Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Automatic Model Router
Discover an automatic model router that selects the optimal LLM for each step in a trip‑planning workflow, halving cost and reducing latency by around 30%.
In this demo, I’ll show how I implemented automatic model router to choose which LLM to call in my AI trip planner workflow. It reduced cost by about 50% and latency by about 30%
Full-stack AI trip planner built with TypeScript, Python, and Pydantic validation.
Related projects
SirPlotsALot
Montreal
Learn how to connect LLMs with JavaScript‑based data analysis, using prompting, function calling, and secure sandboxed code for…
AI Junk Removal Workflow Hack
Montreal
This talk explains how AI and cloud technologies were used to automate junk removal workflows, improve recycling processes,…
LLM.f90 - Minimal Large Language Model Inference Framework
Toronto
A low‑dependency Fortran framework for LLM inference, showing zero‑dependency implementation, matrix operations, and support for Llama, Phi, and…
From Haikus to Helper - Wrangling Agentic LLM's
Montreal
This talk covers building an LLM-powered product for data transformation and enrichment, detailing architecture, SQL and vector retrieval,…
Orchestrating AI Agents for Building Performance: LangGraph, RAG & Real-Time Engineering Calculations
Montreal
Demonstration of a LangGraph‑based multi‑agent system that integrates RAG, MongoDB, encryption, and Python REPL tools for autonomous building…
Hacking Together an AI-Powered Resale & Recycling Workflow
Montreal
Learn how we integrate computer vision, LLMs, and real‑time transcription to automate job estimates, product descriptions, inventory syncing,…