- Published on
If you're not following eval-driven development, you're flying blind. Sohan, our founding engineer, reveals how we use lightweight evals to ship fast improvements to our AI product with confidence.
All Posts
- Published on
New features released in April 2025 –– self-service onboarding, 25% reduction in run latency, AI test generation summary, improved UI/UX for reviewing tests, and more.- Published on
It's the battle of the AI coding agents. We put Tusk, Cursor, and Claude Code to the test to evaluate their unit test generation quality and ability to detect latent bugs on a TypeScript codebase.- Published on
New features released in March 2025 –– intelligent usage of Claude 3.7 and Gemini 2.5, reduced latency with parallel test execution, greater flexibility in committing Tusk's tests, and more.- Published on
Learn how DeepLearning.AI, an AI education platform founded by Andrew Ng, used Tusk's AI-powered unit testing to ship faster while preventing critical regressions.