Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
No-Code Agents: Instructions & Tools
This talk demonstrates how to create no-code agents using only clear instructions and available tools, based on a simple, effective approach developed recently.
We’ll show how to build no-code agents using only instructions and tools.
Model-agnostic enterprise API orchestrating LLMs, custom assistants, and agentic workflows securely.
- 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.
- TransformersThe deep learning architecture that revolutionized sequence modeling (NLP, vision) by replacing recurrent units with a parallelizable multi-head self-attention mechanism.The Transformer: a neural network architecture introduced in the landmark 2017 paper, "Attention Is All You Need." It eliminated the sequential processing bottleneck of prior Recurrent Neural Networks (RNNs) by relying solely on self-attention, enabling massive parallelization and significantly faster training (up to 10x faster) on modern hardware. This efficiency allowed for the creation of large-scale pre-trained models: BERT (encoder-only) and the generative GPT series (decoder-only). The architecture is now foundational to all modern Large Language Models (LLMs) and drives the current state-of-the-art in AI.
- 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.
- LangdockLangdock is the enterprise-grade, model-agnostic AI platform: deploy secure, customizable generative AI tools company-wide, maintaining full data control.This is the unified platform for secure, scalable AI adoption (ISO 27001, GDPR-compliant). Langdock delivers five core products: Chat, Assistants, Agents, API, and Workflows. It gives over 600 customers, including Merck and Personio, a single interface to integrate powerful LLMs (OpenAI, Anthropic, Meta) with internal data sources (Confluence, Slack, Google Drive). The system ensures data residency and compliance while empowering 50,000+ monthly active users to automate tasks and boost productivity tenfold.
Related projects
Nustom: AI Agent for software development
London
The talk explores how AI agents will enable non-technical users to create customized software quickly and affordably, transforming…
Giving Agents 200+ tools via MCP with Docker & E2B
Berlin
Accessing 200+ Docker MCP tools within E2B Sandboxes enables secure and scalable tool-use for AI agents to accomplish…
EidOS, an Agent Operating System
Seattle
Learn how to simplify LLM data products using a multi‑agent approach, then watch a live coding session building…
Deepcode
Vienna
This talk presents an agent-based auto-coder that analyzes GitHub repos, iteratively generates and critiques code, manages context efficiently,…
Build AI agent to accelerate your life
Palo Alto
Learn how to quickly build and deploy AI chatbots with Coze, creating functional agents for everyday tasks without…
Thinking in Systems with Juggernaut Labs
Waterloo
Learn to build sustainable AI systems using Juggernaut Labs' modular framework, enabling automation of internal processes and outsourcing…