How National Australia Bank sped up legacy migrations with Cursor
NAB engineers used Cursor to understand and migrate legacy Silverlight/.NET and Assembly systems, and to build a new payment app. As reported by Cursor, delivery was well ahead of original estimates.
The problem
A Silverlight/.NET monolith needed refactoring, and an Assembly mainframe migration had stalled for lack of people. Some greenfield projects also lacked the right technical expertise.
How they did it
- Used Ask Mode to visualize the business logic of the BizCalc monolith.
- Used Plan Mode with custom internal skills to generate user stories and API specifications.
- Generated flowcharts and business summaries from Assembly code to separate business logic from machine instructions.
- For a new payment app, wrote requirements and a parallelizable plan, then built it with agent models.
Results
- As reported by Cursor: NAB 'originally scoped six months of work' for the BizCalc migration and now expects it to finish in two months, 'a 3x improvement'.
- A greenfield payment app took '3 weeks' instead of a four-month scope.
- NAB standardized 6,000 developers on Cursor.
As reported by the source (Cursor customer story); AgentGid did not measure these figures.
This suits engineering teams with legacy code and someone who can check the agent's explanations against how the system really behaves, since the approach relies on custom internal skills and written specs. Keep in mind that the 3x and 3-week figures are reported by Cursor, and paid plans bill usage at model API rates with overage. GitHub Copilot (Free + $10/mo) is a cheaper option to trial first.
The agent used here
Similar use cases
Cursor's planner-worker agents built a web browser from scratch in about a week
Cursor tested long-running autonomous coding with a hierarchy of planner agents that create tasks and worker agents that just complete them. The headline project was a browser eng…
The agents ran for close to a week, writing over 1 million lines of code across 1,000 files.
How Nokia analyzed more than 50 million lines of code in two weeks with Cursor
Two Nokia engineers used Cursor to analyze a large C, C++ and Go codebase before breaking up a monolith. The analysis had been expected to need a much larger expert team.
As reported by Cursor: 'two engineers analyzed more than 50 million lines of code in two weeks'.
Turn a Figma frame into code by connecting the Figma MCP server
Figma's hosted MCP server gives a coding agent the variables, components and layout data of a frame you link to, so the code it writes matches the design.
The agent gets design context such as variables, components and layout for the selected frame.
Guides
Best AI Agents in 2026: Live Rankings by Category
The leading AI agents for coding, design, research, data, marketing, sales, support, HR, finance, legal, DevOps and security, ranked by public usage data that refreshes daily, with prices and free options.
What Is an AI Agent? A Practical Explanation With Real Examples
What makes software an AI agent, how agents differ from chatbots and plain language models, the main types in use today and how to judge one.
Best AI Coding Agents in 2026: Ranked by Usage, Benchmarks and Price
The AI coding agents developers use most, with live download and install numbers, benchmark results, entry prices and a way to choose between terminal, IDE and cloud agents.
Claude Code vs Codex vs Cursor: Usage, Price and Benchmarks Compared
The three most discussed AI coding agents side by side on live data: downloads, installs, GitHub activity, release cadence, benchmark results and pricing.