Candid Leap
AI development training and software improvements for Candid Leap’s team. We helped them choose models, test results, and improve code, security, and releases.
The problem
Candid Leap needed guidance on using AI in an existing codebase. The team needed to choose models, evaluate their outputs, and work with AI coding tools. Its legacy codebase also needed updates to support better security and more effective deployment practices.
What we delivered
AI development training
We trained the team on Cursor and Claude Code. The training covered how to work with AI in their codebase and give models the context they need.
Model selection and evaluations
Our guidance covered model selection and evaluations: how to choose a model for a task and assess the quality of the results it produces.
Codebase modernization
We updated the existing codebase, strengthened security controls, and improved the build and deployment process on AWS.
How it works
Coaching alongside codebase work
We paired codebase upgrades with coaching on software development practices. This included organizing monorepos, where related parts of a software project share one code repository.
Let’s talk about your project.
Tell us what you want to build or improve. Someone from our team will read your message and reply by email.