watsonx.ai

Read about the latest and greatest, how-tos, best practices, and use cases from our experts and experienced product users.

We would love for you to blog with us! IBMers can blog without approval. All other users please apply here to become a blogger.

 View Only

Search Blogs

Use pivot tables to visualize data in a Decision Optimization experiment in watsonx.ai and Cloud Pak for Data

By Shirley de Jonk posted 3 days ago
In Decision Optimization experiments you can create different visualizations for both input and output data. Sometimes data has several categories and you want to see the information aggregated or to see averages or other values. You can create your own pivot tables in the Visualization view of a Decision Optimization experiment in watsonx.ai or ...
0 comments

Compare data tables in a Decision Optimization experiment in watsonx.ai and Cloud Pak for Data

By Shirley de Jonk posted 3 days ago
When building Decision Optimization models you sometimes want to create different scenarios with different data sets, or make changes to your data and rerun your model to see the effect. Switching between scenarios is easy in a Decision Optimization experiment, but, when making changes to data values, it's helpful to see 2 data tables side-by-side to ...
0 comments

Get things done and solve real problems with GenAI - Watch the Full Session!

By Austin Rexroat posted 7 days ago
Hey everyone👋 For those of you interested, this is an absolutely fantastic session! Go beyond fundamental chatbot concepts and discover how Generative AI can revolutionize various business operations. This workshop delves into practical and cutting-edge uses of Gen AI to tackle actual business challenges. Using interactive examples and ...
0 comments

TechXchange Dev Day - Virtual Agents is Available On Demand!

By NICK PLOWDEN posted 9 days ago
The IBM TechXchange Dev Day: Virtual Agents left us with a wealth of knowledge, and we're thrilled to share that 22 sessions are now available for on-demand viewing. Among these, we've handpicked the top 3 sessions that you won't want to miss: 1. "The year of Agents" fireside chat keynote , an insightful discussion sets the stage for the ...
0 comments

Processing Documents is easy with IBM Docling, CrewAI and watsonx

By Aakriti Aggarwal posted 10 days ago
Processing complex documents just got easier with IBM’s Docling , Crewai , and WatsonX . This cutting-edge combination enables intelligent agents to handle document analysis seamlessly and efficiently. Automate document analysis with highly intelligent agents. Key Features: Docling converts PDFs, DOCX, PPTs and more into a unified ...
0 comments

From Big to Smart: Cut AI Costs with smaller, customized Models Using InstructLab on watsonx.ai(private preview)

By Suhas Kashyap posted 14 days ago
Today, we’re launching a private preview of model alignment with InstructLab in watsonx.ai. With this feature, customers can add their enterprise data, amplify that with synthetic data and alignment tune a small language model. This results in a smaller specialized model that is catered to an enterprise use case without sacrificing on the performance ...
0 comments

🔥 DeepSeek R1 Distilled Models on watsonx.ai (import your custom model)

By MARYAM ASHOORI posted 15 days ago
The buzz today is DeepSeek AI, a very good new Chinese model that discloses reasoning steps. Although I advise against chasing after the latest models, I strongly advocate for understanding your organization's specific needs and gaps. If a new model emerges that addresses those needs, it's worth exploring and testing. Today you can ...
0 comments

Deploy and Inference DeepSeek-R1 Distilled Models with IBM watsonx.ai

By Nisarg Patel posted 16 days ago
Deploy and Inference DeepSeek-R1 Distilled Models with IBM Watsonx.ai Introduction IBM watsonx.ai is an enterprise-grade studio for developing generative AI applications and deploying them into your applications of choice. Our priority is to provide users with a set of open, trusted, and performant models to power their ...
0 comments

Automate the search for an optimized RAG pattern with AutoAI

By Julianne Forgo posted 20 days ago
An effective way to harness the power of generative AI to produce relevant content is to ground it with specific, curated content. Retrieval-augmented generation (RAG) turns an LLM from a creative text generator to a truly useful assistant. Learn how the AutoAI tool in IBM watsonx.ai makes creating a RAG solution for your use case fast and efficient ...
0 comments

Introducing the watsonx Developer Hub

By NICK PLOWDEN posted 24 days ago
At IBM, we're committed to empowering developers and making AI more accessible and productive for enterprises. Our new watsonx Developer Hub offers the latest quick starts and comprehensive guides to train, validate, tune, and deploy AI models. The developer hub offers a toolkit for developers to get quick access to: Models - A combination ...
0 comments

Forget RAG and welcome Agentic RAG!

