Every SaaS company seems to be racing to bolt AI onto its support — and often for the wrong reason. Too often, the goal is to deflect tickets and make humans harder to reach. We think that gets it backwards. AI in support should get you to the right help faster, not put a wall between you and a person.
We’ve added AI to Gearset support too. We built Gearbot on Fin — formerly Intercom, and now being acquired by Salesforce. But it’s worth being clear about what that AI sits on top of.
Gearset’s support is consistently rated among the best in Salesforce DevOps: top marks on G2 and the AppExchange, fast responses even at peak volume, and the same level of help for every customer, with no higher tier to buy your way into. The people answering you understand metadata, deployment errors, and Git integration, because that’s the work they do every day.
That’s why, when we decided to bring AI into support, we made it completely optional.
What optional AI support actually means
When you reach out through in-app chat, you choose the kind of help you want. If a support engineer is free, you talk to a human straight away. If there’s a wait, we tell you up front roughly how long it’ll be — so you can wait a few minutes for a person, or get going now with Gearbot.
Either way, you’re making an informed choice, not guessing. Not “AI first”. Not “AI unless you fight your way to a person”. Just your options, the trade-offs, and the power to pick.
This matters because of where Gearset sits. You’re working with deployments, data, and production Salesforce orgs, where being unblocked correctly matters more than being unblocked fast. Our users are engineers and admins who can tell instantly when a vendor cares more about closing a ticket than solving a problem. Forcing AI on that audience doesn’t build trust — it erodes it.
Three ways to get help
We think about support as three complementary channels, not a hierarchy:
- Documentation, for when you’d rather read and solve it yourself. Fast, self-serve, and no waiting.
- Gearbot, for instant answers to questions that have known answers. It’s strong at the things AI does well: pointing you to the right doc, walking through common how-tos, and surfacing known issues. Because it draws on past support engineer responses and Gearset documentation, it gives you more than a general-purpose model like ChatGPT or Gemini can.
- Support engineers, for the edge cases, the complex problems, and anything account-specific. These are the questions that need judgment, context, and someone who can dig in alongside you.
The point isn’t to crown a winner. Each channel does something different, and we want to land you in the right one for the question you actually have. Engineers bring judgment and years of deep Salesforce experience for the nuanced, high-stakes problems. Gearbot is quick, and it’s hard to beat when you just need a straight answer or a pointer to the right doc.
What we saw before launch
For the six months leading up to release, our support engineers reviewed Gearbot’s answers, sharpened its accuracy, and worked out how to correct it when it got things wrong.
The results held up. When offered the choice, 35% of users chose Gearbot rather than wait for a person. Out of the box, before further refinement, our team rated 70% of Gearbot interactions as Good or Acceptable. We also watched Gearbot mirror and reference the answers our engineers had given users in the past — years of support knowledge, made instantly available.
The principle underneath it all
AI hasn’t changed what good support is. It’s still about getting you to the right answer, in the way that suits you, as fast as the problem allows. AI helps us do that better. It’s not a replacement for our engineers, and it’s not something we’ll ever force on you.
World-class support, on your terms.
