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.
N/A
Mutable.ai
Score 0.0 out of 10
N/A
Mutable.ai for codebases helps software developers by using AI codegen to create features, or refactor multiple files. It also offers AI enhanced explanation and search to understand any codebase, suggested improvements to code and squash bugs, progress reports generated automatically for monitoring updates to a codebase, and the ability to switch from a laptop to the cloud and back with its cli tool.
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 …
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
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 …
While there is always room for improvement (IBM Bob kept a ThreadLocal variable that could have been upgraded using java.time for formatting the date), I am pretty amazed at what can be done with it, and that its breath spans multiple development languages
In some cases, I asked IBM Bob to rewrite a Korn shell script in another language (Python), and it did so quickly. It's just the output looked different and didn't take some exceptions into account I had built in to the original script.
When I pointed out I wanted a "plug-in replacement", with some pointers for things to look for, it corrected those quickly. You do need to check its output (like with any AI).
Some colleagues had trouble signing up for IBM Bob (trials) if their e-mail address did not match their IBM ID etc. That process should be more clear, or foolproof.
Integration of Bob/AI where we built applications makes it way easier and efficient to use the capability I am particularly impressed with the other interactions like with system files and installations that can be performed within the IDE
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 Microsoft tools, which feels odd.
It lessened the dependency on me as 'the programmer' in the team. I usually had to write even the simplest of shell scripts for monitoring purposes. I just taught one of my colleagues to use IBM Bob to do it in a fraction of the time. He created it with two or three decent prompts. That saved him having to contact me and saved me time in creating it.
For the customer, this meant having the monitoring solution online within minutes, instead of days.
I asked IBM Bob to document a complex script that I wrote in ksh and rewrite it in Python. I can read Python but am not "fluent" in programming it. With the help of IBM Bob, I created a plug-in replacement of this tool within 1 day, which would normally have taken me weeks.
Also, the resulting tool runs 4 times faster than the original script.
A customer wanted to know if their suspicions were correct that, at certain times of the day, network traffic was slower. I had the systems (8 systems talking to each other) collect data every 30 seconds and fed the resulting .txt files into IBM Bob for analyzing, asking specific questions about time periods, inter- or intra datacenter traffic, etc. I first verified the details and examples it found in the data (to make sure it is correct) and asked it to generate a user-friendly report with a few tables.
That took less than 30 minutes to execute various queries until I was satisfied. It would have taken me days to analyze the data myself (and would probably missed some of the clues).