Talent Acquisition
AI Candidate Sourcing
Finds and summarizes candidates who match the role profile.
Talent Acquisition
AI Resume Screening for Recruitment
Applications for every client role are extracted and scored against that role's brief, giving consultants a ranked shortlist to check.
Agency consultants lose hours to CVs that were never a fit, while strong candidates for a client role sit unread. This edition reads every application against the right client brief, pulls out the details you care about, such as notice period and right to work, and ranks candidates for the consultant to check. Clients see better shortlists sooner, and your team keeps every placement decision.
- Each client role scored against its own must-have criteria
- Notice period and right-to-work details pulled from every CV
- Consultants check a ranked shortlist instead of a full inbox
$4,900
20–30 working days
Optional maintenance $249/mo
What it is
AI Resume Screening for Recruitment reads the applications your agency receives for each client role, extracts the fields you define and scores them against that role's criteria, then queues a ranked shortlist for a consultant to approve. It never decides who is hired.
Why businesses buy it
In recruitment, speed to a strong shortlist decides who wins the placement. When consultants screen CVs by hand across many client roles, the best candidates are often contacted after a competitor has already called them. This edition handles the reading and first-pass scoring for permanent and contract roles, using each client's own brief, so consultants spend their time on calls and client conversations. The written scope sets out the intake route, systems, document types and fields up front, so the agency knows exactly what it is buying before committing.
Problems this solves
Consultants lose whole days screening applicants for each client role
Applications for each client role are read, the fields you define are extracted, and each applicant is scored against that role's criteria. Consultants start from a ranked shortlist instead of an inbox.
Each consultant screens a client's brief their own way
The recruitment role criteria library gives every client role a written set of criteria. Applicants are scored against it, so the agency screens consistently whoever owns the vacancy.
Strong applicants sit unread while a client is waiting
Screening runs as applications arrive in your inbox or upload folder. The shortlist is queued for a consultant to approve, so the client can see candidates sooner.
Clients query why a candidate was or was not put forward
Each score is tied to the role's criteria and the fields extracted from the application. Consultants can show the reasoning behind a shortlist, and the tool never decides who is hired.
A good fit if
Consultants read every CV by hand across several open client roles, and response times slip.
Each client brief has its own must-haves, and you want applicants scored against that brief, not a generic profile.
Candidates and roles live in an ATS such as Bullhorn, Greenhouse or Workable that can receive the shortlist.
You want borderline applicants checked by a consultant instead of being dropped automatically.
Not the right fit if
Candidates who stopped replying are your bigger problem. See AI Follow-Up Engine for Recruitment.
You need candidates found and approached, not inbound applications screened. See AI Candidate Sourcing.
You need interview slots booked once a consultant approves a shortlist. See AI Interview Scheduling.
You want sourcing, screening, scheduling and job descriptions together. See the AI Recruitment Stack, built on the core products.
How it works
- Applications arrive through one route: the inbox or upload folder your agency already uses for a role.
- You choose up to three document types, such as CVs, cover letters and candidate forms, and up to 25 fields each, for example notice period or years in a sector.
- Each application is scored against the client brief and your validation rules, using the candidate screening workflow from the Recruitment template.
- Low-confidence results go to the consultant you name, who reviews them rather than seeing them rejected.
- The ranked shortlist, with the extracted fields behind each score, is sent to your ATS for the consultant to act on.
- Before launch, 100 of your sample documents are processed and you get an accuracy report.
What you provide within 72 hours
Your portal lists these the moment you order. Delivery starts the working day after everything is in and your access is checked.
- At least 20 real sample CVs or applications per document type, redacted if you prefer.
- The fields to extract and your validation rules, per client role or role family.
- Role descriptions and evaluation criteria from current client briefs.
- Your recruitment policies and screening guidance for consultants.
- Access to your ATS as the destination for shortlists.
- The consultant who reviews low-confidence applications.
- One decision-maker who approves the criteria and field list.
- An API key for your own AI model account (for example OpenAI or Google Gemini), created for this build with a spending limit.
The 72-hour rule. Send everything on your checklist, including access, within 72 hours of ordering so your build starts on time.
Timeline
Start
Intake verified, fields and client-role criteria agreed.
Weeks 1–2
Extraction and scoring trained on your sample CVs.
Week 3
Intake route and ATS destination connected, review queue configured.
Weeks 3–4
100 sample documents processed, accuracy report sent.
Week 4
Two rounds of changes to fields and criteria.
