Claude API · Extraction · Classification

LLM Integration Developer in the Philippines

Les John Paul Oliver · Urdaneta City, Pangasinan, Philippines · Remote worldwide

You know AI could help your product, but not where it pays off or how to ship it without surprises. I add LLM features to the app you already run, scoped to what users will actually use, with cost and failure handling designed in from the start.

Examples from my own work: a Claude Haiku parser that turns messy supplier product titles into clean catalog fields for a sneaker marketplace, and a Chrome extension that turns a free-text track description into structured music metadata in one pass.

Typical LLM features

  • Extraction: pull structured fields out of titles, emails, PDFs, and forms.
  • Classification and routing: tag, prioritize, and send items to the right queue.
  • Drafting: first drafts of replies, summaries, and reports for a person to approve.
  • Tool use: let the model call your APIs for lookups, never unchecked writes.

Shipping it safely

Model choice per task (a small model where it's enough), prompt caching to cut cost, rate limits, logging, and a fallback when the API is slow or down.

Proof: work I shipped

Sneaker Symphony: AI-Run Marketplace

Live

A Philippine sneaker marketplace at sneakersymphony.com, built and run by one person. Yupoo and WGStores supplier scrapers, Claude Haiku product-title parser, GCash, bank transfer, and COD payments with proof-of-payment upload and per-pair QC approval.

Read the case study

SonicSense: AI Music Annotation Assistant

Prototype

Personal workflow automation for music annotation built by Les, a working keyboardist and producer. A Chrome side-panel extension that turns a free-text track description into structured music metadata in one pass, applying his own music knowledge to speed up annotation work.

Read the case study

AI-Assisted Refund Automation

In production

Automates a utility's daily refund and payment-correction approval queue across two legacy systems. Deterministic recipes decide, Claude explains the flagged cases, and a human confirms every action.

Read the case study

Questions people ask

Can you add AI to my existing app?

Yes. That's the usual job: a new endpoint or worker next to what you have, not a rewrite.

Which LLM should I use?

It depends on the task, volume, and budget. I usually start with Claude, testing a smaller model first, and only move up where quality needs it.

How much does LLM integration cost?

Pricing depends on scope. Book a free 30-minute call and you get a straight answer on cost and timeline.

Sa Filipino

Pwede bang lagyan ng AI ang app namin ngayon?

Oo. Kadalasan, nagdadagdag lang ng bagong feature sa tabi ng kasalukuyang app, hindi kailangang gawin ulit mula sa simula.

Pricing depends on scope

Book a free 30-minute call. You get a straight answer on cost and timeline.

Book a free 30-minute call