Hi! I’m Sophie, a Software Engineer on the Network Venture team at Jobber. Our team spends a lot of time obsessing over ways to make Jobber simpler and easier for our customers to use. We try to remove unnecessary clicks, reduce decision fatigue, and help users get to value faster. Every week, we ask ourselves: “Where’s the friction? How do we clear it away?”
It makes sense, then, that the biggest change in how our engineering team works lately comes from applying that same philosophy to ourselves. Our developers have started using AI-powered tools to streamline how we write and test code. Tasks that used to involve half a dozen tabs now happen directly in our code editor. In short, AI is doing for us what we’ve always tried to do for our customers: cutting out the friction.
The Enemy: Context Switching
Historically, building even a small feature required juggling an overwhelming number of tools. Let’s paint a picture, shall we? We want to experiment with a new widget on our home page. Seems straightforward enough, right?
We start in Jira, where the feature requirements live, and gather all the context we need.
We’re not totally sure what the best practices are for this type of experimentation, so we switch over to Confluence and do a bit of digging through our docs.
Once we feel confident with our approach, we hop into our code editor to get started.
Halfway through, a pesky bug pops up that we can’t quite pin down. Time to jump out to Stack Overflow or Google.
A few minutes later, we realize we’ve forgotten a small but important detail from the requirements, “what’s the exact copy for the button again?”. Back to Jira we go.
By the time we’ve bounced between tickets, docs, forums, and our editor, the actual “building” feels like just one part of a much bigger juggling act.
If only there were a way to stay focused in one place, while still having all the context and answers at our fingertips...
Cursor to the Rescue
Cursor is an AI-powered code editor that keeps us in the flow. We can write code, debug issues, and pull in information without ever leaving the editor. We’ve been really excited about the efficiency gains we get with this tool so we’ve doubled down on making it even more useful by writing Jobber-specific Cursor rules and connecting it to our own Jobber MCP server.
Cursor rules are directions we give to Cursor with our own best practices baked in. Instead of just asking AI to “build a GraphQL mutation” or “write a test,” we can write rules that tell Cursor exactly how we expect those things to look at Jobber. The result is code skeletons and patterns that already follow our conventions.
Our MCP server takes it one step further, allowing us to hook Cursor directly into our Atlassian environment. That means all the best-practice documentation from Confluence and the project requirements in Jira tickets are now just a prompt away, right inside the editor. In practice, that means less time hunting for answers and more time building!
The Impact
Let’s revisit that same widget experiment scenario, but now with Cursor in the mix.
We kick things off right inside Cursor. The requirements from Jira are pulled straight into the editor with a single prompt, and we can double-check our approach by pulling in best practices from Confluence — right there beside our code.
When a bug shows up, we just drop the error into the Cursor chat and troubleshoot it together. No more bouncing between tools. Just steady, focused building.
Since we’re already in flow, why stop there? We can ask Cursor to spin up some specs for us. We have a Cursor rule for that. And while we’re at it, let’s have Cursor draft the pull request. There’s a rule for that too!
But the real impact goes beyond saving a few clicks. For engineers, it means more focus time and less mental overhead. For teams, it means less wheel spinning, faster iteration cycles, and more consistent code quality because best practices are baked right into the workflow. The small efficiencies compound, allowing us to experiment quickly, learn fast, and adapt.
The irony isn’t lost on us. As a Growth team, we focus on reducing friction for Jobber customers, and now with AI, we’re doing the same for our own workflows. In other words, we’re not just practicing what we preach, we’re coding the way we want our customers to work: simply, seamlessly, and without friction.
About Jobber
Our awesome Jobber technology teams span across Payments, Infrastructure, AI/ML, Business Workflows & Communications. We work on cutting edge & modern tech stacks using React, React Native, Ruby on Rails, & GraphQL.
If you want to be a part of a collaborative work culture, help small home service businesses scale and create a positive impact on our communities, then visit our careers site to learn more!
Top comments (0)