Mike Murphy

Ruchir Puri

Kim Martineau

News

Deep Dive

Q & A

Continuing the momentum of AI for Code with Project Wisdom

Find and fix IT glitches before they crash the system 

COBOL programmers are getting harder to find. IBM’s code-writing AI can help

Software has eaten the world. What now?

What’s an LLM context window and why is it getting larger?

These new IBM agents will give developers new ways to solve problems — and clear their backlog

How AI will help code tomorrow’s machines

IBM Developer Blog

IBM CodeNet empowers AI to tackle programming

MSR 2025

ICSE 2025

CHI 2025

Foundation Models

AI for Code

Automated AI

Natural Language Processing

Generative AI

Open Source

Granite

AI for IT

Application Modernization

Explainable AI

AI can help sift through the noise to identify significant patterns in the increasingly large pools of data generated by enterprises. We’re reimagining IT operations, using AI to automate core processes, better detection and diagnosis, preformance monitoring, and explainable action recommendations.

Modern computing architectures are revolutionizing the way business gets done. We’re working on tools to help businesses automate much of their daily processes, to save time and drive new insights through trusted, safe, and explainable AI systems.

AI for Business Automation

Most enterprises rely on large volumes of aging code that are a challenge to debug, maintain, and update. At IBM Research, we’re using AI to help modernize software stacks, designing automated programming and refactoring systems to help businesses keep up with the speed of modern life. 

There’s an ever-increasing demand on business systems to keep up with the speed of the web. We’re designing systems to help organizations modernize their applications, while reducing the time it takes businesses to rebuild their products to take advantage of the benefits of the hybrid cloud. 

The hybrid cloud can help businesses tap into the potential of the cloud, while retaining the benefits of private environments. At IBM Research, we’re pursuing open-source standards and code to create an agile and scalable platform that can be deployed anywhere.

Hybrid Cloud Platform

AI for Code

Our work

These new IBM agents will give developers new ways to solve problems — and clear their backlog

What’s an LLM context window and why is it getting larger?

Software has eaten the world. What now?

COBOL programmers are getting harder to find. IBM’s code-writing AI can help

Find and fix IT glitches before they crash the system

Continuing the momentum of AI for Code with Project Wisdom

Publications

Can LLMs Replace Manual Annotation of Software Engineering Artifacts?

AutoRestTest: A Tool for Automated REST API Testing Using LLMs and MARL

ASTER: Natural and Multi-language Unit Test Generation with LLMs

A Multi-Agent Approach for REST API Testing with Semantic Graphs and LLM-Driven Inputs

Codellm-Devkit: A Framework for Contextualizing Code LLMs with Program Analysis Insights Tool Demo

Examining the Use and Impact of an AI Code Assistant on Developer Productivity and Experience in the Enterprise

IBM CodeNet empowers AI to tackle programming

Related topics