Skip to main content

Screen Resumes and Score Candidates With AI

By the end of this recipe, every candidate on your hiring board carries a score, a short list of strengths and gaps, and a shortlist recommendation — measured against the same role scorecard, so you walk into screening with a ranked list instead of a folder of resumes. Resume screening is a read-and-narrate job: someone has to read each candidate against the role's must-haves and turn a stack of applications into a ranked shortlist. Because your candidates, the role scorecard, and your calendar all live in one workspace, Copera AI can read across them and do that first pass for you.

Readiness: Available now — ask Copera AI on demand to score and rank every candidate against the role, backed by an optional automation that screens each new applicant the moment they apply. A named teammate that screens your whole pipeline on its own schedule is rolling out in early access.

What it does​

Resume screening answers one question, over and over: of everyone who applied, who's worth a call? The information is already there — it's just spread across a stack of resumes and application answers. This recipe pulls it into one place and scores it, and it works in two layers:

  1. A ranked, scored read (Ask Copera AI). On demand, Copera AI reads every candidate on your hiring board and your role scorecard, scores each one against the must-haves you defined, and writes the score, a couple of strengths, the gaps, and a Shortlist / Maybe / Pass recommendation back onto each row. Then it posts a ranked shortlist to your hiring channel — the top candidates first, each with a one-line reason. This is the primary path: only a read across the whole pool can rank it.

  2. An optional intake screener (Automation). A small automation scores each applicant the moment they apply — extracting their details from the application form, scoring that text against the role criteria, writing a first-pass score onto their row, and pinging the recruiter when someone looks like a strong fit. So a fresh score is already waiting before anyone opens the board.

The score is a first pass, never a verdict. It ranks and explains; a person still reads the shortlist and decides who advances. Everything stays internal — scores land on your hiring board and a summary goes to your team's channel. Nothing is ever sent to a candidate.

Build it yourself​

The ranked read — scoring every candidate against the role and ordering the shortlist — is a read-and-narrate task, and the fastest way to produce it is to ask Copera AI (next section). What you build here is the layer beneath it: a board that holds each candidate's content, a scorecard the AI scores against, and an optional automation that screens applicants as they arrive. Get this right and every score Copera AI writes is grounded in the same rubric and fresh data.

One-time setup​

Build your hiring board

Give each candidate one row on a Candidates board with the columns a screen needs to read and fill: Candidate (text), Role (link or select), Resume / experience (long text — the content the AI actually scores), and Resume file (an attachment for the original document). Then add the empty scoring columns Copera AI will write back into: Score (number), Fit (a status such as Strong fit, Possible, Not a fit), Strengths and Gaps (long text), and Shortlist (a status such as Shortlist, Maybe, Pass). New to columns? See Boards Overview.

Write the role scorecard

Create a short role scorecard as a Copera document: the must-haves (required skills, years of experience, qualifications), the nice-to-haves, any deal-breakers, and how you weight them. This is the single rubric every candidate is measured against — write it once, and both the automation and Ask Copera AI score from it. Copera AI reads your documents, so keeping the scorecard as a doc means you tune the bar in one place.

Get each resume's content onto the row

Ask Copera AI reads Copera boards and documents, so each candidate's experience needs to live as text on the row for it to be scored. The cleanest way is an application form whose answers write straight to a new candidate row (skills, years, location, links, and a paste of their resume). You can also paste a resume's text into the Resume / experience column by hand, or save it as a linked Copera document. The original file can stay in the Resume file attachment or in Drive for a person to open — the AI scores the captured text, not the file.

Optional automation — screen each applicant on intake​

This automation gives every new applicant a first-pass score the moment they apply, so no resume sits unread.

Trigger: Form submitted

Publish your job application form and add an automation with a Form submitted trigger, so every application starts the flow and lands as a candidate row.

AI step: Extract the details

Add an AI → Extract step that pulls the structured facts out of the application text — skills, years of experience, location, and links — into fields you can compare consistently across candidates.

AI step: Score against the role

Add an AI → Classify step (or AI → Generate) that scores the captured text against the role criteria you write into its prompt — the same must-haves as your scorecard. Have it return a Fit label (Strong fit / Possible / Not a fit) and a one-line reason. It scores the details on the form, one applicant at a time.

Action: Write the score onto the row

Add a Set field action that writes the Fit, the Score, and the one-line reason onto the candidate's row. The board now carries a first-pass read without anyone typing it in.

Condition + notify: flag the strong fits

Add a condition that continues only when Fit equals Strong fit, and on the true path a Send direct message (or Send notification) to the recruiter. Strong candidates get a look while they're still warm; the rest wait quietly in the queue for the full ranked read.

One applicant at a time

This automation scores each applicant as they apply, from the text on their form — it can't open a resume file, and it can't read across every candidate to rank them against one another. Ranking the whole pool is a read-across job, which is exactly what Ask Copera AI does next. Everything above uses documented Automation blocks; see the full list in Automations.

Or just ask Copera AI​

This is the primary path to the ranked shortlist, and the one we recommend — because it reads across your board and scorecard in one pass, Ask Copera AI can do what no single automation can: score and rank every candidate at once. Open Ask Copera AI and describe it in plain English:

"Read the Candidates board for the Senior Backend Engineer role and the role scorecard document. Score each candidate 1 to 5 against the must-haves in the scorecard. Write each candidate's Score, two Strengths, their biggest Gaps, and a Shortlist status (Shortlist, Maybe, or Pass) back onto their row, with a one-line reason. Then post a ranked shortlist to the #hiring channel — the Shortlist candidates first, each with their score and top reason."

