ChatGPT was great at answering questions, but it lived in a bubble. It only knew what you typed into it. For companies, that was the dealbreaker. The work that actually mattered sat in their files, their repos, and their internal tools, and ChatGPT couldn't see any of it. People were pasting whole documents into the chat just to get a useful answer, which kind of defeated the point.

I co-led the end-to-end design of Connectors (now part of Apps in ChatGPT), the feature that let ChatGPT reach into those tools and work from real data. The hard part was never the "connect" button. It was trust. The moment a model starts reading someone's private documents, the questions get personal. What is it looking at? Can I stop it? Where did that answer actually come from? Get those wrong, and no security team would ever turn it on.

So I spent most of my time on the moments people never notice. How ChatGPT asks to connect an account, and what it promises in return. How it shows what it's about to open before it opens it. How it pauses to let you approve an action instead of running ahead on its own. I designed the waiting, too, those few awkward seconds while it searches, so it reads as working rather than frozen. And I pushed hard on citations, so every answer pointed back to the exact file it came from and people could check the source instead of taking the model's word for it.

None of it could be a one-off. Drive, GitHub, and SharePoint each behave differently under the hood, but to the person using them they all had to feel like the same calm, predictable thing. A lot of the work was finding the shared language that held up across very different tools, so connecting your tenth app felt as obvious as your first.

The payoff was simple. Companies could finally bring their own knowledge into ChatGPT and trust what came back. That trust layer is a big part of what made ChatGPT usable inside the enterprise, and it became the groundwork for the apps teams plug in today.