Prompt caching is a prefix problem
Prompt caching reads cost a tenth of input on most tiers. The prefix that qualifies runs 512 to 4,096 tokens, and that floor picks your cheapest model.
Articles
Practical notes on building, deploying, and shipping real products for solo devs and small teams.
Prompt caching reads cost a tenth of input on most tiers. The prefix that qualifies runs 512 to 4,096 tokens, and that floor picks your cheapest model.
A full disk corrupted my database's write-ahead log and it wouldn't start. The recovery runbook, and ops habits I deferred until Saturday made them due.
TLS breaks on a VPS two ways: silent expiry and deploys that drop sessions. Set it up so renewals run, sessions survive, and you stop worrying about it.
AI gets you a prototype in minutes. The real work is webhooks, deploys, TLS, and refunds. Here is what lives in the gap and why it decides whether you ship.