No Clocks

In this article, I'll share the principles of LLM agent evaluation and you how to do it using DeepEval.

Patterns from our colleagues' work building with Generative AI

RAG combines LLMs with information retrieval systems. Explore top RAG tools and learn how to choose the best one for your specific use case.

"This thing is a tangled mess." I was relieved to hear the presenter say the words I was thinking. He had just finished walking me through a new AI agent, which I'm going to call Sherpa throughout this article. Sherpa was a proof of concept for a new AI agent their team had been working

Up to this point, we've covered agentic system architecture, how to organize your system into sub-agents and to build uniform mechanisms to standardize communication. Today we'll turn our attention to the tool layer and one of the most important aspects of agentic system design you'll need to consider: data retrieval. Data Retrieval and Agentic RAG

The article discusses creating uniform interaction models in modular agentic systems for effective request dispatching among agents and subagents.

The article looks at the benefits of modularity in agentic systems, enhancing clarity, maintainability, and reducing complexity.

RAG pipelines are the key to providing your LLM-powered apps with fresh, accurate data. In this guide, we explore best practices and antipatterns.

This article delves into the technical intricacies of Agentic AI Architecture, exploring its core components, key principles, development phases, technological integrations, applications, challenges, and future directions.

This guide outlines how to create efficient agentic systems by focusing on three layers: tools, reasoning, and action. Each layer presents unique challenges that can impact overall system performance.

The Automated Design of Agentic Systems (ADAS) is a unique approach in AI that enables the creation of agents capable of designing, testing, and refining themselves.

Explore essential AI tools for R programming to enhance your low-code development capabilities and streamline your projects. | Restackio

Introduction. Few days ago I discovered the OpenAI Gym library which is a bunch of standardized AI environments written in Python to benchmark the skills of AI programs and scripts, aka agents.

Like many of you, my first real exposure to AI was when ChatGPT dropped. I spent way too much time prompting it with random stuff, used it for some PowerShell, and tried out the voice feature when that launched. Mostly, I’ve used AI for things like writing docs, double-checking my grammar and English, and making some funny pictures.

Let’s start this with some confessions: I’m at best an enthusiastic amateur with AI. I know more than most, and I know nothing in the grand scheme. Example: I’m not sure I have any idea of what an AI agent is. I think I do, but there’s so much marketing hype around them that I

Use Meta Prompting to rapidly generate results in the GenAI Age - README.md

Generating diagrams with AI / LLMs

Replace 'hub' with 'ingest' in any GitHub URL for a prompt-friendly text.

A flexible, feature-rich yet light-weight logging framework based on R6 classes. It supports hierarchical loggers, custom log levels, arbitrary data fields in log events, logging to plaintext, JSON, (rotating) files, memory buffers. For extra appenders that support logging to databases, email and push notifications see the the package lgr.app.

The rcrd class extends vctr. A rcrd is composed of 1 or more fields, which must be vectors of the same length. Is designed specifically for classes that can naturally be decomposed into multiple vectors of the same length, like POSIXlt, but where the organisation should be considered an implementation detail invisible to the user (unlike a data.frame).

Use piped workflows for efficient data cleaning and visualization.

Create custom Streamlit and Shiny R apps effortlessly with AI assistance. Design, code, and deploy data apps in minutes.

LLMs are great at generating text, but how do you get them to generate structured output?

Seamless SSO for R applications

Learn how to implement strong authentication and SSO in Shiny apps with Descope. This guide integrates both OIDC and SAML with Posit Connect for seamless login.