ai-that-works
🦄 ai that works - every tuesday 10 AM PST
Stars: 550
AI That Works is a weekly live coding event focused on exploring advanced AI engineering techniques and tools to take AI applications from demo to production. The sessions cover topics such as token efficiency, downsides of JSON, writing drop-ins for coding agents, and advanced tricks like .shims for coding tools. The event aims to help participants get the most out of today's AI models and tools through live coding, Q&A sessions, and production-ready insights.
README:
On Zoom, Tuesdays at 10 AM PST - an hour of live coding, Q&A, and production-ready AI engineering
Tuesday, September 16, 2025 at 10 AM PST
On this week's AI That Works, we'll explore the great Bash vs. MCP debate - what's better for helping coding agents do more?
We'll talk about:
- Token efficiency and Downsides of JSON
- Writing your own drop-ins for MCP tools
- Other advanced tricks like .shims for forcing uv instead of python or bun instead of npm
Weekly conversations with @hellovai & @dexhorthy about getting the most juice out of today's models
When: Every Tuesday at 10 AM PST on Zoom
Duration: 1 hour of live coding, Q&A, and production-ready insights
Goal: Take your AI app from demo → production
Before joining, get familiar with our toolkit:
|
|
|
| đź“… Episode | đź“ť Description |
|---|---|
On this week's AI That Works, we'll explore the great Bash vs. MCP debate - what's better for helping coding agents do more?
We'll talk about:
|
|
We'll explore hard problems in building rich UIs that rely on streaming data from LLMs. ​Specifically, we'll talk through techniques for rendering **STRUCTURED** outputs from LLMs, with real-world examples of how to handle partially-streamed outputs over incomplete JSON data. We'll explore advanced needs like * Fields that should be required for stream to start * ​Rendering React Components with partial data ​* Handling nullable fields vs. yet-to-be-streamed fields * ​Building high-quality User feedback * ​Handling errors mid-stream |
|
Exploring voice-based AI agents and supervisor threading patterns for managing complex conversational workflows. |
|
On #17 we talked about advanced context engineering workflows for using Claude code to work in complex codebases. This week, we're gonna get a little weird with it, and show off a bunch of ways you can use Claude Code as a generic agent to handle non-coding tasks. We'll learn things like: Skipping the MCP and having claude write its own scripts to interact with external systems, Creating internal knowledge graphs with markdown files, How to blend agentic retrieval and search with deterministic context packing |
|
Anyone can build a chatbot, but the user experience is what truly sets it apart. Can you cancel a message? Can you queue commands while it's busy? How finely can you steer the agent? We'll explore these questions and code a solution together. |
|
A few weeks ago, the Manus team published an excellent paper on context engineering. It covered KV Cache, Hot-swapping tools with custom samplers, and a ton of other cool techniques. On this week's episode, we'll dive deep on the manus Article and put some of the advice into practice, exploring how a deep understanding of models and inference can help you to get the most out of today's LLMs. |
|
By popular demand, AI That Works #17 will dive deep on a new kind of context engineering: managing research, specs, and planning to get the most of coding agents and coding CLIs. You've heard people bragging about spending thousands/mo on Claude Code, maxing out Amp limits, and much more. Now Dex and Vaibhav are gonna share some tips and tricks for pushing AI coding tools to their absolute limits, while still shipping well-tested, bug-free code. This isn't vibe-coding, this is something completely different. |
|
AI That Works #16 will be a super-practical deep dive into real-world examples and techniques for evaluating a single prompt against multiple models. While this is a commonly heralded use case for Evals, e.g. 'how do we know if the new model is better' / 'how do we know if the new model breaks anything', there's not a ton of practical examples out there for real-world use cases. |
|
Dive deep into practical PDF processing techniques for AI applications. We'll explore how to extract, parse, and leverage PDF content effectively in your AI workflows, tackling common challenges like layout preservation, table extraction, and multi-modal content handling. |
|
Last week on #13, we did a conceptual deep dive on context engineering and memory - this week, we're going to jump right into the weeds and implement a version of Decaying-Resolution Memory that you can pick up and apply to your AI Agents today. For this episode, you'll probably want to check out episode #13 in the session listing to get caught up on DRM and why its worth building from scratch. |
|
How do we build agents that can remember past conversations and learn over time? We'll explore memory and context engineering techniques to create AI systems that maintain state across interactions. |
|
This week's session was a bit meta! We explored 'Boosting AI Output Quality' by building the very AI pipeline that generated this email from our Zoom recording. The real breakthrough: separating extraction from polishing for high-quality AI generation. |
|
Content creation involves a lot of manual work - uploading videos, sending emails, and other follow-up tasks that are easy to drop. We'll build an agent that integrates YouTube, email, GitHub and human-in-the-loop to fully automate the AI that Works content pipeline, handling all the repetitive work while maintaining quality. |
|
