Tag
The author shares lessons from putting an AI agent with write access into production, explaining that retry logic inside the agent loop fails when the process dies. They advocate for treating side-effectful tool calls as durable background jobs with idempotency keys.
River is a robust, high-performance job processing system for Go and Postgres, emphasizing transactional enqueuing to avoid distributed system pitfalls.
After reviewing 14 AI SaaS MVPs built with tools like Lovable, Bolt, and Cursor, the author identifies five common production failures: untested RLS policies, broken auth refresh flows, background jobs sharing the same connection pool, poorly designed schemas, and missing idempotency for payments/APIs. The fix is 2-3 weeks of targeted infrastructure work.