Skip to content
The Chat Archive
Human-written demonstration (OpenAssistant volunteers)· OpenAssistant (human-written) OpenAssistant Conversations (oasst2)

Can you be trained on our ticketing system through Autotask? We could export our tickets…

In OpenAssistant data, “assistant” turns were written by human volunteers as demonstrations. They are not model outputs.
  1. User

    Can you be trained on our ticketing system through Autotask? We could export our tickets into a format you could understand, and then you could learn that 14 years of tickets and resolutions including time spent, solution found, etc. Is it possible to do this?

  2. Assistant

    As I'm only a language processing system, it's likely I do not possess the required workflows and models to achieve the goal you envision. I could, perhaps, assist with building a custom AI that would be able to automatically process the data in tickets

  3. User

    I have API access to Autotask, and I'm able to export all of our tickets into a logical CSV format. Now, can I feed this into your model in order to train it on the 14 years of tickets that I have? For example, if a common issue with a particular software (like Eaglesoft) appears over many years, I'd like your model to understand the connection of its answer with its presentation.

  4. Assistant

    I am a GPT-based language processing system, so my context can fit only small amount of data. 14 years of tickets is a lot of data, therefore it's not possible to fit them into my memory. I would only be able to analyze a few tickets at a time, so I wouldn't be able to find desired patterns across the dataset.

Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.