IBM Bob is an AI-assisted development tool designed to support developers across the software development lifecycle. It helps interpret developer intent and provides assistance when working with real-world codebases by using contextual awareness of the surrounding project.
Bob provides better integrations
Specific AI work flows for Z/Mainframes put it way infront of other technologies that provide generic outputs versus Bob leveraging IBM's mainframe knowledge
As an IBM Business Partner working on IBM applications, I found that using IBM Bob was a natural progression. However, our team did evaluate Claude Code. The basic use of Claude Code was very similar - a sidebar interface in VS Code. We saw that Claude could do many of the same …
I have used both Google Gemini and the corporate (paid) ChatGPT, especifically the 5.6 Sol High model. While both work well, and obviusly the paid ChatGPT version produces higher quality output and considers more context, Bob is a good tradeoff between the two and worked as …
IBM Bob is THE missing piece in validating all default and customised code within IBM Maximo. It helps client to migrate from a heavy customised MX76 version to a clean MAS9 instance by converting Java code into front-end managed and controlled automation scripts
Verified User
Consultant
Chose IBM Bob
ChatGPT just did not have the breadth and depth of insight for my coding needs. To get an approximation of what I wanted I had to restate my prompt multiple times, and it looked almost like it did not learn from one time to the other.
I don't want to use ChatGPT for serious development work or customer data.
Copilot could do the same type of work, but I don't think it is tailored to software the way IBM Bob is. Also, I like the way IBM Bob is integrated in an IDE. My only access to Copilot is from various …
IBM Bob stands out in legacy code revamping and transformation that helps in bridging the gap between the legacy code and developers who doesnt have expertize in the legacy codes. With Semgrep scanning, the code is developed with all security considerations, saving time on …
The first time using it feels like magic. Its ability to analyze an existing codebase and adapt accordingly to questions, feature requests, issues, etc. is remarkable. However, it is not limited to an existing codebase - I've had it create new applications based on styling from another application from scratch. It has quickly gone from an amazing novelty to something that is relied upon daily.
It works well, for the most part, but asking for authorization for multiple steps or tool installation and use sometimes becomes bothersome. You can grant blanket authorizations but I do prefer to have a tradeoff there so not all is bad, but sometimes I get the impression that we get asked the same question several times during the same workflow.
ChatGPT just did not have the breadth and depth of insight for my coding needs. To get an approximation of what I wanted I had to restate my prompt multiple times, and it looked almost like it did not learn from one time to the other.