
The challenge
NDM’s constraint was not ambition; it was capacity.
NDM needed to accelerate customer change without adding delivery risk. The goal was to increase reliable coverage, shorten release cycles and prove measurable throughput gains inside the teams and metrics already in place. Limited SDET availability made it harder to sustain automated test coverage at the level needed for faster releases. Coverage had held at around 65% across key parts of the application suite, but after crunch periods where engineers were pulled into manual testing, coverage fell to 25–30% in parts of the stack, and the remaining tests became harder to trust. Adding headcount alone would not close the gap quickly enough, so NDM turned to Godel’s forward-deployed engineers to rebuild pace and confidence. NDM protected quality by swarming manual testing around each release. But that protection came at a price: slower feature delivery, longer release cycles and a reduced pace of change for the 3 million members across healthcare, education, caring and charity. NDM did not need more experimentation. It needed a delivery model that could restore automation capacity fast, prove impact in live workstreams and create the foundation for agentic delivery.
The solution
The answer wasn’t headcount. It was a new way to deliver.
Godel’s agentic engineers embedded Claude Code agents directly into NDM’s daily test automation work, creating a reusable delivery system rather than a one-off AI trial. That momentum is already visible inside NDM, where teams dedicate time each week to building new AI skills and agents across the business. For NDM, the outcome is more than faster test creation. It is a working proof that AI agents can be introduced into live engineering delivery with measurable impact, trusted safeguards and a clear route from productivity gain to customer value.


