I've built 12+ AI agent systems across development, DevOps, and data operations. Here's why the current hype around autonomous agents is mathematically impossible and what actually works in production.
Generally, the agent will use the whole repo. The workflow is that you get them to make the changes to satisfy the query, then run tests, and use the feedback from the tests to iterate. They’re getting surprisingly good at this nowadays for common tasks.
Generally, the agent will use the whole repo. The workflow is that you get them to make the changes to satisfy the query, then run tests, and use the feedback from the tests to iterate. They’re getting surprisingly good at this nowadays for common tasks.