# Automated candidate screening & response with OpenAI: n8n workflow

> Started by an arriving email, and works across Gmail, Google Sheets and Slack. It puts OpenAI behind a retrieval step, so answers are drawn from documents...

Source: https://millionrounds.com/workflow/automated-candidate-screening-and-response-with-openai (Millionrounds; every figure on the page links to its filing or article)

[Automation library](https://millionrounds.com/workflows) · [Hiring](https://millionrounds.com/workflows?category=Hiring#library)

# Automated candidate screening & response with OpenAI

Started by an arriving email, and works across Gmail, Google Sheets and Slack. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 19 steps, 2 branches: a working afternoon to understand properly.

Medium Calls a model: OpenAI Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fautomated-candidate-screening-and-response-with-openai)

**19 steps** Medium: a working afternoon

**2** Branches: places the flow splits

**0** Loops or waits

**3** Services it connects to

## The flow

Starts it 1 Model 4 Logic 6 Service 8

The steps in the order they run, from what starts it.

- 1 **Trigger: New Candidate Email (Gmail)** Gmail trigger *Starts it*
- 2 **Fetch HR Job Requirements** Google Sheets Tool *Service*
- 3 **Parse AI Output (Structured JSON)** Output Parser Structured *Model*
- 4 **AI Model: GPT-4 Screening Engine** Lm Chat Open Ai *Model*
- 5 **AI Memory: Candidate Context** Memory Buffer Window *Model*
- 6 **Parse Email Metadata** Set *Logic*
- 7 **Check for Resume Attachment** If *Logic*
- 8 **AI Agent: Candidate Evaluator** Agent *Model*
- 9 **Merge Email + Resume Data** Merge *Logic*
- 10 **Upload Resume (Mistral OCR)** Http Request *Service*
- 11 **Map AI Results to Fields** Set *Logic*
- 12 **Fetch Signed Resume URL** Http Request *Service*
- 13 **Filter by AI Score / Recommendation** If *Logic*
- 14 **Extract Resume Text (Mistral OCR)** Http Request *Service*
- 15 **Update Candidate Record (Sheets)** Google Sheets *Service*
- 16 **Send Shortlist Confirmation (Email)** Gmail *Service*
- 17 **Notify HR: High-Scoring Candidate (Slack)** Slack *Service*
- 18 **Send Rejection Email** Gmail *Service*
- 19 **Store Resume Text** Set *Logic*

## How it's built

- **Starts on:** An arriving email
- **Steps:** 19, with 2 branches
- **Size:** Medium: a working afternoon
- **Connects to:** Gmail, Google Sheets, Slack
- **Model:** OpenAI
- **Retrieval:** Answers are drawn from documents you supply, not from the model alone

## Questions

What does it need to run?

An n8n account, plus your own Gmail, Google Sheets and Slack accounts, and a key for OpenAI. You connect your own accounts after importing it; none are included.

What starts it?

It starts on an arriving email.

Does it use AI?

Yes. It calls OpenAI. Its answers draw on documents you give it, not on the model alone. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Plan an afternoon. 19 steps is enough that you should read each one before running it.

How do I import it?

Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.

**Before you run it**

Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 19 steps before you point it at anything that matters.

## Run it in n8n

- **Create your n8n account** Free to start. n8n is where the workflow runs. [Create an n8n account ↗](https://millionrounds.com/n8n)
- **Download the workflow** Free with a Millionrounds account. [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fautomated-candidate-screening-and-response-with-openai)
- **Paste it into n8n** Open a new workflow in n8n and paste. Then connect your own accounts.

Stored with the author's traces removed: canvas notes, instance identifiers, saved credential names and any live document they had left behind.

## Connects to

Each opens the other workflows that use it.

[Gmail](https://millionrounds.com/workflows?service=Gmail#library)[Google Sheets](https://millionrounds.com/workflows?service=Google+Sheets#library)[Slack](https://millionrounds.com/workflows?service=Slack#library)

## Workflows like it

Also hiring, with the same services where possible, closest in size first.

- [**Automate Resume Analysis & Candidate Screening with JotForm** 19 steps · calls a model · Gmail, Postgres](https://millionrounds.com/workflow/automate-resume-analysis-and-candidate-screening-with-jotfor)
- [**Automate candidate rejections with Google Sheets and Gmail** 19 steps · calls a model · ClickUp, Gmail](https://millionrounds.com/workflow/automate-candidate-rejections-with-google-sheets-and-gmail)
- [**Automate recruitment with OpenAI and Airtable** 19 steps · calls a model · Airtable, Email](https://millionrounds.com/workflow/automate-recruitment-with-openai-and-airtable)
- [**Generate tailored CV and Cover Letter from job links** 19 steps · calls a model · Google Docs, Google Sheets](https://millionrounds.com/workflow/generate-tailored-cv-and-cover-letter-from-job-links)
- [**Score job postings and draft tailored CV summaries** 19 steps · calls a model · Gmail, Google Docs](https://millionrounds.com/workflow/score-job-postings-and-draft-tailored-cv-summaries)
- [**AI resume analysis & candidate evaluation with Slack** 20 steps · calls a model · Google Drive, Google Sheets](https://millionrounds.com/workflow/ai-resume-analysis-and-candidate-evaluation-with-slack)