Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Trip Genius: Agentic Travel Automation
This talk presents Trip Genius, an AI-driven platform that automates end-to-end travel planning and booking using agent-based architecture and real-time API integration.
Trip Genius is an AI-driven agentic travel planning and booking platform that integrates flights, hotels, and itinerary management into a unified system. Using Large Language Models (LLMs) such as GPT-3.5-turbo, GPT-4o-mini and GPT-4o, the platform employs Natural Language Processing (NLP) to extract user preferences and automate end-to-end travel logistics. Unlike traditional travel systems that stop at planning, Trip Genius leverages real-time API interactions with services like Amadeus, Google Places, and TripAdvisor to enable direct bookings \cite{patil2023gorilla}. Its modular agent-based architecture comprises specialized agents for flight booking, hotel reservations, and itinerary generation, ensuring scalability and flexibility. Trip Genius introduces a novel graph-based clustering and optimization algorithm for itinerary planning and is the first solution to completely automate end-to-end travel bookings for the user. The evaluation results demonstrate a 98.7\% entity extraction accuracy, 100\% intent matching accuracy, and a TP99 latency of 4.85 s, highlighting the reliability and efficiency of the system. By providing a seamless, automated, and personalized travel experience, Trip Genius reduces manual effort and sets a new standard in AI-driven travel solutions.
Trip Genius uses LangChain agents, GPT-3.5-turbo, FastAPI, and React for trip booking.
- PythonPython: The high-level, general-purpose language built for readability, powering everything from web backends to advanced machine learning models.Python is the high-level, general-purpose language prioritizing clear, readable syntax (via significant indentation), ensuring rapid development for any team . Its ecosystem is massive: use it for robust web development with frameworks like Django and Flask, or leverage its power in data science with libraries such as Pandas and NumPy . The Python Package Index (PyPI) provides thousands of community-contributed modules, offering immediate solutions for tasks from network programming to GUI creation . The language is actively maintained by the Python Software Foundation (PSF), with the stable release currently at Python 3.14.0 (as of November 2025) .
- LangChainThe open-source framework for building and deploying reliable, data-aware Large Language Model (LLM) applications.LangChain is the essential framework for engineering LLM-powered applications: it simplifies connecting models (like GPT-4 or Claude) to external data, computation, and APIs. The platform provides a modular set of components—Chains, Agents, Tools, and Memory—allowing developers to quickly build complex workflows like Retrieval-Augmented Generation (RAG) pipelines and sophisticated conversational agents. Its Python and JavaScript libraries, combined with LangChain Expression Language (LCEL), offer a standardized interface for rapid prototyping and moving applications to production with confidence.
- LangGraphA low-level orchestration framework for building long-running, stateful, and cyclic multi-agent systems using a graph-based architecture.LangGraph is the specialized, low-level runtime for developing complex AI agents, extending the LangChain ecosystem to handle intricate, stateful workflows. It models the agent's logic as a directed graph: nodes represent actions (LLM calls, tool use), and conditional edges dictate the flow, enabling critical features like cycles (loops) for iterative reasoning. This graph-based approach ensures durable execution, allowing agents to persist through failures and resume operations. Key capabilities include comprehensive memory management via a shared state object and built-in human-in-the-loop functionality (interrupts) for external oversight. This robust framework is trusted by production teams at companies like Klarna and Replit for deploying scalable, resilient agent architectures.
- Third-Party APIsExternal services providing pre-built functionality (payments, mapping, communication) via a standardized interface: they are the building blocks for rapid application development.Third-Party APIs allow developers to integrate specialized, external services without building the functionality in-house. This strategy accelerates time-to-market and leverages domain expertise: think using Stripe for secure payment processing, Google Maps for real-time geolocation, or Twilio for SMS/voice communication. Access is typically secured via API keys or OAuth flows, managing access and protecting the vendor's resources. Adopting these APIs means outsourcing complex, non-core features, allowing internal teams to focus 100% on core product differentiation.
Related projects
Dad
New York City
Learn practical conversation starters, current event topics, sports updates, and strategies for navigating hearing loss and requesting financial…
Ambient Commerce / Why I Learned to Love Agentic Amazon
New York City
This talk presents an MVP of an on-chain ambient commerce system where buyer and seller agents negotiate and…
AI Agents vs Agentic AI
Austin
The session clarifies the distinction between AI agents and agentic AI, outlines practical use cases, and addresses common…
Multi-agent demo with Microsoft Semantic Kernel
Toronto
This talk demonstrates a multi-agent personal finance app using Microsoft Semantic Kernel to coordinate agents for transactions, vision…
Agent harness built for agents to build agents that actually work
New York City
This talk introduces Gambit, an agent harness using markdown for building reliable agents, assistants, and workflows with integrated…
Building for the Future Internet: Agent Services
Upstate Ny
Demonstrating meetSpace, an agent-first service for creating and finding local in-real-life events, showing the shift toward agent-driven internet…