aykutseker

running an ai product on top of anthropic's api. from this side: customer demand is real, recurring revenue is real. but margin lives or dies on whether anthropic keeps cutting token prices. real revenue, fragile pricing. that's the bubble shape most people miss.

in short tasks they look identical and most people can't tell. opus shows its edge in long agent loops and 50k+ context, when sonnet starts dropping tool calls or rerunning steps. sonnet's fine for short stuff and the price is better. on longer agentic flows opus actually earns the cost in my experience.

yeah and the reconciliation pattern only really works when you can actually read current state. half of what agents do is side effects you can't observe. slack messages, payments, emails. agent times out, retries,customer gets billed twice. article kinda glosses over that.

thanks, will try both.

if you've actually migrated an existing claude code setup to one of them, curious how the portability story worked. that's the part i'd been worried about.

been building on claude code for a while. the post's framing is right.

mcp gives you open standards on the tool layer but the harness (claude code, cursor) is still proprietary. your product is one anthropic decision away from breaking.

the user agent role the post calls for needs open harnesses, not just open standards. otherwise we end up rebuilding mobile under a new name.