By Armand Ruiz posted 29 days ago
𝗡𝗮𝘁𝗶𝘃𝗲 𝗥𝗔𝗚 In Native RAG, the most common implementation nowadays, the user query is processed through a pipeline that includes retrieval, reranking, synthesis, and generation of a response. This process leverages retrieval and generation-based methods to provide accurate and contextually relevant answers. 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗥𝗔𝗚 Agentic RAG is an ...
2 comments

2025 will be all about AI Agentic features & solutions

By Armand Ruiz posted 29 days ago
In 2025, everyone will be talking about & shipping AI Agentic features & solutions. Let's learn the basics: 𝗗𝗲𝗳𝗶𝗻𝗶𝘁𝗶𝗼𝗻 An AI agent is a system designed to reason through complex problems, create actionable plans, and execute these plans using a suite of tools. These agents exhibit advanced reasoning capabilities, memory retention, ...
0 comments

AI Trends for 2025 - With Martin Keen

By Martin Keen posted Sun January 12, 2025
Want to learn more the importance of AI agents and assistants in 2025? Register for Virtual Agents Day here → https://ibm.biz/BdaAVa Download the AI model guide to learn more → https://ibm.biz/BdGE4R The world of AI is changing and changing quickly. Martin Keen, Master Inventor is here to help set some expectations for what ...
0 comments

How I Use IBM Watsonx to Drive Productivity as a Data Scientist

By Sahir Maharaj posted Thu January 09, 2025
AI isn’t something from the future anymore, it’s already here and helping businesses improve every day. You’ve probably seen how AI can make big changes in areas like helping customers or managing supply chains. The real question now is how to use AI in a way that actually makes a difference. That’s where IBM Watsonx comes in. Watsonx gives you a set ...
0 comments

LLM Security Framework: Protecting RAG And AI Applications with IBM Granite Guardian

By Yash Sawlani posted Thu January 02, 2025
Introduction In today's rapidly evolving AI landscape, Large Language Models (LLMs) have become integral to many business applications. However, with this adoption comes significant security, compliance and governance challenges - from prompt injection attacks to data leakage and harmful content generation. Prompt injection attacks are ...
0 comments

Leveraging Watsonx.ai and LangChain for Document Extraction, Summarisation And Automated Quiz Generation

By Yash Sawlani posted Thu January 02, 2025
Introduction In today’s fast-paced world, automation and AI are transforming how we approach problem-solving across various domains. One area where AI is making a significant impact is in education and content creation, particularly in generating personalised quizzes from large and unstructured data sources like PDFs. This blog delves into ...
0 comments

Video Tutorial: How to check token usage on watsonx.ai

By Catherine Cao posted Thu December 19, 2024
#watsonx.ai #MachineLearning #PromptLab #GenerativeAI
1 comment

Granite Guardian 3.1 is Now Available!

By Kush Varshney posted Thu December 19, 2024
The new Granite Guardian 3.1 release is now available at it is even better at harm detection than Granite Guardian 3.0. The main new feature is 'function calling hallucination' detection relevant for tool-using AI agents. Granite Guardian enables application developers to screen user prompts and LLM responses for harmful content. These models ...
0 comments

The new IBM Granite 3.1 delivers powerful performance, longer context, new embedding models and more

By Kate Soule posted Thu December 19, 2024
IBM Granite 3.1 is the latest update to our Granite series of open, performant, enterprise-optimized language models. This suite of improvements, additions and new capabilities focuses primarily on augmenting performance, accuracy and accountability in essential enterprise use cases like tool use, retrieval augmented generation (RAG) and scalable ...
0 comments

How IBM watsonx can revolutionize team productivity

By Dinesh Divakaran posted Tue December 17, 2024
When people think of Watsonx, they often imagine it as just an "assistant." But this perception barely scratches the surface of its potential. One of the greatest challenges business owners face is aligning their teams . It doesn’t matter how advanced or expensive your productivity tools are - if your teams aren’t on the same page, their efficiency ...
1 comment