Rumblings of an AI Developer

CrewAI has emerged as a powerful framework for creating collaborative AI teams. Today, I’m excited to introduce CrewAI Chat UI – a sleek, intuitive web interface that makes interacting with your local CrewAI crews simple. Checkout the project on GitHub. What is CrewAI Chat UI? CrewAI Chat UI is a

Accurate and intuitive product search capabilities are crucial for user experience and conversion rates in e-commerce. Traditional keyword based search often fails when dealing with natural language queries or semantic understanding. This blog post explores how I implemented a Retrieval Augmented Generation (RAG) system using MastraAI to enhance product search

Introduction Imagine you're a busy real estate agent with dozens of new leads flooding your inbox daily. Some are ready to make an offer this week, while others are just casually browsing. How do you quickly identify which leads deserve your immediate attention? This is where an AI-powered

The ability to generate structured outputs has become increasingly important for practical applications. This post explores structured outputs, their significance, use cases, implementation strategies, and best practices for leveraging them in real-world applications. What Are Structured Outputs? Structured outputs are formatted, predictable responses that follow specific patterns or schemas. Unlike

AI agents are becoming more powerful and autonomous, making it important to implement proper safeguards. In these notes, we will explore task guardrails in CrewAI. What are guardrails? Task guardrails are protective measures that make sure AI systems operate safely and predictably. They act as boundaries that constrain an AI

Multimodal AI agents are systems that can process, understand, and generate multiple types of data or "modalities"—such as text, images, audio, and video. They are a step up from the text-only AI agents people are used to. Below are some use cases of multimodal agents: * Healthcare -Doctors

CrewAI's RLHF (Reinforcement Learning from Human Feedback) feature enables your AI agents to learn directly from your feedback. Let’s look at how this feature can help you build better AI systems. What is RLHF? RLHF is a training technique that helps AI systems better understand and align

CrewAI recently released a new feature called Knowledge that allows you to set up a knowledge base for your crews and agents. Compared to traditional RAG pipelines, it's simple and fast to set up. Here's how it works: * Create a folder called knowledge in your project&

A few months ago, I wrote a blog post on building conversational chatbots with CrewAI, but because the AI world moves so fast, I believe it’s now due for an update. In the previous version, I built a simple chatbot that used Mem0 for long-term memory. Now that Mem0

A practical framework for enterprise AI automation It’s the beginning of 2025, and AI agents are all the rage. People are starting to explore the promise of AI agents and how their businesses can benefit. This short blog post will highlight why I believe CrewAI is a great fit

When it comes to AI automation, managing complex workflows efficiently is crucial. The CrewAI team has recently released Flows, a powerful feature designed to simplify the creation and management of AI workflows. Whether you're building a simple chatbot or a sophisticated multi-agent system, Flows provides the structure and

The CrewAI team keeps shipping at the speed of light and it might be hard for you to keep up with all the latest changes. From version 0.61.0 to 0.63.6, the team has introduced many new features, optimizations, and improvements that significantly enhance the framework’s

AI agents are software entities that perform tasks, powered by LLMs. They take in inputs, reason, make decisions, and take action. However, their potential is unlocked when we extend their capabilities beyond their inherent knowledge. AI agents use tools to perform their tasks, including external data sets, web searches, APIs,

AI agents are software entities that perform tasks, powered by LLMs. They take in inputs, reason, make decisions, and take action. However, their true potential is unlocked when we extend their capabilities beyond their inherent knowledge. In this blog post, we'll be learning how to extend the capabilities

LLMs, the current backbone of AI-powered applications are stateless, which means they take inputs and return results that are independent of previous inputs. To create applications that can handle meaningful and complex workflows a memory system becomes a prerequisite. Memory plays a crucial role in creating systems that can learn,

In a previous post, I walked you through creating an AI-powered friend chatbot built with AutoGen and Mem0. You can read the blog post here and view the code on GitHub. In this post, we are going to evolve the AI friend chatbot to have a GUI powered by Gradio.

LLM-powered applications and AI agents have taken the world by storm in the last 2 years. At the heart is Retrieval-Augmented Generation (RAG), which is a powerful tool for enhancing the capabilities of models by providing contextually relevant information from external sources. In my last post, I explained how to

Have you ever wondered how to create a chatbot that can answer questions based on specific documents or data? Enter the world of RAG (Retrieval-Augmented Generation) applications! In this tutorial, I'll walk you through building a RAG chatbot using Autogen and LlamaIndex, two powerful tools in the AI

Note: The CrewAI pipeline feature was deprecated in favor of CrewAI Flows. I have written a comprehensive guide on flows, and you can read it here. In this blog post, we'll dive deep into CrewAI Pipelines and Routers, exploring how they work, their key components, and how to

Imagine having a dedicated team of AI experts at your disposal, ready to plan your dream vacation. With Autogen's GroupChat functionality, you can create a personalized travel planner that automates the mundane tasks of itinerary planning, destination suggestions, and budget management. By harnessing the power of multiple AI

It is generally agreed that AI agents are applications powered by LLMs, and have some decision-making capabilities and control flow. They also have memory and can use tools to execute their tasks. In a previous blog post, I detailed how to create a basic chatbot that is powered by the

Generative AI has taken the world by storm and people’s minds are blowing up with the possibilities. A lot of research and experimentation is going on and one area that has received much attention is AI agents. This blog post will introduce you to the world of AI agents

The CrewAI team has just released a new version packed with new features. As usual, I’m going to unpack the ones I find the most exciting. To upgrade to the new version run the following command from the terminal pip install --upgrade crewai 'crewai[tools]' Remember the

08/01/2025 There is an updated version of this blog post: Building conversational chatbots with knowledge using CrewAI and Mem0 Conversational chatbots are among the most common use cases for LLM-powered applications. On their own LLMs are not that powerful but given the ability to use tools and plan

Lately, I’ve been researching how to make AI agents that don’t suck, are engaging, and produce the expected results and one thing that kept coming up is the importance of having well-crafted prompts. Prompts are texts that go into an LLM and induce it to take an action