Evaluating Agents, Models, and Settings on Your Own Tasks
← Back to Blog & Articles Public benchmarks do not tell you whether an agent will work on your codebase. A small evaluation built […]
← Back to Blog & Articles Public benchmarks do not tell you whether an agent will work on your codebase. A small evaluation built […]
← Back to Blog & Articles For iOS apps, release involves certificates, provisioning profiles, and App Store review. This makes the release path a […]
← Back to Blog & Articles Tests give an agent concrete feedback and give you evidence that the code works. The quality of those […]
← Back to Blog & Articles SwiftUI makes screens easy to write, which is why agents produce them readily. The subtle issues are in […]
← Back to Blog & Articles Swift Package Manager makes it easy to split an app into well-defined modules. That structure also helps agents […]
← Back to Blog & Articles An agent that can run commands can also run the wrong ones. Controls on commands and secrets are […]
← Back to Blog & Articles A new teammate gets an onboarding guide. An agent needs the same, written in a form it can […]
← Back to Blog & Articles A coding agent is, at its core, a short loop. Building a small one is the best way […]
← Back to Blog & Articles Running a coding model on your own hardware keeps source code in-house, but the model must fit your […]
← Back to Blog & Articles Coding agents can read a project, edit multiple files, and run builds. For iOS teams, the question is […]