{"id":75126,"date":"2026-10-20T05:42:46","date_gmt":"2026-10-20T12:42:46","guid":{"rendered":"https:\/\/birdeye.com\/blog\/?p=75126"},"modified":"2026-10-20T05:42:47","modified_gmt":"2026-10-20T12:42:47","slug":"removery-ai-human-in-the-loop","status":"publish","type":"post","link":"https:\/\/birdeye.com\/blog\/removery-ai-human-in-the-loop\/","title":{"rendered":"Care isn\u2019t automated. How Removery decides what AI should never handle."},"content":{"rendered":"\n

\u201cJust because it looks pretty on the screen, don\u2019t assume that it\u2019s right,\u201d<\/strong> said Michael DeHaven of Removery, after small glitches slipped past his tests. The same discipline tells him where AI stops. The last thing to hand a non-human agent, he said, is \u201ctrue care for a customer.\u201d<\/p>\n\n\n\n

Summary<\/strong><\/h2>\n\n\n\n

At Birdeye View 2026, Michael DeHaven, Chief Systems and Digital Officer at Removery (165+ studios), and moderator Sanjay Kini, Birdeye\u2019s Chief Customer Officer, discussed what AI should and should not own. Removery has AI agents test each other\u2019s work before humans review it, uses AI to respond to positive reviews and route problems, and keeps clinical data and customer care in human hands. This post covers each guardrail.<\/p>\n\n\n\n

What did Removery learn from trusting AI output too quickly?<\/strong><\/h2>\n\n\n\n

\u201cI wasn\u2019t doing enough QA,\u201d DeHaven said of the early phase. He ran unit tests, saw them pass, and moved on. Then small glitches started showing up in work he had thought was perfect. Coding quality from AI agents is \u201cnight and day\u201d better than a year ago, he said, but it still makes mistakes, and he does not expect it ever to be perfect.<\/p>\n\n\n\n

Kini hit the same wall in Birdeye\u2019s own support team. His head of technical support ran case data through Claude and got a polished analysis quickly. Something looked wrong, so he asked whether it was right or whether Claude was guessing. The reply was \u201coh, I guess.\u201d Kini remembered Claude wasn’t sure, but nothing in the polished answer suggested that. A confident tone tells you nothing about whether the answer is reliable.<\/p>\n\n\n\n

How does Removery verify what AI builds?<\/strong><\/h2>\n\n\n\n

DeHaven rebuilt his process around a requirement: multiple rounds of QA before anything is pushed to GitHub.<\/p>\n\n\n\n

One evening, a request landed on his desk that was not on his priority list. Before leaving, he gave an AI agent the problem and had it research three code bases. It came back with a dev story and acceptance criteria. He approved it, and by morning the agent had built the whole thing, with pieces already deployed. Four agents ran QA at the same time. They found errors, the fixes went in, and the whole loop ran three times before the work was cleared to push.<\/p>\n\n\n\n

For another project, so complex that eight QA agents were working against it, the agents were \u201cantagonizing\u201d the code base and trying to break it in every possible way. Human QA still has a job to do as well. The right number of agents depends on the project, but the principle holds: the agent that builds something should not be the only one vouching for it.<\/p>\n\n\n\n

Where does Removery draw the line with customers?<\/strong><\/h2>\n\n\n\n

For reviews, the rule is simple. When someone writes a four- or five-star review, having AI react in a relevant way \u201ccan be absolutely amazing,\u201d DeHaven said. A quick \u201cthanks for writing that review, you\u2019re awesome\u201d is something he is happy to let a bot handle.<\/p>\n\n\n\n

Constructive reviews, and sometimes negative ones, route to people, so the response is meaningful and someone takes action. Sometimes that means identifying the client and reaching out personally to make sure they are taken care of. \u201cIf somebody\u2019s having a problem,\u201d he said, \u201cdon\u2019t lose the personal touch.\u201d PennyMac draws a similar line, which we cover in our post on regulated brands.<\/p>\n\n\n\n

AI still does the routing. A studio is not always the right place to send an issue, so Removery wants to connect each customer with whoever can solve it fastest and best. AI can make that call instead of fixed procedural logic. Store teams still learn from the feedback, and DeHaven expects the right people to have more time to do excellent work instead of moving each customer through.<\/p>\n\n\n\n

What data does Removery keep away from AI?<\/strong><\/h2>\n\n\n\n

Removery\u2019s work is considered a medical service in many states and countries, DeHaven said, so the company separates customer data from clinical data. Most of the time, clinical data stays private and available only to humans. Other customer data can be queried by chatbots, people, and dashboards alike.<\/p>\n\n\n\n

His goal is for humans and AI agents to \u201ccoexist\u201d in the same environment and complement each other. Data has to be accessible, he said, but at the right moment and with privacy controls. Legal questions work the same way. He often asks Claude or Gemini what a state law change means, then decides whether it needs the humans in legal for an official opinion.<\/p>\n\n\n\n

How does Birdeye support a human-in-the-loop review workflow?<\/strong><\/h2>\n\n\n\n

DeHaven credits a Birdeye feature built for exactly this split. Birdeye Reviews<\/a>, powered by Jay, the marketing AI coworker<\/a>,<\/strong> lets teams decide which reviews AI answers and which go to a person.<\/p>\n\n\n\n