# The Right AI for The Right Problem

> When LLM Isn’t Always the Answer. LLMs are not the answer to everything. Three case studies show when vector search + a solver, traditional ML, or deep learning beat an LLM on cost, speed, and results.

Canonical page: https://laam.my.id/talks/the-right-ai-for-the-right-problem
Last updated: 2026-09-29

- **Type:** Meetup
- **Event:** Scale the World with AI: Builder Insights · Nakoding
- **Date:** 2025-08-09
- **Location:** Wingstop Buaran, East Jakarta
- **Audience:** Builders & developers
- **Language:** Bahasa Indonesia
- **Topics:** Applied AI, LLM, Machine Learning, Deep Learning, System Design
- **Slides:** [view the deck](https://canva.link/fphv2n7bt3p08fo)

It started with a hackathon: Hangout AI (AI-generated itineraries for Jakarta, Singapore, and Kuala Lumpur) and WIGO AI, and the feeling that LLMs could solve everything. Then came the assessment. For car detection, YOLO + CNN beat GPT-4V at ~$0.001 vs $0.01–0.03 per image and 50 ms vs 3–5 s.

Three case studies follow. Itinerary planning: vector search + OR-Tools gives consistent, optimal plans ~25x cheaper and 16x faster than LLM generation. Price prediction for 100K products: traditional ML (XGBoost / Random Forest) wins on structured data. Content moderation at 10M+ posts a day: custom multi-modal deep learning beats both GPT-4V (cost, latency, privacy) and keyword filters.

The takeaway is a decision framework. Generative → LLM; structured prediction → traditional ML; complex multi-modal patterns → deep learning; optimization under constraints → solver. Then weigh budget, scale, latency, maintenance, and compliance. The best engineering solution is the one that works reliably, scales economically, and solves the real problem.