Delivering high-performance customer support
The company uses a combination of OpenAI’s models—including GPT‑3.5, 4, 4o, 4 Turbo, and OpenAI o1‑mini—to deliver agentic bots that go beyond response generation and service the entire customer lifecycle. ## Delivering fast, nuanced, and scalable solutions with OpenAI Decagon’s customers require scalable, high-quality support that can handle complex inquiries. With OpenAI’s models, the Decagon team was able to architect a flexible solution that allows clients to fully customize their workflows to their needs.
- Agent or tool
- OpenAI
- Topic
- Customer Support
- Reported on
- Case study (OpenAI)
- 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 554 sightings filed under Customer Support on Agent Sightings (number 389 by interest), and one of 25 involving OpenAI.
How you could try it
Here is a reusable prompt, written by us in our own words, that captures the task. Paste it into OpenAI 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. The tool in the source case was OpenAI.
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 (OpenAI): https://openai.com/index/decagon. 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.
Browse more like this
Related sightings
- Ringg’s AI agents resolve up to 65% of customer calls with OpenAI
- How avatarin built a 24/7 retail agent with GPT-Realtime
- Here’s why AI is the key to more empathetic customer experiences
- Draft replies and promo codes for L'Oréal support advisors
- Warp’s big bet on building open source with GPT-5.5
- Unify engineers growth by using the right model for every task