Disambiguating many ways of naming the same thing (companies, skills, etc.) - from entity extraction to resolution to deduping. We'll explore breaking problems into extraction → resolution → enrichment stages, scaling with two-stage designs, and building async workflows with human-in-loop patterns for production entity resolution systems. |
|
Ready to level up your prompting skills? Join us for a deep dive into advanced prompting techniques that separate good prompt engineers from great ones. We'll cover systematic prompt design, testing tools / inner loops, and tackle real-world prompting challenges. Perfect prep for becoming a more effective AI engineer. |
|
Agents are great, but for the most accuracy-sensitive scenarios, we some times want a human in the loop. Today we'll discuss techniques for how to make this possible. We'll dive deep into concepts from our 4/22 session on 12-factor agents and extend them to handle asynchronous operations where agents need to contact humans for help, feedback, or approvals across a variety of channels. |
|
MCP is only as great as your ability to pick the right tools. We'll dive into showing how to leverage MCP servers and accurately use the right ones when only a few have actually relevant tools. |
|
One of the most common problems in AI engineering is looking at a set of policies/rules and evaluating evidence to determine if the rules were followed. In this session we'll explore turning policies into prompts and pipelines to evaluate which emails in the massive Enron email dataset violated SEC and Sarbanes-Oxley regulations. |
|
Live workshop in San Francisco on building 12 factor agents. Interactive instruction, code-along format, and hackathon to build production-ready AI agents. |
|
Minimalist and high-performance testing/evals for LLM applications. Stay tuned for our season 2 kickoff topic on testing and evaluation strategies. |
|
Live workshop in NYC on building 12 factor agents. Interactive instruction, code-along format, and hackathon to build production-ready AI agents. |
|
Learn how to build production-ready AI agents using the twelve-factor methodology. We'll cover the core concepts and build a real agent from scratch. |
|
Large models can do a lot, but so can small models. We'll discuss techniques for how to leverage extremely small models for generating diffs and making changes in complete codebases. |
|
Models can reason but you can also reason within a prompt. Which technique wins out when and why? We'll find out by adding reasoning to an existing movie chat agent. |
|
LLMs are great at classification from 5, 10, maybe even 50 categories. But how do we deal with situations when we have over 1000? Perhaps it's an ever changing list of categories? |
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for ai-that-works
Similar Open Source Tools
ai-that-works
AI That Works is a weekly live coding event focused on exploring advanced AI engineering techniques and tools to take AI applications from demo to production. The sessions cover topics such as token efficiency, downsides of JSON, writing drop-ins for coding agents, and advanced tricks like .shims for coding tools. The event aims to help participants get the most out of today's AI models and tools through live coding, Q&A sessions, and production-ready insights.
Awesome-AI-Agents-HUB-for-CrewAI
A comprehensive repository featuring a curated collection of AI-powered projects and Multi Agent Systems (MAS) built with the Crew AI framework. It provides innovative AI solutions for various domains, including marketing automation, health planning, legal advice, and more. Users can explore and deploy AI agents, Multi Agent Systems, and advanced machine learning techniques through a diverse selection of projects that leverage state-of-the-art AI technologies like RAG (Retrieval-Augmented Generation). The projects offer practical applications and customizable solutions for integrating AI into existing workflows or new projects.
latitude-llm
Latitude is an open-source prompt engineering platform that helps developers and product teams build AI features with confidence. It simplifies prompt management, aids in testing AI responses, and provides detailed analytics on request performance. Latitude offers collaborative prompt management, support for advanced features, version control, API and SDKs for integration, observability, evaluations in batch or real-time, and is community-driven. It can be deployed on Latitude Cloud for a managed solution or self-hosted for control and customization.
-Topaz-DeNoise-AI-Tool
Topaz DeNoise AI is a powerful tool designed for photographers and videographers to enhance image quality by reducing noise while preserving detail. It leverages advanced AI algorithms to clean up images, providing stunning results without sacrificing clarity. With features like AI-powered noise reduction, detail preservation, batch processing, and a user-friendly interface, users can easily improve the quality of their visuals. The tool offers a seamless workflow from downloading and installing the software to uploading images and applying noise reduction. Additionally, it provides documentation, contribution guidelines, and emphasizes security and responsible use.
humanlayer
HumanLayer is a Python toolkit designed to enable AI agents to interact with humans in tool-based and asynchronous workflows. By incorporating humans-in-the-loop, agentic tools can access more powerful and meaningful tasks. The toolkit provides features like requiring human approval for function calls, human as a tool for contacting humans, omni-channel contact capabilities, granular routing, and support for various LLMs and orchestration frameworks. HumanLayer aims to ensure human oversight of high-stakes function calls, making AI agents more reliable and safe in executing impactful tasks.
