Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
AI-Native Agentic Workflows
This talk demos delivering outcomes using custom code blending deterministic steps and AI reasoning, covering the full agent lifecycle and builder implementation.
The goal of any agent is to deliver an outcome. But most real-world outcomes require a mix of deterministic steps that have to take place reliably, and those that require single-step or multi-step reasoning.
I’ll walk through a demo of how our product delivers outcomes via custom code written to implement a mix of deterministic and AI steps, all via intuitive plain-English interfaces.
I’ll also talk about the full lifecycle of an agent, which includes handling errors and implementing modifications, and how we’ve implemented those in our builder.
Neurosymbolic AI agents autonomously generate production-ready software.
- GPT-4GPT-4 is OpenAI’s large multimodal model: it processes both text and image inputs, delivering human-level performance on complex professional and academic benchmarks.This is OpenAI’s latest milestone in scaling deep learning: a large multimodal model accepting both text and image inputs. It demonstrates a significant capability leap over its predecessor, scoring in the top 10% on a simulated bar exam (GPT-3.5 scored in the bottom 10%). The model handles nuanced instructions and long-form content, supporting context windows up to 32,768 tokens (32K model). This capacity allows processing up to 25,000 words in a single, complex prompt. GPT-4 is engineered for enhanced reliability, steerability, and advanced reasoning across diverse tasks.
- 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.
- 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) .
- OpenAI APIOpenAI API: Your direct gateway to cutting-edge AI models (GPT-4o, DALL-E 3, Whisper), enabling scalable, multimodal intelligence integration into any application.The OpenAI API provides authenticated, programmatic access to a powerful suite of generative AI models. Developers leverage REST endpoints and official libraries (Python, Node.js) to integrate capabilities like advanced text generation (GPT-4o), image creation (DALL-E 3), and speech-to-text transcription (Whisper). This platform is engineered for scale, supporting millions of daily requests for tasks from complex reasoning to real-time customer support agents, ensuring your application gets reliable, state-of-the-art intelligence.
- Frontier LLMsFrontier Large Language Models represent the industry's most capable systems, defined by their massive scale (often trillions of parameters) and superior general intelligenceFrontier Large Language Models represent the industry's most capable systems, defined by their massive scale (often trillions of parameters) and superior general intelligence. These are the proprietary, cutting-edge models—like OpenAI's GPT-4, Anthropic's Claude, and Google's Gemini—that exhibit strong zero-shot reasoning and multimodal capabilities (text, image, audio). They are typically accessed via API, not open-weight, and set the performance benchmark for all complex, high-stakes AI applications across diverse domains. Tracking their progress is essential; they define the technological frontier.
Related projects
AI Agents vs Agentic AI
Austin
The session clarifies the distinction between AI agents and agentic AI, outlines practical use cases, and addresses common…
Coding Agents Are Good at Algorithms
Eindhoven
This talk explores using coding agents to develop a complex algorithm for a word game, demonstrating how collaboration…
Agent Runner
Seattle
This talk demonstrates Agent Runner, a desktop app using BAML for type-safe AI agents, accessible via hotkey with…
From Tool Call to React Component: Building Generative UI for Agentic Workflows
San Diego
See how AI agents generate interactive React components directly in chat for agentic workflows. Learn about the callback…
Agents require executive function
Toronto
Explore an open-source YAML specification for agent orchestration, drawing on cognitive science to build an artificial neocortex and…
Agentic Kanban: Making AI workflows behave like real teams
Dublin
Learn how Agentic Kanban structures AI agents like a team, moving tasks across a board for research, execution,…