n8n workflow template · 15 nodes · OpenAI
Handling Job Application Submissions with AI and n8n Forms is a free n8n workflow template that starts when someone submits an n8n form and works with OpenAI and Airtable. It has 15 nodes, 5 of them AI nodes (OpenAI Chat Model, Structured Output Parser, Text Classifier and Basic LLM Chain). The notes inside the workflow say: “Our application process starts with a simple file upload to get the applicant's CV for processing.” To run it, you add your own credentials for Airtable API and OpenAI API.
The text below comes from the sticky notes inside the workflow. We removed links, code samples and anything that looks like a key or token.
Learn more the Form Trigger node
Our application process starts with a simple file upload to get the applicant's CV for processing.
Read more about the Text Classifier
Form validation remains a critical step and before the introduction of LLMs, classifying document types was a relatively troublesome process. Today, n8n's text classifier node does an excellent job at this task.
Contextual validation powered by AI means invalid, incomplete or poorly created applicant CVs can be rejected as a quality check. When this happens in our workflow, we present the user again with the file upload form to retry.
Read more about the Basic LLM node
Information extraction is a logical next step once we have our PDF contents but we can extend further by only extracting data which is relevant to our job post. This ensure the information we extract is always relevant which saves time for the hiring team.
To achieve this for this demo, I've included the job post in the prompt for the LLM to compare the CV against. The provides the AI enough context to complete the task successfully.
Read more about the Airtable node
Next, we can complete our simple data capture by integrating and pushing data to our Applicant Tracking System.
Here, we're using Airtable because we can also store PDF files in our rows.
See our example Airtable here
Learn more about Form Ending
Finally to complete the form flow for step 1 of 2, we'll use a form ending node to redirect the user to step 2 of 2.
Here, we using query params as part of our redirect as this will pre-fill the form fields in step 2 of 2.
This redirect requires the full base URL, change it to the host of your n8n instance.
Learn more about Forms
In the second part of the application process, applicants are presented with a form containing multiple fields to complete. This step has often been a source of frustration for many, as they end up duplicating information that’s already in their CV.
If our redirection with prefilled data works as intended, this issue will be resolved, as the fields will be automatically populated by our LLM during step 1 of 2. This also allows candidates the opportunity to review and refine the application fields before submitting.
The text below comes from the sticky notes inside the workflow. We removed links, code samples and anything that looks like a key or token.
It's a perfect low-cost solution without the bells and whistles of the surface yet is highly advanced with its use of AI.
Join the Discord or ask in the Forum!
The 15 nodes in file order (sticky notes excluded). Branches and connections determine execution order in n8n:
Configure your own credentials after importing. Create each credential in n8n, then select it in the node.
Do you need somewhere to run it? Read our guide to self-hosted n8n.
We can adapt this workflow to your apps, data and process, then deploy and support it.
Contact Us