Members-Only

Recent Talks & Demos are for members only

Exclusive feed

You must be an AI Tinkerers active member to view these talks and demos.

Sign in View FAQ

July 10, 2025 · DC

Can You Trust the AI?

This talk explores methods to safely validate AI responses using JSON schema, JavaScript validation, solution graphs, and error correction by additional AI instances.

Overview

How do we use large language models (LLMs) safely? How do we check the AI response?
We are working on an app builder service with AI assitanet and we use these methods to validate the AI response:

JSON schema
JavaScript expression validation
Solution Graph and diagram for user validation
Other AI instance to fix errors by LLM

Links

https://appforgelab.com/
App Forge Lab leverages AI to generate applications from user descriptions.

Tech stack