Policies let you set fine-grained rules about who can access which data and under what conditions. While tags and roles control broad visibility, policies add another layer — they govern what questions people can ask and what answers they can receive.Documentation Index
Fetch the complete documentation index at: https://docs.humanintelligence.com/llms.txt
Use this file to discover all available pages before exploring further.
How policies work
A policy is a rule that says: “This group of people cannot see this type of data in this context.” Policies are enforced automatically whenever someone interacts with Human Intelligence, including through connected AI assistants like Claude. When a user asks a question, Human Intelligence checks the applicable policies before returning an answer. If a policy restricts the query, the user sees a clear explanation of why the data isn’t available to them — not an error, just a boundary.Examples
Policies are flexible. Here are a few common patterns:- Managers can’t see individual performance scores — only aggregated team-level data.
- Only HR can access compensation data — even if other teams have access to the underlying data source.
- Recruiters can’t view demographic breakdowns of candidate pools below a minimum group size.
- Finance sees headcount numbers but not the underlying employee-level detail.
Policies are available on the Enterprise tier. If you’re on a different plan, tags and roles handle your access control.
Policies and AI assistants
When you connect an AI assistant to Human Intelligence, policies are enforced at query time. The assistant won’t surface restricted data in its answers, even if a user phrases their question creatively. This means your governance rules travel with the data, no matter how people access it.Want to learn more about policies or upgrade to Enterprise? Contact our team and we’ll walk you through it.