
Who writes the agent's tests: three ways to define what's correct
Who writes an agent's tests defines what counts as correct. Three levels of input: spec and tests by hand, examples the agent turns into tests, or the repo's suite as the evaluator.
Tag archive

Who writes an agent's tests defines what counts as correct. Three levels of input: spec and tests by hand, examples the agent turns into tests, or the repo's suite as the evaluator.
What is a Local Test? A local test is a small script that runs on your computer inside your...
An AI-generated test that passes proves nothing until it can go red. Mutation testing exposes the phantom tests, with a Go example to prove it.
How to write unit tests for a production Bash script without an external framework. Mocking patterns, function isolation, readable assertions.
You can't hit the real Binance API in tests. ExchangeClient interface, mockgen mocks, httptest for parsing real responses, testcontainers for PostgreSQL integration tests.
Preparing for a certification exam can be really stressful without the right resources. Professional...
How We Migrated 100k Tests from Jest to Vitest at Shopify in 2026 In early 2026, Shopify’s...
In 2026, multi-cloud IaC deployments average 47% longer init times than single-cloud equivalents—we...
In Q1 2026, our 12-engineer DevOps team ran 1,200 multi-cloud IaC deployment cycles across AWS,...
Rust 1.83’s stabilized test features cut unit test boilerplate by 62% compared to 1.70, but 73% of...
In a 2024 internal benchmark of 40+ Rust production codebases, teams using Codeium 2.0 to generate...