Available on the Zendesk Marketplace
The documentation is available at the link: https://2app.pro/ai-agent-assist/help/
The AI Agent Assit app has no cost to use or install.
However, there are costs for using the ChatGPT API. The application must use the OpenAI API (Chat GPT-3 maintainer) to be able to perform the integration.
The ChatGPT provides several models for use. ZenAI by default uses the GPT-3.5-Turbo model. GPT-3.5-Turbo is the model that powers ChatGPT and is optimized for conversational formats.
The application allows you to use other ChatGPT models. This is defined in the application settings.
About the prices of each model, we recommend a visit to the OpenAI page: https://openai.com/pricing#language-models
Yes, it is compatible with ChatGPT 4. You can configure this directly in the App, in “Settings” -> “GPT Models”.
The app does not have the feature to train/instruct AI.
The application does not have the feature that allows you to perform searches on other data sources and also does not allow the possibility for training/instruction of the AI.
The content of ChatGPT is based on a large dataset of text, which includes texts in various languages and sources, such as books, web articles, news, and other types of publicly available text on the internet.
You need to create an account on the OpenAI platform: https://platform.
Creating the API token is done on the page: https://platform.openai.
You can provide the API token at app install time, or later by accessing the app’s settings in Zendesk.
Important! To use the API you need to have credits in your OpenAI account.
To open the application in Zendesk, just access the icon next to the ticket editor.
It is also possible to make the application available in the Sidebar. To do so, simply access the application’s configuration in Zendesk and enable the “Display App on Ticket Side Bar” parameter.
To do so, simply access the application’s configuration in Zendesk and enable the “Display App on Ticket Side Bar” parameter.
- Changes to some layout components.
- New component for settings: Speed Dial, Prompts and ChatGPT Templates.
- Customize the Speed Dial.
- Customize the Prompt for ChatGPT.
- Enable config Model.
- Enable Display App On Sidebar.
- Act as Support Analysts and Rewrite a Response.
- Update speed diup layout.
- Using the new model gpt-3.5-turbo.
- Fix error: Sorry, an error has occurred. This model’s maximum context length is XXXX tokens, however you requested YYYY tokens (ZZZ in your prompt; 4000 for the completion).
- Added limit to 3900 characters per request.
- No Data Storage: Our Application does not store any data on our servers. All information exchanged between you and the ChatGPT API is transmitted directly between your device and the OpenAI servers.
- Disclaimer of Warranties and Limitation of Liability: Our Application is provided “as is” and without any warranty or guarantee, express or implied. We do not guarantee the accuracy, timeliness, completeness, or usefulness of any information provided by the ChatGPT API. In no event shall we be liable for any direct, indirect, incidental, special, or consequential damages arising out of or in any way connected with the use of our Application or the ChatGPT API.