Genie is Uber’s internal on-call copilot, designed to provide real-time support for thousands of queries across multiple help channels in Slack®. It enables users to receive prompt responses with proper citations from Uber’s internal documentation. It also improves the productivity of on-call engineers and subject matter experts (SMEs) by reducing the effort required to address common, ad-hoc queries. While Genie streamlines the development of an LLM-powered on-call Slack bot, ensuring the accuracy and relevance of its responses remains a significant challenge. This blog details our efforts to improve Genie’s answer quality to near-human precision, allowing SMEs to rely on it for most queries without concern over potential misinformation in the engineering security and privacy domain.

An idiot's comprehensive guide to modern sampling

But for what I do use LLMs for, it’s invaluable.

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Programmatically integrate Claude Code into your applications using the SDK.

One common practice for working with MCP tools calls is to put the outputs from a tool back into the LLM as a message, and ask the LLM for the next step. ...

Check if your markdown looks janky here: https://t.co/Iw3aKDQDS7

An autonomous AI coding assistant for VS Code with Plan/Act modes, terminal execution, file editing, and Model Context Protocol for custom tools

The RAG narrative is oddly insidious, a mind virus

Check out Recraft’s newest featues for free – https://go.recraft.ai/codingsloth. Use my code SLOTH11 for $11 off any paid plan. AI Agents are kinda crazy ngl. // SLOTH ARTISTS // Pixel Art Sloth: https://www.behance.net/harveydentmustdie // NEWSLETTER // Sloth Bytes: https://slothbytes.beehiiv.com/subscribe // BUSINESS INQUIRIES // For business: thecodingsloth@smoothmedia.co For brand partnerships: https://tally.so/r/mZVvKa // SOCIALS // Twitter: https://twitter.com/TheCodingSloth1 TikTok: https://www.tiktok.com/@thecodingsloth Discord: https://discord.gg/2ByMHqTNca // TOOLS/THINGS I REALLY LIKE // If you wanna build 10x developer level projects check out CodeCrafters https://app.codecrafters.io/join?via=TheCodingSloth If you want to build an awesome newsletter like Sloth Bytes I use beehiiv https://www.beehiiv.com?via=the-coding-sloth If you want to make nice looking apps: https://mobbin.com/?via=sloth (some of these links are affiliates, so I'll earn some money which supports the channel!)

Learn how to design, build and ship AI agents with this interactive step by step guide in 2025. We also have resources and short descriptions attached to the roadmap items so you can get everything you want to learn in one place.

Allowing an LLM to formulate calls to external systems

Repository demonstrating best practices and patterns for implementing agentic workflows in Python, featuring modular, scalable, and reusable design patterns for intelligent automation. - arunpshank...

Collection of leaked system prompts. Contribute to jujumilk3/leaked-system-prompts development by creating an account on GitHub.

In this guide, we highlight why unmanaged vibe coding falls short for enterprise applications, what to prioritize when evaluating AI app development platforms, and how Superblocks delivers the security, reliability, and scalability enterprises need.

On digging AI shaped holes

expert led courses for front-end web developers and teams that want to level up through straightforward and concise lessons on the most useful tools available.

🚀 Exciting news! AgentWorkflow from @llama_index now in TypeScript! Build powerful AI systems with: 🔄 Multi-agent orchestration 🤝 Task handoffs between agents ⚡️ Real-time event streaming Level up your AI development now: $ npm i llamaindex

Learn how to build your own Deep Research agent from scratch in LlamaIndex! In our latest workshop tutorial, we cover going from zero knowledge of LlamaIndex to a fully-fledged multi-agent system for deep research! You'll learn: ➡️ Using AgentWorkflow to create a single agent ➡️ Creating a multi-agent system using AgentWorkflow ➡️ Dropping down to Workflows for even finer-grained control ➡️ Building a multi-agent system from scratch with Workflows Includes tool use, managing state, and common design patterns like reflection! Check it out here: https://colab.research.google.com/drive/1xYq4wr4dkmvOuq0Ljwt1W9fIxfR50ekq#scrollTo=OfNzCgHl08Sc

Today, we’re releasing new Llama protection tools for the open source AI community.

The question isn’t if AI will transform your business, but how to use it to maintain your competitive edge. Vercel CTO Malte Ubl shows how companies can understand AI’s fundamental shifts, adapt their skills, and integrate AI into their businesses.

Lightweight coding agent that runs in your terminal - openai/codex

A blog post covering tips and tricks that have proven effective for using Claude Code across various codebases, languages, and environments.

What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers? - humanlayer/12-factor-agents

A comprehensive guide to voice AI in 2025