Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
HandIt.ai: Self-Improving AI Systems
Explore why most AI systems underperform, learn the difference between monitoring and true optimization, and see how HandIt.ai enables self‑improving AI with real case studies.
AI was supposed to revolutionize business, but most AI systems fall short. They drift, underperform, or break—leaving teams in endless cycles of firefighting instead of delivering real value. HandIt.ai introduces a paradigm shift: AI that improves itself.
In this talk, we’ll explore:
- Why most AI systems fail to meet expectations.
- The gap between AI monitoring and true AI optimization.
- How
HandIt.ai enables AI agents to learn, adapt, and optimize themselves—automatically.
- Real-world case studies of how self-improving AI delivers measurable business impact.
If you’re building or managing AI systems, this talk will show you how to take them from static tools to dynamic assets that evolve with your business.
Open-source engine auto-optimizes AI agents via LLM-as-Judge evaluation and A/B testing.
Related projects
Your technical interviews sucks, so let's fix it.
Medellín
Demonstrates building a real-time voice interview agent with Realtime API and Chainlit, showing tool integration, prompt design, and…
Facilitando el proceso de selección y pruebas técnicas.
Medellín
Learn how to automate CV parsing, scoring, and sentiment analysis of interview videos using LLMs, Google Sheets, and…
Agentes AI - Puesta en marcha
Bogotá
Learn how AI agents work and how to enhance language model functionality using open‑source tools and Google Vertex…
Automating What 400 People Do: Building an AI Agent for Trade Compliance
Medellín
Demonstrating an AI system that extracts, interprets, and validates import documents using legal logic and embeddings to automate…
Netgenius - AI for Network automation and smart fault detection and solution
Medellín
The talk explains how AI agents automate management and operation of network probes, detect faults, provide solutions, and…
Agentic Control of Research Labratories (AI Scientists!)
San Francisco
Demonstration of multi-agent systems controlling lab automation to design, execute, and review wet‑lab experiments, including deployment in a…