Screen and score every CV with Mistral OCR and Google Gemini

Reads incoming CVs, scores each candidate against your job description, and sends the right email automatically.

How the work actually flows

It branches. Exactly one path is taken.

Pattern: Exclusive Choice (4) · Simple Merge (5)

flowchart TD trig>"cv email received"]:::trig s0["extract text from cv"]:::task s1["score against job description"]:::task s2["send email to candidate"]:::task s3(("hr receives summary")):::human trig --> s0 s0 --> s1 s2 --> s3 gx{"× candidate shortlisted or not"}:::gate s1 --> gx p00["send interview invite"]:::task gx -->|"shortlisted"| p00 p10["send polite decline"]:::task gx -->|"not shortlisted"| p10 jn{"○ email sent"}:::gate p00 --> jn p10 --> jn jn --> s2 out[/"candidate scored and emailed"/]:::out pay{{"no candidate left without response"}}:::pay s3 --> out out --> pay classDef task fill:#e7f6fe,stroke:#34b8f0,color:#2c2a29 classDef svc fill:#f6f8fa,stroke:#7c8795,color:#2c2a29 classDef mi fill:#e7f6fe,stroke:#0079a8,color:#2c2a29,stroke-width:2px classDef human fill:#fff,stroke:#0079a8,color:#0079a8 classDef store fill:#f6f8fa,stroke:#0079a8,color:#2c2a29 classDef trig fill:#00a4eb,stroke:#0079a8,color:#fff,font-weight:bold classDef trigtime fill:#00a4eb,stroke:#0079a8,color:#fff,font-weight:bold classDef trigdata fill:#8ad4f5,stroke:#0079a8,color:#06314c,font-weight:bold classDef gate fill:#fff,stroke:#e8a23d,color:#6b4708,font-weight:bold classDef out fill:#1f9d6b,stroke:#167a53,color:#fff,font-weight:bold classDef pay fill:#06314c,stroke:#021f33,color:#fff
Starts itA stepA personOne path onlyPaths rejoinResultPayoff
Build size
Standard

A mid-size build with several tools working together.

Business functions
Email AutomationDocument Processing & OCRHR & Recruiting
Connects
EmailMistral AIGoogle Gemini

The problem it solves

You get flooded with CVs for every open role and don't have hours to read each one carefully. Good candidates sit in your inbox while you get around to replying, and rejections often never go out at all.

Who it fits

HR teams and hiring managers who receive a high volume of CV emails for open roles.

How it works

  1. A new CV arrives by email
  2. The system pulls the text out of the CV, even scanned PDFs
  3. AI compares the candidate against your job description and scores them
  4. Shortlisted candidates get an interview invite and others get a polite decline
  5. HR receives a summary with the CV attached
What you get

Candidates ranked and ready to review

You get every incoming CV automatically scored against your job description, with a clear summary and shortlist ready for your team to review.

What you get

A scored candidate summary in HR's inbox plus the right email sent automatically to the candidate.

What you need

An email inbox, a Mistral AI account, and a Google Gemini API key.

We can build this. But should you?

The hard question is not how to build it. It is whether this is the right thing to build first.

That is what a Fractional Chief AI Officer figures out with you, before anyone writes a line of code.

Let's Talk Strategy

Related automations

Score how well a candidate's resume matches a job posting

Compares a candidate's resume to a job description with AI, then emails them a fit score and improvement tips.

Advanced

Automatically process files from Google Drive, forms, and FTP

Automatically pull in files from Google Drive, FTP, or web forms, then convert, analyze, or extract data from them.

Advanced

Ask questions and get answers from your PDF documents

Reads your PDF documents with AI, stores them for search, and lets you ask questions in plain English.

Advanced

Score and organize job applicant CVs automatically with AI

Collects job applications, has AI score each resume against the job description, and logs everything in a spreadsheet.

Advanced
Back to the AI Playbook