How to train an AI agent with internal company documents and policies
Training an agent with documents means attaching files — a vacation policy, an HR manual — to an AI agent, so it can answer questions based on that content, even without a linked table. In Jestor, the same agent keeps context across follow-up questions in the same conversation.
The problem with important information living outside tables
Not all important company information lives in a table: internal policies and manuals tend to be scattered, and without an easy way to look them up, the same questions end up getting repeated to HR.
- Document-based, not table-based: answers based on attached files.
- Fewer repeated questions: about policies that are already documented.
- Customizable by process: an agent can represent HR, finance, or support.
- Context maintained: follow-up questions don't lose the thread of the conversation.
How to train an agent with documents in Jestor
- Create an AI agent: inside the agents area.
- Attach the reference documents: vacation policy, manual, internal documentation.
- Configure the agent's purpose: for example, to represent the HR process.
- Test it with a real question: and check whether the answer reflects the attached document.
- Use follow-up questions: the agent keeps the conversation's context.
How to configure it in Jestor: a practical example is an HR agent with the vacation policy attached — when someone asks about it, the agent checks the document directly, without anyone needing to open the file manually.
Why choose Jestor to reduce repeated questions to HR or internal support?
HR and internal support teams spend real time answering the same questions about already-documented policy — an agent trained on those documents absorbs a good chunk of that volume, without requiring anyone to memorize or rewrite the policy as an FAQ.
Frequently Asked Questions
Does the agent need a linked table to work with documents? No, you can train an agent with just attached documents, no table.
Does the agent keep context across questions in the same conversation? Yes, it can answer follow-up questions while keeping the previous context.
Can this agent be used by any area of the company? Yes, it can be configured to represent any process, such as HR, finance, or support.
Video Tutorial: Step by Step
Check out other practical tutorials on the Jestor YouTube channel.
Get to know Jestor
With Jestor, your vacation policy or internal manual becomes an agent that answers on its own, without repeating the same explanation every week.
Visit the official Jestor website and scale the efficiency of your operation.