How Numan scaled safe, AI-first support with Fin AI Agent
As support volume surged to nearly 70,000 conversations a month, Numan needed a more scalable solution that could deliver fast, accurate answers and ensure that all medical queries were assigned to trained clinicians. At the time, Numan was using another customer service platform – but as volumes surged to 70,000 conversations a month, it became clear it wasn’t built to scale with intelligence.
- Agent or tool
- Fin
- Topic
- Customer Support
- Reported on
- Case study (Fin)
- Added
- 2026-11-11
Why it matters
Support is repetitive and time-sensitive. Agents can draft answers, look things up and handle simple requests, so people can focus on the tricky ones. It is one of 591 sightings filed under Customer Support on Agent Sightings (number 405 by interest), and one of 7 involving Fin.
How you could try it
Here is a reusable prompt, written by us in our own words, that captures the task. Paste it into Fin or any similar agent and adjust the details to your situation.
I want an agent to handle routine customer questions end to end, and pass anything unclear to a person.
Tip: Start small: run it once on a low-stakes example, read what the agent did, and only then let it run on real work.
Source
Read the original first-hand account on Case study (Fin): https://fin.ai/customers/numan. Our summary is a paraphrase; details are in the source.
Built an AI agent? Feature your agent on Agent Sightings, free submission or a featured spot.
202 sightings of this same job
- ASAPP brings human-level AI to customer service with Claude
- Agentforce resolves over 75% of visitor issues on the Salesforce Help site.
- Discover OpenTable’s secret sauce to building AI agents that people actually want to use.
- Eneco moves to Microsoft Copilot Studio to better support over 1.5 million customers
- Finnair’s Finnish hospitality shines with Agentforce's 24/7 support.
- Gradient Labs transforms financial services customer support with Claude