Ask Copera AI reads and searches your workspace data, so it opens the board and the scorecard document, reasons about each candidate against the rubric you gave it, and drafts the scores. Then it updates the rows — writing the score, strengths, gaps, and shortlist status onto each candidate — and posts a channel message to #hiring. With the default Ask before acting permission mode, it shows you a review card before each write and before the post, with a Sources list so you can see exactly which rows and which part of the scorecard it drew from. It only ever reads candidates and posts to channels your own account can already reach. See the full capability list in What Copera AI Can Do.

A few useful variations of the same ask:

  • Score against each requirement. Add "…and break down each candidate's score requirement by requirement, so I can see who's strong on system design but light on the on-call experience." You get a per-criterion read, not just one number.
  • Calibrate the bar first. Add "…before you score, research what a strong background for this role typically looks like, and tell me the two or three signals that matter most." Copera AI can research the role, then apply the same bar to everyone.
  • Keep it private first. Swap "post it in #hiring" for "DM the shortlist to me" to get a personal read before anything is written back or shared with the panel.
  • Turn the shortlist into interviews. Add "…then check my calendar and suggest three interview slots this week for the top two candidates." Copera AI can read your schedule and schedule the meetings for your review.
  • Drill in. After it runs, ask "Why did you pass on this candidate?" — it's already looking at the same rows and will explain the score from the resume content and the scorecard.

To get this on a rhythm, just ask at the end of each application window — dictate it hands-free with Bankai voice if you're heads-down — or save the prompt and reuse it for the next role. For a version that runs entirely on its own, see the next section.

Make it a standing teammate​

Early access

AI teammates are rolling out gradually. If you don't see them in your workspace yet, they're on the way — everything in this guide can be built today as an Automation plus an on-demand ask to Copera AI.

When one is available, you can put a named teammate — a "Recruiting Screener" — in charge of this whole recipe. On its own schedule and under its own identity, it reads your candidates board (and the scorecard you point it at), scores each new applicant against the role, writes the score and shortlist status back to each row, and posts the ranked shortlist to your hiring channel — no one has to ask. A teammate's read tools are always on, and writing rows and posting to channels are opt-in per agent; it can't delete data or send anything outside your workspace, so the screening stays a safe, internal briefing that never reaches a candidate. Until then, the automation above plus the on-demand ask do the same job today. Learn more in AI Teammates.

Tips​

tip

Keep a human in the loop, and score only what matters for the job. The score is a first pass that ranks and explains — a person still reads the shortlist and decides who advances. Point the scorecard at job-relevant criteria (skills, experience, qualifications) and review the writeback before anyone is passed over. Used this way, the AI saves you the first read; it doesn't make the call.

tip

Write the scorecard once, and reuse it everywhere. The quality of the score is the quality of your rubric. Spell out the must-haves, nice-to-haves, and deal-breakers in the scorecard document, then put the same criteria in your automation's AI prompt and your Ask Copera AI request. One definition applied to everyone is what keeps scores comparable across candidates.

tip

Structure the intake so scoring stays fair. An application form with consistent fields — years of experience, key skills, location, links — gives every candidate the same shape of input, so the score reflects the role and not who wrote the more polished paragraph. Consistent inputs make consistent scores.

tip

Review the writeback, then trust it. Keep the default Ask before acting mode so you see each score on a review card before it lands on a candidate. After a couple of clean runs you'll know what to expect — and you can always have it DM the shortlist to you first for a private read before it posts to the panel's channel.

Frequently Asked Questions​

Can Copera AI screen resumes and score candidates?​

Yes. Ask Copera AI reads every candidate on your hiring board and your role scorecard, scores each one against the must-haves you defined, and writes the score, strengths, gaps, and a shortlist recommendation back onto each row. It runs on demand and, by default, shows every change on a review card before it writes anything. It screens against the resume content you keep in your workspace as text, not by opening a file on its own.

Does the AI decide who to hire or reject candidates on its own?​

No. The scorer is a first-pass assist that ranks and explains, not a decision-maker. It writes scores to your internal hiring board and posts a shortlist to your internal channel; it never contacts a candidate. A person reviews the scores and decides who advances. Keep a human in the loop and score only against job-relevant criteria.

Where do resumes need to live for Copera AI to read them?​

Ask Copera AI reads your Copera boards and documents, so each candidate's resume content needs to live as text on the hiring board — captured through an application form, pasted into a long-text column, or saved as a linked Copera document. The original resume file can stay attached to the row or in Drive for a person to open.

Can it rank the whole pool at once, or one applicant at a time?​

Both, and they complement each other. Ask Copera AI reads across every candidate on the board in a single pass and returns a ranked shortlist. An Automation scores each applicant individually the moment they apply, so a fresh score is waiting before anyone opens the board. Use the automation for intake and Ask Copera AI for the ranked read.

Is candidate data used to train AI?​

No. Your workspace content is used only to answer what you asked, never to train models. Ask Copera AI also acts as you and within your permissions, so it only reads the candidates and posts to the channels your own account can already access.