Trusting AI-generated code you didn't read line by line: trust the harness you built, not the model. AI now assists ~42% of committed code.
Secure Spring Boot 4 messaging over RabbitMQ AMQP 1.0 with OAuth2 and the native spring-rabbitmq-client: same Keycloak scopes, simpler in-place token refresh.
Secure your Spring Boot app's messaging with OAuth2, not guest/guest. RabbitMQ joins your HTTP APIs' Spring Security setup as a resource server.
When I started ralphctl, 'harness' was a word from one Anthropic post. Now it's the third phase of AI engineering, there's an arXiv paper, and the whole field has standardized on the patterns I built early.
Agent harnesses orchestrate code generation. Delivery is a longer pipeline. Here's the mental model I've been using to plug team, tools, context, and models into one value stream, and where the agent harness fits inside it.
Story points, t-shirts, fruit salads, and now tokens. A messy, honest look at why estimation was already broken before AI showed up, and what it takes to keep planning sane when the tools move faster than the humans.
Anthropic's first harness article inspired ralphctl. Their second one on generator-evaluator loops pushed me to build an evaluator for v0.2.0, and the tool changed identity.
