Amol Walunj

We usually think of breaking changes as API updates, database migrations, or features that stop working after a release.

But I've been thinking about a different kind of breaking change.

I have been thinking about this while working on integrations with third-party platforms.

Imagine a user connects their CRM, payment provider, or another external service. Everything works initially, but a few weeks later, an API token expires or the provider starts rate-limiting requests.

We talk a lot about AI automating work, but setting up AI products still requires a surprising amount of manual effort.

Take an AI customer support agent. You need to connect integrations, configure instructions, define business rules, set permissions, test different scenarios, and keep everything updated.