The HR bot use case is very close to my domain - literally one of the teams reporting to me are maintaining the HR bot for a large enterprise - and it is a legal minefield. Whatever the bot provides as a response could be legally binding, according to legal. Examples of the kind of prompts we get in a many-thousands sized org:
- What are my p/maternity entitlements?
- When will I be promoted?
- What will the bonus pool be this year?
- What will happen to me if my boss finds out I have been slacking off?
and many more examples of prompts that HR/legal simply will not accept a vague, or worse: incorrect, response to. Each of those types of questions require specific and considerate knowledge that LLMs simply cannot produce.
- What are my p/maternity entitlements?
- When will I be promoted?
- What will the bonus pool be this year?
- What will happen to me if my boss finds out I have been slacking off?
and many more examples of prompts that HR/legal simply will not accept a vague, or worse: incorrect, response to. Each of those types of questions require specific and considerate knowledge that LLMs simply cannot produce.