AI support risked hallucinations. Now, 20 specialized models fact-check every answer against strict company policies.
A customer service software provider supporting a hypergrowth trajectory since 2011, serving thousands of businesses with high-volume support tools.
Automating support required handling complex inquiry types while strictly protecting against model hallucinations. The system needed to verify that...
“Fin will say, ‘Hey, here's knowledge I think you should add. Here’s an API that, if I had, I could resolve more.’”
Intercom is a SaaS company that specializes in customer communication and engagement.
Cloud computing platform and on-demand infrastructure services.
Worked with Intercom to develop Fin, its AI agent, using Claude models on AWS.
Related implementations across industries and use cases
Agents were slowed by manual searches. AI now resolves 51% of queries—including refunds—freeing humans for strategic work.
Redacting data for security broke reasoning. Now, private channels allow full context, enabling natural dialogue over rigid menus.
Previous AI lagged 20s and lost context. A new copilot now summarizes history and drafts replies in <10s, boosting productivity 30%.
Engineers manually correlated alerts across systems. AI agents now diagnose issues and suggest fixes, cutting recovery time by 35%.
Minor edits required days of crew coordination. Now, staff use avatars to modify dialogue and translate languages instantly.
Lab supply orders were handwritten in notebooks. Digital ordering now takes seconds, saving 30,000 hours for research annually.
Experts spent 15 minutes pulling data from scattered systems. Natural language prompts now generate detailed reports instantly.