IMO you're better off investing in tooling that works with or without LLMs:
- extremely clean, succinct code
- autogenerated interfaces from openAPI spec
- exhaustive e2e testing
Once that is set up, you can treat your agents like (sleep-deprived) junior devs.
Been using gRPC with json transcoding to REST on a greenfield project. All auto generated clients across 3 languages. Added frontend wrapper to pre-flight auth requests so it can dynamically display what users are allowed to do.
Claude Code has been an absolute beast when I tell it to study examples of existing APIs and create new ones, ignoring bringing any generated code into context.
Autogenerated interfaces from openAPI spec is so key - agents are extremely good at creating React code based on these interfaces (+ typescript + tests + lints.. for extra feedback loops etc..)
Once that is set up, you can treat your agents like (sleep-deprived) junior devs.