Moving from intent-based bots to proactive AI agents
📰 OpenAI News
Zendesk partners with OpenAI to build adaptive service agents that use generative reasoning to resolve customer issues autonomously
Action Steps
- Identify the limitations of traditional intent-based bots
- Explore the use of generative models like Retrieval-Augmented generation (RAG) for basic interactions
- Implement generative reasoning to enable AI agents to plan and execute tasks independently
- Monitor and evaluate the performance of AI agents to ensure they are meeting resolution goals
Who Needs to Know This
Customer service teams and developers at companies like Zendesk can benefit from using proactive AI agents to improve resolution rates and automation, as it allows them to provide more efficient and effective support to customers
Key Insight
💡 Proactive AI agents can improve resolution rates and automation by using generative reasoning to plan and execute tasks independently
Share This
💡 Zendesk & OpenAI partner to build adaptive service agents that resolve customer issues autonomously
Key Takeaways
Zendesk partners with OpenAI to build adaptive service agents that use generative reasoning to resolve customer issues autonomously
Full Article
# Zendesk uses OpenAI to build adaptive service agents focused on resolutions | OpenAI
[Skip to main content](https://openai.com/index/zendesk#main)
[](https://openai.com/)
* [Research](https://openai.com/research/index/)
* Products
* [Business](https://openai.com/business/)
* [Developers](https://openai.com/api/)
* [Company](https://openai.com/about/)
* [Foundation(opens in a new window)](https://openaifoundation.org/)
[Try ChatGPT(opens in a new window)](https://chatgpt.com/)
* Research
* Products
* Business
* Developers
* Company
* [Foundation(opens in a new window)](https://openaifoundation.org/)
[Try ChatGPT(opens in a new window)](https://chatgpt.com/)
OpenAI
Table of contents
* [Moving from intent-based bots to proactive AI agents](https://openai.com/index/zendesk#moving-from-intent-based-bots-to-proactive-ai-agents)
* [A new class of AI agents, built for resolution](https://openai.com/index/zendesk#a-new-class-of-ai-agents-built-for-resolution)
* [Shifting from static flows to adaptive reasoning](https://openai.com/index/zendesk#shifting-from-static-flows-to-adaptive-reasoning)
* [Benchmarking the best models for every use case](https://openai.com/index/zendesk#benchmarking-the-best-models-for-every-use-case)
* [Accelerating the path to 80% automation](https://openai.com/index/zendesk#accelerating-the-path-to-80percent-automation)
March 27, 2025
# Zendesk uses OpenAI to build adaptive service agents focused on resolutions
[Try for free(opens in a new window)](https://chatgpt.com/team-sign-up?promo_campaign=team-1-month-free&utm_campaign=WEB-team-1-month-free&utm_internal_medium=referral&utm_internal_source=openai_business)[Contact sales](https://openai.com/contact-sales/)
Loading…
Share
Zendesk has helped businesses deliver great customer experiences for over a decade. Its platform powers more than 4.6 billion resolutions each year.
In early 2023, Zendesk began working closely with OpenAI to explore how AI could reshape service and product development. Today Zendesk is [piloting a new class of AI agents(opens in a new window)](https://www.zendesk.com/newsroom/articles/relate-2025-resolution-platform/), powered by OpenAI models, that not only manage entire conversations but plan and execute responses autonomously:
* Reducing setup time from **days to minutes**
* Increasing automation rates toward**80%**
* Giving teams**full control** over how the AI behaves
## Moving from intent-based bots to proactive AI agents
Even the most sophisticated service platforms face limitations when it comes to traditional automation. The standard model relied on intent classification: predict an intent, trigger a predefined dialogue or workflow, and hope the customer followed the script.
This setup worked for structured interactions, but broke down quickly with nuance, follow-ups, or edge cases.
“The old world was message in, response out,” says Adrian McDermott, CTO at Zendesk. “Real customers change their minds, ask clarifying questions, and expect the AI to follow along naturally. In service, the only outcome that matters is resolution, and until now, bots have been somewhat limited in their ability to achieve it.”
Zendesk began working with OpenAI to adopt a generative approach using Retrieval-Augmented generation (RAG) for basic FAQ interactions. Today, their focus has shifted to generative reasoning that enables AI agents to plan and execute tasks independently.
[](https://openai.com/)
* [Research](https://openai.com/research/index/)
* Products
* [Business](https://openai.com/business/)
* [Developers](https://openai.com/api/)
* [Company](https://openai.com/about/)
* [Foundation(opens in a new window)](https://openaifoundation.org/)
[Try ChatGPT(opens in a new window)](https://chatgpt.com/)
* Research
* Products
* Business
* Developers
* Company
* [Foundation(opens in a new window)](https://openaifoundation.org/)
[Try ChatGPT(opens in a new window)](https://chatgpt.com/)
OpenAI
Table of contents
* [Moving from intent-based bots to proactive AI agents](https://openai.com/index/zendesk#moving-from-intent-based-bots-to-proactive-ai-agents)
* [A new class of AI agents, built for resolution](https://openai.com/index/zendesk#a-new-class-of-ai-agents-built-for-resolution)
* [Shifting from static flows to adaptive reasoning](https://openai.com/index/zendesk#shifting-from-static-flows-to-adaptive-reasoning)
* [Benchmarking the best models for every use case](https://openai.com/index/zendesk#benchmarking-the-best-models-for-every-use-case)
* [Accelerating the path to 80% automation](https://openai.com/index/zendesk#accelerating-the-path-to-80percent-automation)
March 27, 2025
# Zendesk uses OpenAI to build adaptive service agents focused on resolutions
[Try for free(opens in a new window)](https://chatgpt.com/team-sign-up?promo_campaign=team-1-month-free&utm_campaign=WEB-team-1-month-free&utm_internal_medium=referral&utm_internal_source=openai_business)[Contact sales](https://openai.com/contact-sales/)
Loading…
Share
Zendesk has helped businesses deliver great customer experiences for over a decade. Its platform powers more than 4.6 billion resolutions each year.
In early 2023, Zendesk began working closely with OpenAI to explore how AI could reshape service and product development. Today Zendesk is [piloting a new class of AI agents(opens in a new window)](https://www.zendesk.com/newsroom/articles/relate-2025-resolution-platform/), powered by OpenAI models, that not only manage entire conversations but plan and execute responses autonomously:
* Reducing setup time from **days to minutes**
* Increasing automation rates toward**80%**
* Giving teams**full control** over how the AI behaves
## Moving from intent-based bots to proactive AI agents
Even the most sophisticated service platforms face limitations when it comes to traditional automation. The standard model relied on intent classification: predict an intent, trigger a predefined dialogue or workflow, and hope the customer followed the script.
This setup worked for structured interactions, but broke down quickly with nuance, follow-ups, or edge cases.
“The old world was message in, response out,” says Adrian McDermott, CTO at Zendesk. “Real customers change their minds, ask clarifying questions, and expect the AI to follow along naturally. In service, the only outcome that matters is resolution, and until now, bots have been somewhat limited in their ability to achieve it.”
Zendesk began working with OpenAI to adopt a generative approach using Retrieval-Augmented generation (RAG) for basic FAQ interactions. Today, their focus has shifted to generative reasoning that enables AI agents to plan and execute tasks independently.
DeepCamp AI