AI-Blueprints
This repository hosts a collection of AI blueprint projects for HP AI Studio, providing end-to-end solutions across key AI domains like data science, machine learning, deep learning, and generative AI. The projects are designed to be plug-and-play, utilizing open-source and hosted models to offer ready-to-use solutions. The repository structure includes projects related to classical machine learning, deep learning applications, generative AI, NGC integration, and troubleshooting guidelines for common issues. Each project is accompanied by detailed descriptions and use cases, showcasing the versatility and applicability of AI technologies in various domains.
refact-vscode
Refact.ai is an open-source AI coding assistant that boosts developer's productivity. It supports 25+ programming languages and offers features like code completion, AI Toolbox for code explanation and refactoring, integrated in-IDE chat, and self-hosting or cloud version. The Enterprise plan provides enhanced customization, security, fine-tuning, user statistics, efficient inference, priority support, and access to 20+ LLMs for up to 50 engineers per GPU.
oreilly-retrieval-augmented-gen-ai
This repository focuses on Retrieval-Augmented Generation (RAG) and Large Language Models (LLMs). It provides code and resources to augment LLMs with real-time data for dynamic, context-aware applications. The content covers topics such as semantic search, fine-tuning embeddings, building RAG chatbots, evaluating LLMs, and using knowledge graphs in RAG. Prerequisites include Python skills, knowledge of machine learning and LLMs, and introductory experience with NLP and AI models.
ChatFAQ
ChatFAQ is an open-source comprehensive platform for creating a wide variety of chatbots: generic ones, business-trained, or even capable of redirecting requests to human operators. It includes a specialized NLP/NLG engine based on a RAG architecture and customized chat widgets, ensuring a tailored experience for users and avoiding vendor lock-in.
AgentForge
AgentForge is a low-code framework tailored for the rapid development, testing, and iteration of AI-powered autonomous agents and Cognitive Architectures. It is compatible with a range of LLM models and offers flexibility to run different models for different agents based on specific needs. The framework is designed for seamless extensibility and database-flexibility, making it an ideal playground for various AI projects. AgentForge is a beta-testing ground and future-proof hub for crafting intelligent, model-agnostic autonomous agents.
plandex
Plandex is an open source, terminal-based AI coding engine designed for complex tasks. It uses long-running agents to break up large tasks into smaller subtasks, helping users work through backlogs, navigate unfamiliar technologies, and save time on repetitive tasks. Plandex supports various AI models, including OpenAI, Anthropic Claude, Google Gemini, and more. It allows users to manage context efficiently in the terminal, experiment with different approaches using branches, and review changes before applying them. The tool is platform-independent and runs from a single binary with no dependencies.
WaveExecutor
WaveExecutor is a robust Windows-based script executor tailored for Roblox enthusiasts. It boasts AI integration for seamless script development, ad-free premium features, and 24/7 support, ensuring an unparalleled user experience.
Stake-Crash-Predictor
The Stake Crash Predictor is a demo-focused toolkit that combines statistical analysis, decryption tools, and AI-assisted summaries to help users study rounds on Stake.us. It includes features like real-time prediction accuracy, AI summaries, decryption tools, and demo bot templates. Users can install the tool by downloading the ZIP file, run it in demo mode to explore crash predictor outputs, and use the server seed hash decrypt helper for educational purposes. The tool is designed for Stake.us and focuses on stake mines predictor and stake predictor workflows.
ComfyUI-TBG-ETUR
ComfyUI-TBG-ETUR is a repository for TBG Enhanced Tiled Upscaler and Refiner Pro, offering advanced enhancement suite for tiled image generation and refinement in ComfyUI. It introduces neuro generative tile fusion, interactive tile-based editing, and multi-path processing pipelines designed for extreme resolution workflows up to 100MP. The tool applies advanced algorithms for AI image enhancement, high-resolution generation, image polishing, and seamless tile fusion. It features a user-friendly interface and offers PRO features for Patreon supporters. The repository provides tutorials, installation guides, and API access for testing PRO features. Users can enhance images, generate high-resolution visuals, and refine images with fine detail using TBG Enhanced Tiled Upscaler and Refiner Pro.
