I'm Learning Why AI Shouldn't Do Everything

Mary Johnson — Tue, 01 Sep 2026 17:32:13 +0000

One thing I'm realizing while learning AI is that an LLM doesn't need to handle every task.

For example:

User question
↓
AI understands intent
↓
Call the right API
↓
Get real data
↓
AI explains the result

If I need to calculate distance, normal code can do it.

If I need to retrieve a database record, SQL can do it.

If I need to check whether a location is open, an API should provide the answer.

Then AI can focus on understanding the user's request and presenting the information naturally.

I'm starting to think the best AI applications aren't necessarily the ones with more AI.

They're the ones that use AI in the right places.

What tasks do you think should never be left entirely to an LLM?

I Want to Build an AI Assistant for My Website 🤖

Mary Johnson — Tue, 01 Sep 2026 17:31:10 +0000

I'm learning AI and I want to build something practical for my website instead of just another basic chatbot.

My idea is an AI assistant that can help visitors:

📍 Find the nearest location
🍴 Search and understand the menu
💰 Find menu prices
🥗 Find nutrition information
⚠️ Understand allergen information
🎯 Get personalized menu suggestions
🔎 Navigate to the right page using natural language

For example, a user could simply ask:

“What's the closest location to me?”

“I want something spicy. What should I order?”

The AI would retrieve information from my website/database instead of guessing.

I'm currently learning about RAG, APIs, tool calling, location services, and AI agents, and this is the project I want to experiment with.

My website/project: https://chickensaladchickmenuprice.com/

If you've built an AI assistant connected to a real website, what would you recommend I build first?

DEV Community: Mary Johnson

I'm Learning Why AI Shouldn't Do Everything

I Want to Build an AI Assistant for My Website 🤖