Bilel Abdelmoula

Home › AI integration developer

AI integration · OpenAI · Claude

AI integration developer: AI inside real products

I add AI where it saves people time: matching candidates to jobs with embeddings, reading CVs and travel documents with OCR, and chat assistants that answer from a site's own facts. Built into production apps, not demos.

📅 Book a free call ✉ Email me CV
  • OpenAI and Claude APIs
  • Embeddings + vector search
  • OCR document parsing
  • Background jobs so users never wait

Results

Measured on real projects.

  • 35kcandidates matched to 4k jobs
  • 32 s → <1 sCV upload, AI parsing in background
  • 1 workerbuilt to serve AI chat on many sites
  • 2022thesis on semantic search (LSI)

Case studies

AI features I've built and shipped.

Talent Match: AI recruitment ATS & CRM

Italian software startup · recruitment client · 2024–2026

  • AI candidate matching with OpenAI embeddings and vector search across 35k candidates and 4k jobs.
  • Combined with boolean (AND / OR / NOT) and distance filters so recruiters stay in control.
  • CV parsing with OpenAI + Google Vision moved to background jobs: upload wait cut from 32 s to under 1 s.
  • Xano
  • PostgreSQL
  • WeWeb
  • React
  • TypeScript
  • OpenAI
  • Python

Guest management platform

Events group with 13 companies in 12 countries · 2024–2026

  • Guests, flights, hotels and drivers in one platform instead of spreadsheets.
  • AI reads travel documents and fills in guest details.
  • Driver and car assignment for each pick-up; mobile-responsive for staff on the move.
  • Xano
  • WeWeb
  • OpenAI

site-assistant: Claude chat on any website (open source)

Cloudflare Worker · code on GitHub

  • One worker powers AI chat assistants on many sites; each site's facts live in its own JSON file.
  • API key stays on the server: origin allowlist, per-IP rate limit, message and history limits.
  • Safe fallback: if the AI API fails, the widget answers from its built-in FAQ.
  • Claude API
  • Cloudflare Workers
  • JavaScript

lsi-spark: semantic search engine (Master's thesis)

USTO-MB, 2022 · code on GitHub

  • Latent Semantic Indexing search engine (TF-IDF + SVD).
  • Benchmarked on one machine (NumPy) against a Spark cluster.
  • Python
  • NumPy
  • Apache Spark

AI work I can do for you

  • Semantic search and matching with embeddings and vector search
  • Document reading: CVs, IDs, travel documents (OpenAI + Google Vision OCR)
  • Chat assistants on your site or app, with your API key kept on the server
  • Prompt design and output checks so answers stay reliable
  • Run AI calls in background jobs so your app stays fast
  • Connect AI to your stack: Xano, PostgreSQL, React, Make, Cloudflare Workers

FAQ

Quick answers before we talk.

Which AI models do you work with?

OpenAI (embeddings and chat models) and Anthropic's Claude API, plus Google Vision for OCR. I pick based on the job, cost and speed.

Will AI slow my app down?

Not if it's built right. I run AI calls in background jobs: on a recruitment platform this cut the CV upload wait from 32 s to under 1 s.

Can you add AI to a Xano or WeWeb app?

Yes, that's most of my AI work. See my Xano developer and WeWeb developer pages.

Do you use AI tools to code?

Yes. I use Claude Code as a pair programmer, for example to rebuild a WeWeb front end in React + TypeScript, and I review and test everything it writes.

How do we start?

Book a free call or email me at [email protected] with the task you'd like AI to handle.

Let's build it properly

Tell me what's slow, messy or missing. A short call is enough to see if I can help.

📅 Book a free call ✉ [email protected]

Also see