05 · AI integration · Events & catering · Automation
Automated quote generation
An event and catering business created quotes manually from close to 50 templates — based on incomplete form submissions. Time-consuming, error-prone, not scalable.
Client project · client anonymized (confidentiality) · project from 2025
- Custom development
- OpenAI API
- PHP
- JavaScript
- MariaDB
- PDF generation
- CRM/ERP integration
- 120 min → 3 min
- quote generation from inquiry to PDF delivery
- according to the client
- Complete
- every inquiry — the chatbot asks until all details are there
- 50 templates
- covered automatically, CRM data filled in directly
01 · Problem
Customers sent inquiries through a simple contact form — often without the necessary details on guest count, location, menu preferences or time frame. The team had to follow up on every inquiry manually to qualify it, then pick the right one from close to 50 quote templates, fill it in individually, export it as a PDF and send it by email. Per quote according to the client: 120 minutes or more. Peak periods in summer and during trade show season led to waiting times of several days.
02 · Solution
vona built a custom solution that replaces the inquiry form entirely: a tailor-made AI chatbot — built in PHP and JavaScript, connected to the OpenAI API — guides prospects through a structured conversation. It asks specifically about event type, date, guest count, scope of catering and other details relevant to the quote, and keeps asking until all the information is complete. Only then does it ask for the customer's email address. All captured conversation and inquiry data is stored in a MariaDB database. A purpose-built PHP middleware reads this data, selects the matching cost estimate template, automatically generates a customized PDF from it and emails it to the customer in real time. In parallel, all data flows directly into the ERP/CRM system.
03 · Result
According to the client, quote generation now takes just under 3 minutes from the first chatbot message to PDF delivery — instead of up to 120 minutes of manual work before. Because the chatbot keeps asking until all details are there, inquiries arrive complete from the start – no more follow-up over missing details. The team sees every inquiry already structured in the CRM and can focus on personal consultation for complex events. The pipeline runs around the clock — including outside business hours.
04 · Workflow
- Prospect: Chat instead of form
- AI chatbot: PHP + JS, OpenAI API, keeps asking until all details are in
- MariaDB: Conversation + inquiry data
- PHP middleware: picks the matching template from ~50
- IN REAL TIME: PDF quote customized, Customer PDF by email in real time
- IN PARALLEL TO CRM: ERP/CRM all data directly, Team advises personally on complex events
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
Prompt Engineering: Eight Principles, a Template and Examples
Eight principles for better prompts with a before-and-after example, a template to take away, notes on prompt injection and a prompt library for your team.
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 →