llmops-duke-aipi
LLMOps Duke AIPI is a course focused on operationalizing Large Language Models, teaching methodologies for developing applications using software development best practices with large language models. The course covers various topics such as generative AI concepts, setting up development environments, interacting with large language models, using local large language models, applied solutions with LLMs, extensibility using plugins and functions, retrieval augmented generation, introduction to Python web frameworks for APIs, DevOps principles, deploying machine learning APIs, LLM platforms, and final presentations. Students will learn to build, share, and present portfolios using Github, YouTube, and Linkedin, as well as develop non-linear life-long learning skills. Prerequisites include basic Linux and programming skills, with coursework available in Python or Rust. Additional resources and references are provided for further learning and exploration.
trigger.dev
Trigger.dev is an open source platform and SDK for creating long-running background jobs. It provides features like JavaScript and TypeScript SDK, no timeouts, retries, queues, schedules, observability, React hooks, Realtime API, custom alerts, elastic scaling, and works with existing tech stack. Users can create tasks in their codebase, deploy tasks using the SDK, manage tasks in different environments, and have full visibility of job runs. The platform offers a trace view of every task run for detailed monitoring. Getting started is easy with account creation, project setup, and onboarding instructions. Self-hosting and development guides are available for users interested in contributing or hosting Trigger.dev.
For similar tasks
ai-that-works
AI That Works is a weekly live coding event focused on exploring advanced AI engineering techniques and tools to take AI applications from demo to production. The sessions cover topics such as token efficiency, downsides of JSON, writing drop-ins for coding agents, and advanced tricks like .shims for coding tools. The event aims to help participants get the most out of today's AI models and tools through live coding, Q&A sessions, and production-ready insights.
For similar jobs
sweep
Sweep is an AI junior developer that turns bugs and feature requests into code changes. It automatically handles developer experience improvements like adding type hints and improving test coverage.
teams-ai
The Teams AI Library is a software development kit (SDK) that helps developers create bots that can interact with Teams and Microsoft 365 applications. It is built on top of the Bot Framework SDK and simplifies the process of developing bots that interact with Teams' artificial intelligence capabilities. The SDK is available for JavaScript/TypeScript, .NET, and Python.
ai-guide
This guide is dedicated to Large Language Models (LLMs) that you can run on your home computer. It assumes your PC is a lower-end, non-gaming setup.
classifai
Supercharge WordPress Content Workflows and Engagement with Artificial Intelligence. Tap into leading cloud-based services like OpenAI, Microsoft Azure AI, Google Gemini and IBM Watson to augment your WordPress-powered websites. Publish content faster while improving SEO performance and increasing audience engagement. ClassifAI integrates Artificial Intelligence and Machine Learning technologies to lighten your workload and eliminate tedious tasks, giving you more time to create original content that matters.
chatbot-ui
Chatbot UI is an open-source AI chat app that allows users to create and deploy their own AI chatbots. It is easy to use and can be customized to fit any need. Chatbot UI is perfect for businesses, developers, and anyone who wants to create a chatbot.
BricksLLM
BricksLLM is a cloud native AI gateway written in Go. Currently, it provides native support for OpenAI, Anthropic, Azure OpenAI and vLLM. BricksLLM aims to provide enterprise level infrastructure that can power any LLM production use cases. Here are some use cases for BricksLLM: * Set LLM usage limits for users on different pricing tiers * Track LLM usage on a per user and per organization basis * Block or redact requests containing PIIs * Improve LLM reliability with failovers, retries and caching * Distribute API keys with rate limits and cost limits for internal development/production use cases * Distribute API keys with rate limits and cost limits for students
uAgents
uAgents is a Python library developed by Fetch.ai that allows for the creation of autonomous AI agents. These agents can perform various tasks on a schedule or take action on various events. uAgents are easy to create and manage, and they are connected to a fast-growing network of other uAgents. They are also secure, with cryptographically secured messages and wallets.
griptape
Griptape is a modular Python framework for building AI-powered applications that securely connect to your enterprise data and APIs. It offers developers the ability to maintain control and flexibility at every step. Griptape's core components include Structures (Agents, Pipelines, and Workflows), Tasks, Tools, Memory (Conversation Memory, Task Memory, and Meta Memory), Drivers (Prompt and Embedding Drivers, Vector Store Drivers, Image Generation Drivers, Image Query Drivers, SQL Drivers, Web Scraper Drivers, and Conversation Memory Drivers), Engines (Query Engines, Extraction Engines, Summary Engines, Image Generation Engines, and Image Query Engines), and additional components (Rulesets, Loaders, Artifacts, Chunkers, and Tokenizers). Griptape enables developers to create AI-powered applications with ease and efficiency.