Cursor vs. IBM Bob

Less appropriate for people who don't use LLMs to code but instead to create artifacts. Cursor is a fluid development platform, not something that will create an artifact to run in the cloud. Well designed to work on teams, to manage the code and how the LLMs interact with the code itself. Great for deep vibe coding.

Incentivized

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.

Incentivized

• API creation.
• Integrations
• Plan mode for large tasks.
• Refactoring.

Incentivized

• Analyzing existing programs, explaining clearly what it does.
• Rewriting programs in a more modern language and/or a much more modular design, adding lots of explanatory comments.
• Analyzing large amounts of data, verifying assumptions are either true or false.
• Improving my ability to write good prompts, by asking IBM Bob feedback about the prompt(s) I used.

Incentivized

• The CLI agent can be quite finicky via ACP.
• It can be hard to understand how much different models will cost.
• Support can be unresponsive.

Incentivized

• The setup of skills can be more simplified
• since the IBM Bob IDE is embedded in a VSCode based framework, we have to deal with the same UI (and missing guided workflows)
• The help pages are only available via URLs. I like to see an embedded help file which is structured and includes a search feature

Cursor is the best AI-powered IDE available today. The agents intelligently absorb context from the code, memory, and rules, and are capable of iterating with subagents until acceptance criteria is met.

Incentivized

Cursor is useful for all our developer team. Each and every team member use Cursor for coding and also Cursor has various models like composer, codex, claude and openai models which helps a lot for quality codings. Also Cursor help to create documents in md file format with markdown and preview which helps a lot.

Incentivized

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.

Incentivized

graphical user interface is really the thing that setting apart because other code harnesses are really focused on commandline interfaces but whenever you want a good graphical interface with all of the tools and workflow that us software developers we want I think that Cursor is the one that has done it the best out of all of the code harnesses that we’ve tried

Incentivized

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.

Incentivized

• Development speed increased at least 25%
• The result of the final Product is better than before/without it
• We use it as a standard now

Incentivized

• The ROI from converting our Installer app went from an initial estimate of 2 weeks to 3 days.
• The testing of the finalized app, which had to communicate with an already existing app w, was difficult to implement and test.
• Converting old scripts from a proprietary IDE was done instantly.

Incentivized