Invenias AI Assistant (Formerly Copilot) FAQ

This article contains answers to frequently asked questions about Invenias AI Assistant (formerly Copilot) and AI. Invenias AI Assistant is an optional feature that is available to all Invenias customers. To request this feature, please reach out to your Account Manager.

Related Articles and Resources

General Interest

What is Generative AI?

Generative AI is a type of AI system that is powered by Large Language Models (LLMs) and can be used to create new content in response to your questions or instructions, which are referred to as "prompts". The most well-known generative AI system is ChatGPT.

What is an LLM?

An LLM, or Large Language Model, is a deep learning model that has been pre-trained on vast amounts of data and is used to power generative AI.

Which LLM should I choose? Which model is best for me?

We currently support Azure and OpenAI. Selecting the right LLM depends on factors like your number of users, the number of requests they might make per day, how much data you have (in terms of number and size of resumes/CVs), and what speed you’re looking for.

If I choose OpenAI as my LLM provider, do I need to purchase ChatGPT or an API model?

If using OpenAI, you'll need to purchase an API model.

How do I enable my LLM so I can use Invenias AI Assistant?

You can start by reviewing Enabling Invenias AI Assistant (Formerly Copilot). Each LLM has its own instructions for getting started, so we recommend reviewing the OpenAI Quickstart Guide or Create and deploy an Azure OpenAI Service Resource or other help content from the providers. As part of the enablement process you will need to provide details from your LLM such as the model and API key.

What is a token? What's an average token length?

A token is a unit of data, such as a word or a punctuation mark, that an AI system processes. For example, when you ask AI "What is a token?" AI looks at each word, space, and piece of punctuation to understand and respond to your question. Each token is roughly four characters for typical English text. For more information, please see this article: What are tokens and how to count them?

Enablement

How do I get started with Invenias AI Assistant?

All Invenias customers can take advantage of AI Assistant. You'll need to choose your LLM and model, speak with your Account Manager to review and sign the legal addendum, and respond to Invenias Support when they reach out to enable AI Assistant in your ATS. For additional enablement details, see Enabling Invenias AI Assistant (Formerly Copilot).

If you're ready to get started, speak with your Account Manager.

If a newer model is released, will I have to buy that newer model, or will it automatically update with the newer version?

You would need to purchase the newer model through your AI provider. Any time you make a model update with your AI provider, make sure you update the details stored in Invenias accordingly.

What if a new version of the same model is released? Will I have to buy that and make the same configuration updates as a newer model?

Newer versions of models are frequently released, and you'll need to manually update the model deploy configuration in your AI provider to the desired version.

Data Security & Privacy

Is data stored in AI Assistant?

No, AI Assistant does not store data. Only prompts are stored, not the data used.

Is data always available to the AI provider, or only when I provide access?

Information is only passed to the AI provider when you select or enter a prompt.

What information is available to push to the AI provider/AI model?

AI Assistant uses the following data sources to generate prompts:

  • CV/Resume: The information in the person’s CV/Resume pane (not the attached Document marked CV/Resume)
  • My Details: Your name, job title, and company name, as listed on your Invenias user profile. This is used to create a signature/footer in email prompts.

Can AI Assistant pull information from LinkedIn?

No, AI Assistant does not have this functionality.

Can I customize what data is available to send to the AI provider?

No, AI Assistant does not have this functionality.

Are there any GDPR implications for EMEA customers using AI Assistant?

Please view Bullhorn’s Commitment to the General Data Protection Regulation (GDPR) or speak to your compliance officer.

Does AI Assistant use client data to train AI or machine learning functionality, or in any other way to develop Bullhorn products?

AI Assistant utilizes a "Bring Your Own Model" implementation, so Bullhorn doesn’t host, train or control the AI model. This is completely owned and controlled by the customer.

Does AI Assistant share data between customers?

No, since AI Assistant integrates with the customer-owned AI model for each specific customer ATS instance, no data is shared between customers.

Where is the server for our LLM instance housed? Is it with Bullhorn or is it with our AI Provider?

You will need to ask OpenAI or Azure for details on where your LLM instance is housed.

Using AI Assistant

Can I customize the available default prompts?

No, AI Assistant does not have this functionality.

I've refined my prompt but I prefer the version I had before. How do I retrieve a previous version of a prompt?

AI Assistant maintains your conversation history while you have the record open, so you can scroll back up to the previous version of your prompt. However, your AI Assistant conversation history isn’t saved when you navigate away from a record, so we recommend copying and pasting any prompts you like into a document or note so that you don't lose them.

Can AI Assistant be limited at a user level?

AI Assistant cannot currently be limited at a user level, so once it is enabled everyone will have access. The ability to restrict AI Assistant by individual users will be coming in a future enhancement.

What can I do if I am seeing unexpected results?

AI Assistant pushes data from the person’s CV/resume to the AI provider. If you're seeing unexpected results, we recommend checking the content of the CV/resume to ensure that it contains the correct information.