07 · AI integration · Recruitment · Custom development
Automated job postings
A recruitment agency for physicians entered clinics' job postings by hand — up to 30 minutes per listing, 40 fields, error-prone and barely scalable.
Client project · client anonymized (confidentiality) · project from 2025
- Custom development
- PHP middleware
- MariaDB
- OpenAI API
- Google Indexing API
- JSON-LD Job Posting
- > 80%
- time saved per job posting
- our estimate
- 40 fields
- detected and filled in automatically
- Fully automatic
- through to publishing and Google indexing
01 · Problem
The client places physicians with clinics and has to keep publishing current job postings on its websites to do so. Maintaining these listings was a tedious, manual process: read the information off the clinic's website, enter 40 attributes per job posting one by one into a backend, check for completeness, publish. Up to 30 minutes per listing — with a high volume of openings, a significant bottleneck with frequent data entry errors.
02 · Solution
vona built a tailor-made AI workflow with a custom PHP/MariaDB middleware: the client simply enters the URL of the clinic's job page. The middleware automatically reads the HTML body of the target page and passes it to a custom-built AI chatbot — configured with fixed system and user prompts tailored precisely to the structure of medical job listings. The chatbot identifies all relevant characteristics of the job posting, extracts all 40 attributes and stores them in the database in structured form. Once the client approves it, the job posting is published on the website fully automatically, submitted for indexing via the Google Indexing API and enriched with structured JSON-LD data in the Job Posting format.
03 · Result
The manual effort for entering job postings fell by more than 80% by our estimate. What used to take up to 30 minutes per listing, the workflow handles in a few minutes. All 40 fields are filled in automatically; the client reviews every listing before approval. After approval, publishing and Google indexing happen with no further manual step. The structured Job Posting data is also a prerequisite for the listings to appear in Google's job search.
04 · Workflow
- Clinic job page: Client only enters the URL
- PHP middleware: reads the HTML body of the target page
- AI chatbot: fixed system and user prompts
- MariaDB: 40 attributes, structured
- Approval: by the client
- FULLY AUTOMATIC AFTER APPROVAL: Website published, Indexing Google Indexing API, JSON-LD Job Posting format
Related services
We can do this for you, too.
The services behind this project — with examples, process and frequently asked questions.
AI integration
We implement artificial intelligence where it creates real value in everyday work — from intelligent chatbots and AI workflows to the automation of recurring office tasks.
Learn more →Development
Web development, app development and custom software — tailor-made, performant and built around your business. We build digital products that keep working: cleanly built, easy to maintain and ready to grow.
Learn more →Keep reading
Background from practice.
Blog
Automation with AI Workflows: A Guide with Checklist
Which processes suit AI automation, how a workflow is built, which tools exist and how to calculate expectations and benefit realistically.
Read more →Blog
AI and Data Privacy: What Companies Need to Know Now
GDPR, DPAs, third countries and shadow AI: a practical overview with a data traffic light and checklist so you use AI in your company with data protection in mind.
Read more →Next project
Your project here?
Tell us about your problem. The first conversation is of course free of charge and without obligation.
Request a project →