall evidence

Strong Evidence

Final

Executive Summary

Priya has owned Go payment services end to end, including a ledger migration with a measured, zero-mismatch cutover. Her interview answers were specific and matched the resume. Explore how she would scale on-call practices as the team grows.

Overall Assessment

Combined resume, JD, and interview evidence

Final

Proceed to a final conversation about system design trade-offs.

8.4/10

Overall evidence

8.1/10

Resume–JD baseline

85%

Interview coverage

82%

Assessment confidence

Fig. 6 · Candidate report · app.probbai.com/reports/priya-nairSample · fictional data

How the resume score is built

Each resume is scored against the job on five criteria, each with written reasoning, the evidence found and the gaps that remain.

  1. 01Role requirements match
  2. 02Technical evidence
  3. 03Experience scope
  4. 04Execution impact
  5. 05Evidence risks

How the interview score is built

Every interview finding cites the answer it came from. Communication is scored leniently: accent and non-native phrasing aren't penalised.

  • Core role skills35%
  • Applied problem solving25%
  • Role and experience fit25%
  • Communication clarity10%
  • Evidence coverage5%

Candidate matching

Your talent pool, matched both ways.

Find the best people for a new req from candidates you've already screened, or the best open roles for someone on your bench.

Match direction
  • Requirements are split into must-have, important and optional
  • Transferable experience is called out, not hidden
  • Shortlist, dismiss or run a full analysis in one click

Matches

Find candidates for a job or jobs for a candidate.

Candidates for a jobJobs for a candidateSaved matches

Job and filters

Senior Data Engineer

214 eligible candidates · Data platform

Find matching candidates
All match levelsAll decisions
#1

Lena Fischer

Report readyStrong potential

Data Engineer

7 of 8 criteria supportedBerlin
Reviewing evidence
#2

Rahul Verma

Possible match

Analytics Engineer

5 of 8 criteria supportedPune
Review evidence
#3

Sofia Marin

Exploratory match

Backend Engineer

4 of 8 criteria supportedLisbon
Review evidence
Fig. 7 · Matches · app.probbai.com/matches/candidatesSample · fictional data

Who it's for

Two ways teams use it.

You

Recruiters & agencies

Screen your candidate bench against each new req, and send clients a report instead of a bare resume.

  • Check the evidence before you submit
  • Share a report with one link
  • Match past candidates to new reqs
Start screening

Hiring for a small team

ProBB AI handles the first pass, so your time goes into the final interviews.

  • The JD coach helps you write a clear job post
  • An AI voice interview takes the first-round call
  • Ready-made questions for your final interview
Make your first hire

Pricing

Start pay-as-you-go. Go monthly as you grow.

Pay-as-you-go needs no seat licence or annual contract. Teams that screen every month can move to a monthly plan.

Rate card · pay-as-you-go

Resume report$0.02
Evidence check against the job, integrity signals and tailored interview questions.
AI interview$1.00
A voice interview of about 15 minutes, with the full transcript and scoring.

Screening 30 resumes and interviewing the top 5 costs $5.60, less than an hour of an engineer's time.

  • $10 in free credits to start
  • 4 seats + unlimited viewers
  • Bulk upload and bulk invite
  • API, webhooks and sandbox on request
  • AI assistant access (MCP) in every plan

Estimate your month

300 resumes
30 interviews

300 × $0.02$6.00

30 × $1.00$30.00

Estimated total

$36.00
Get $10 in free creditsCompare monthly plans

Monthly plans

For agencies and teams with steady volume

A monthly allowance of resume reports and AI interviews, sized to how much you screen.

  • Monthly resume report and interview allowance
  • Seats for everyone on your team who screens
  • Priced on your volume
Talk to sales

Trust

How candidate data is handled.

Compliance

Compliant with GDPR and UK GDPR and India’s DPDP Act.

A Data Processing Agreement is available on request. Request a DPA

  • Every record and file is isolated per organisation
  • Protected characteristics are excluded from evaluation
  • Your data is never used to train AI models
  • Export or delete candidate data at any time
  • A named Data Protection Officer (GDPR) and Grievance Officer (India's DPDP Act)
Read our privacy commitmentsSee our sub-processors

For builders

Connect it to your own tools.

Add jobs and candidates, start reports, invite candidates and read decisions over a REST API. Get a signed webhook for every change, including changes made in the app. Available on request, with a sandbox to test against.

Prefer to work from an AI assistant? The same data is available over a native MCP server, with OAuth sign-in and a confirmation for every action that uses credits.

api.probbai.comSandbox
  1. POST/api/v1/candidates
  2. POST/api/v1/reports
  3. ◆ hookreport.completedsigned
  4. POST/api/v1/interviews
  5. ◆ hookinterview.completedsigned
Read the API docs

FAQ

Common questions.

Something else on your mind? Ask us directly.

Around 15 minutes. Candidates open a link in their browser and talk with a voice interviewer at a time that suits them. There's nothing to install.

They can decline on the consent screen. Nothing is recorded or scored, and they're asked to contact you for an alternative assessment.

Both. Recruiters and staffing agencies screen candidates against each client req and send a report instead of a bare resume. Companies that are short on people use it for resume screening and the first-round interview, so the hiring manager only meets the strongest candidates.

Keyword filters reward whoever copies the job description. ProBB AI checks each resume against the job's requirements and lists the evidence and gaps for every criterion, then a short AI voice interview asks the candidate to explain the work they claim.

Interviews run in English today.

Scores are evidence summaries, not verdicts. Each one comes with the evidence and gaps behind it, interview findings cite the answers they came from, and integrity checks are advisory, so a person reviews before any decision.

No. ProBB AI organises evidence, highlights gaps and suggests follow-up questions. Integrity checks are advisory. A person makes the decision.

Technical roles today: software, data and ML, cloud and infrastructure, security, QA, IT systems, embedded and engineering leadership. Other roles can be screened, but reports are tuned for technical hiring.

It stays in your organisation's workspace, it's never used to train AI models, and you can export or delete it at any time. ProBB AI complies with GDPR, UK GDPR and India's DPDP Act, candidates can exercise their rights through our named Data Protection Officer and Grievance Officer, and a Data Processing Agreement is available on request.

No. Pay-as-you-go uses credits per resume report and per interview, and every new workspace starts with free credits, four seats and unlimited viewers. For steady volume there are monthly plans; talk to us to set one up.

Yes. A REST API lets your software add jobs and candidates, start reports, invite candidates to interviews, and read results and hiring decisions. You get a signed webhook for every change, including changes made in the app, and a sandbox to test against. It is available on request. There are no native ATS integrations yet, so a developer connects it to your system.

Yes. ProBB AI has a native MCP server, so Claude, ChatGPT, Cursor and any assistant that supports custom MCP connectors can read your jobs and candidates, build shortlists and compare people. You connect it by copying one address from Settings → AI assistants and signing in. It's included in every plan at no extra charge, and an admin can switch assistants off for the whole organisation.

Only with your yes, every time. Anything that uses credits, like analysing resumes or inviting a candidate to an AI interview, shows the cost first and waits for you to confirm. A standing approval doesn't count. When you connect, you can also untick spending so the assistant can only read, and viewers' assistants can never do more than read.

Your next shortlist, backed by evidence.

The free credits cover 500 resume reports or 10 AI interviews, so you can try it on a real job first.

Try it freeTalk to us