Go-live
Live for new applications, recorded handoff, 30 days of support.
| Option | Delivery time | Price |
|---|---|---|
| Standard | 20–30 working days | $4,900 |
| Express | 15–25 working days | $5,750 |
| Rush | 10–20 working days | $6,600 |
What you receive at handover
- AI Resume Screening for Recruitment running on one intake route (email inbox or upload folder)
- Recruitment role criteria library and screening templates for client roles
- Extraction for up to three document types, with validation rules and a consultant review queue
- Connection to your agreed source and destination systems
- Test report using recruitment scenarios, with an accuracy report from 100 sample documents
- Admin guide, recorded handoff session and 30 days of post-launch support
Expected benefits and how to measure them
- Can free consultant time for client and candidate conversations
- Helps the agency send shortlists to clients sooner
- Makes screening consistent across consultants and clients
- Time from brief to first shortlist sent
- From your recruitment system, compare the average time from job registration to first shortlist for roles before and after launch.
- Submission-to-interview ratio
- Track how many submitted candidates clients agree to interview, comparing the quarter before launch with the quarter after.
- Screening hours per vacancy
- Have consultants log screening time for a sample of vacancies before launch and a similar sample after.
Before you start: For a handful of recent client roles, record applications received, screening hours and how long the first shortlist took. Note each role's interview ratio.
These are things to track, not promised results. Outcomes depend on your data, your team and your market.
Running costs
You pay for the build once. Running it costs roughly $30 to $200 a month, depending on page volume, for OCR and AI usage plus storage, all in your own accounts. An agency processing many long CVs each week sits toward the top of that range.
Usage during build and testing is billed to your accounts as well.
Ask about running costsCustom requirements
A fourth document type, more than 25 fields per type, or a second intake route for another office can be quoted. Add a note at checkout for a written Change Quote.
Request a custom versionKeep it running
Monthly maintenance covers monitoring, fixes and a monthly allowance of change hours, enough to load criteria for new client roles.
$249/mo (the minimum fee, includes 2 change hours)
Optional. Starts after the post-launch support period. Cancel any month.
How maintenance worksHow this compares
| Do it yourself with a SaaS tool | Hire a custom agency | Upmark Labs | |
|---|---|---|---|
| Price | An ATS screening add-on bills per recruiter seat or per role | A screening outsourcer charges per role | Ours is one fixed price, shown on this page before you buy |
| Criteria | A generic match score for every role | Depends on the screener | Ours scores against each client brief you supply |
| Decisions | Some tools reject below a cut-off | An outsourced screener decides alone | Ours queues borderline candidates for a consultant |
| Delivery | Quick sign-up, then criteria to configure per role | Set per contract | Ours has a fixed delivery time shown before you buy, with faster options |
Questions about this product
Can AI Resume Screening for Recruitment use different criteria for each client?
Yes. Criteria come from the role descriptions and evaluation criteria you provide, so two clients hiring for similar titles can be scored against different must-haves. New client roles are added by loading their criteria, which fits inside the monthly change hours of maintenance rather than needing a new build.
Does AI Resume Screening for Recruitment send shortlists into Bullhorn?
Yes, if Bullhorn is your destination and you provide the access. The scope covers two connected systems, a source and a destination, so a typical pairing is your application inbox feeding an ATS such as Bullhorn, Greenhouse or Workable. A third system is quoted separately.
Will AI Resume Screening for Recruitment reject candidates on its own?
No. It scores and ranks, and anything it is unsure about is queued for the consultant you name. Final hiring decisions stay with your team and your clients, as the Scope Card states. That limit is part of the product, not a setting that can be switched off.
How is the Recruitment edition different from the core AI Resume Screening?
It keeps the core screening engine and adds an agency setup: criteria held per client role, permanent and contract roles, and fields such as notice period and right-to-work status checked against your rules. Examples and wording are tuned to agency job briefs and candidate CVs. The scope limits are otherwise the same: one intake route, two systems, three document types and 25 fields each.
How quickly can AI Resume Screening for Recruitment screen live applications?
Live screening starts on the delivery date shown in the delivery panel on this page, counted from the day your intake is complete and access is verified. Your sample CVs and field list are due within 72 hours of ordering, and each late day adds 3 working days. Once it is live, each new application is scored as soon as it reaches your intake route.
Can we redact the sample CVs we send for AI Resume Screening for Recruitment?
Yes. Sample documents can be redacted before you send them, as long as the fields you want extracted remain readable. You need at least 20 per document type. For live screening, the PII Redaction Layer and Data Retention and Deletion Configuration add-ons are available if your policies need them.
Who handles hiring-law duties for AI Resume Screening for Recruitment?
Your company does, as the employer. A person on your team makes every advance or reject decision. The AI score is stored next to it in your connected system. Duties under laws such as New York City Local Law 144 or the EU AI Act stay with you. These include bias audits, candidate notices and risk assessments. This page is not legal advice.
Hand consultants a shortlist, not an inbox.
Order AI Resume Screening for Recruitment and every client role's applications are scored against its own brief, ready for consultant review on a fixed delivery date.
Works well with
Talent Acquisition
AI Job Description Generator
Writes inclusive, structured job descriptions from role notes.