Screen new Lever applicants against the role they applied for

Every new application gets checked against the job requirements, scored, and written back onto the candidate profile in Lever, with strong fits flagged in Slack.

Agentic Task
LeverSlack BotHR & PeopleDocument ProcessingNotifications & Alerts
PromptCreate

When a new application is created in Lever, screen the applicant against the role they applied for and write the assessment straight back onto their candidate profile. Trigger this with a Lever webhook on the application created event. The webhook payload identifies the opportunity (the candidate profile) behind the new application.

Start by gathering the facts. Use Retrieve Opportunity with the contact expanded to get the applicant's name, email, and profile link, and to identify which posting they applied to. Use Retrieve Posting to pull that role's description and requirements. If either the posting or the opportunity is confidential, stop immediately: read nothing further, write no note, and send no Slack message. Confidential records are out of scope for this workflow.

Then read the resume. Use List Resumes on an Opportunity to find what the applicant attached, and Retrieve a Resume on the most recent one to read its parsed data, which holds their positions, employers, dates, education, and schools. If no resume is attached, do not guess and do not fall back on the job title alone: write a note saying no resume was attached so no assessment could be made, and stop there without sending a Slack message.

Now judge the fit. Pull the must-have requirements out of the posting description and check each one against the parsed resume. A requirement counts as met only when something in the resume actually evidences it. If the resume is silent or ambiguous on a requirement, it is unclear, not met. Do not infer seniority, scope, or skill from job titles, company names, or school prestige.

Write the result to the candidate with Create Note on an Opportunity. Structure the note in four parts: the must-have requirements clearly met, each with the specific resume detail that supports it; the requirements missing or unclear; a fit score from one to five; and a two-line recommendation for the recruiter. Keep it factual and neutral, since the whole hiring team reads these notes. Before writing, check the existing notes on the opportunity and skip writing if this workflow has already left a screening note there, so a replayed webhook never produces duplicates.

Only when the fit score is four or five, post a short alert to the recruiting channel with Slack Bot Send a Message. Include the candidate's name, the role title, the score, one line on why they stand out, and a link to their Lever profile. Keep it to a few lines so it scans in the channel. Scores of three or below get the Lever note only and no Slack message, so the channel stays a signal for strong applicants rather than a firehose.

Guardrails that matter. Never advance a candidate to another stage, never reject anyone, and never archive an opportunity. This workflow reads, writes one note, and optionally sends one Slack message, and nothing else. Every claim in the note must be grounded in what the resume actually says rather than what it implies. And skip confidential postings entirely rather than partially processing them.

What does this prompt do?

  • Starts the moment a new application lands in Lever, then reads the applicant's resume and compares it against the requirements on the job posting they applied for.
  • Writes a structured note onto the candidate profile in Lever covering which must-have requirements are clearly met, which are missing or unclear, a fit score from one to five, and a two-line recommendation.
  • Posts a short alert to your recruiting channel in Slack only when someone scores four or five, so strong applicants get seen within minutes instead of at the next pipeline review.
  • Never advances, rejects, or archives anyone, skips confidential roles entirely, and grounds every claim in what the resume actually says.

What do I need to use this?

  • A Lever account with permission to read job postings and candidate profiles and to add notes to them.
  • A Slack workspace and the recruiting channel where you want strong applicants flagged.
  • Job postings in Lever whose descriptions spell out the must-have requirements. The clearer the requirements are written, the sharper the scoring gets.

How can I customize it?

  • Move the alert threshold. Flag at three and above if you want more volume across the team, or reserve Slack for fives only.
  • Send alerts to different channels for different teams or seniority levels, or to a hiring manager's direct message instead.
  • Change what the note covers, for example adding a location or work eligibility check, or asking for a longer recommendation on senior roles.

FAQs

Will this move candidates through the pipeline on its own?
No. It only writes a note on the candidate profile and, for strong applicants, posts a Slack alert. Advancing, rejecting, and archiving stay entirely with your recruiters.
What happens with confidential roles?
They are skipped completely. If the posting or the candidate is marked confidential in Lever, nothing is read, no note is written, and no Slack message goes out.
What if the applicant did not attach a resume?
The note says so plainly and no score is invented. Nothing gets posted to Slack, so a missing resume never looks like a weak candidate.
How quickly does the assessment appear?
It runs as soon as the application arrives in Lever, so the note is usually sitting on the candidate profile within a minute or two of them hitting submit.
Does it guess seniority from job titles?
Deliberately not. It only credits requirements the resume actually evidences, and marks anything it cannot verify as unclear, so you do not get inflated assessments.
Can we still use our own scorecards and interview feedback?
Yes. This adds a screening note at the very top of the funnel and leaves your existing stages, scorecards, and feedback forms untouched.

Related templates

Build a credential rotation checklist when someone leaves

When someone leaves, we check which shared passwords they used in their final months and post a ranked rotation list to your security channel.

1Password
Rippling
Slack Bot
+1
Agentic Task
Weekly Amazon S3 bucket security audit posted to Slack

Every Monday, check every S3 bucket for public exposure, missing encryption and weak backup settings, then get the risks ranked in Slack.

Amazon S3
Slack Bot
Google Sheets
Agentic Task
Log Agorapulse social conversations to HubSpot contacts

Twice every weekday, the conversations from your social inbox land on the right HubSpot contact timelines, with a Slack recap for sales.

Agorapulse
HubSpot
Slack Bot
Agentic Task
Clean up HubSpot contacts from your Amazon SES suppression list

Every morning, find the addresses that hard bounced or filed a spam complaint, update the matching HubSpot contacts, and post a short Slack recap.

Amazon SES
HubSpot
Slack Bot
Agentic Task
Draft polite follow-ups for emails that never got a reply

Every weekday at 4pm, spot the threads that went quiet, stage a ready-to-send nudge in your mailbox, and get a ranked Slack recap.

Aurinko
Google Sheets
Slack Bot
Agentic Task
Replay failed SQS messages when a bug fix is merged

When you merge a fix in GitHub, this agent checks the matching dead-letter queue, replays the failed messages, and reports back on the pull request and in Slack.

Amazon SQS
GitHub
Slack Bot
Agentic Task

Stop reading every resume by hand.

Let every new Lever application arrive pre-screened, scored, and written up on the candidate profile before a recruiter even opens it.