---
title: "Knowledge Hub and Agent knowledge"
description: "One library for the account, and each agent's own view of what it draws on — grouped, filtered and searchable."
source: https://hiy.ai/docs/knowledge-library
---

# Knowledge Hub and Agent knowledge

Fix your bio once and every agent that uses it is correct.

Your material belongs to the **account**, not to one agent. A source you add
while working on your Support Agent can feed your public twin too, and neither
of them holds a second copy of it. There are two screens, and the difference
between them is the whole idea.

- **Knowledge Hub** — The account's library. Every source you hold, which agent it was added on, which agents draw on it, and the confidential switch.

- **Agent knowledge** — One agent's own view. What it draws on **From Knowledge Hub**, what was **Added here**, and a picker for taking more from the library.

## Knowledge Hub — the account's library

Two tabs, **Sources** and **Add**, the same bar the agent's page uses.

### Sources

Everything the account holds, grouped by **where it came from** — the site,
then the section of it — exactly as an agent's own page groups its material,
and exactly as the picker grouped your pages when you imported them. Each
group says how many sources and how many words it holds, biggest first.

**Search** matches the title, the type, the address and the agent a source was
added on, and **kind chips** — Web pages, Video, Files, Notes, Written by hiy —
narrow to one kind. Both open every group that still has something in it, so
nothing matching stays hidden behind a closed heading.

Each row says:

- **what it is** — the type badge and the word count;
- **where it came from** — the agent it was added on, or *Added here* for
  something added straight to the Hub, which belongs to no agent at all. An
  agent's name links to its own knowledge page, which is where you'd remove a
  source that was added there;
- **which agents use it** — this is the part no other screen can show you. A
  source can feed one agent, several, or none at all;
- **whether it's confidential** — see below.

Removing a source added on an agent isn't here: it lives on that agent, next
to the warning about what removal means. Something added straight to the Hub
has no agent to remove it from, so its Remove is here — and if an agent is
using it, that agent has to stop first.

### Add — to the hub, and to no agent yet

The **Add** tab is the same six-way form as an agent's own — paste text, an
assistant's memory, a file, a web page, a YouTube link, a LinkedIn export —
with one difference, and it's the point of the screen: what you add here goes
into your **library**, not onto an agent.

Nothing uses it until you say so. Open the agent that should have it, go to its
**Add** tab, and pick it out of the hub — search, tick, add. From then on the
hub shows that source tagged with that agent.

It works the other way round too, and always has: anything you add **on an
agent** appears in the hub straight away, tagged with the agent it was added
to. The hub is the whole picture; the agents are what draws from it.

**Note:** Nothing trains straight away, either way. The material is stored and counted,
and it joins an agent's answers at that agent's next train — the one you
confirm on its Overview, or the nightly one. The exception is an agent that has
never been trained at all: it has no index to wait for, so material added to it
is built immediately rather than sitting unanswerable. [Sources](/docs/sources)
and [Training](/docs/training) describe that one.

**How much the hub holds.** Your library has an allowance of its own, five
times what a single agent may hold, and the Add tab prints it above the form so
you can see where you are. Material you add straight to an agent counts against
that agent as it always has, and **using a source on a second agent costs
nothing** — it isn't copied.

**Who can change what.** The Hub's own material belongs to the whole team:
anyone you've invited can add to it and take things out of it. Two limits.
Marking something **confidential** is an owner or admin only, because it's the
one switch the database itself enforces downstream. And a source that was added
**on an agent** stays that agent owner's to change — team-wide editing covers
what was added to the Hub, not everything visible in it. A colleague who owns
no agent of their own also has no Hub screen to reach yet; they see the inbox
they were invited to.

**Removing something.** A source in the hub that no agent uses is removed in
one press. If an agent is using it, the press asks which you meant: take it off
that agent, or remove it from the library. Take it off every agent first — a
source disappearing from under an agent that answers from it would change what
that agent knows without saying so.

### Syncing a site

Web pages change after you import them. **Sync**, on any site's group, does two
things in one press:

1. **Re-reads every page you already hold from that site** and replaces the
   text where the page changed. Your title stays yours — a rename you made is
   never overwritten.
2. **Asks the site what else it has now**, and shows anything you don't
   already hold in a checklist. Nothing new is added unless you tick it.

You get a report either way: how many pages changed, how many are new, and any
that couldn't be read — with the reason, page by page. A page that fails is
left exactly as it was; a sync never deletes anything.

**Note:** **Sync doesn't train.** It's a data refresh: the new words are stored and the
material is marked as waiting, and your agents keep answering from what they
already knew until the next train. Pages you add from the picker import in the
background — watch them land on that agent's Overview.

Sync is offered on sites, and only for material with a web page behind it.
Pasted text, uploads and videos have no address to go back to, and the panel
says how many of the group it's leaving alone.

## Agent knowledge — one agent's view

The same list, from one agent's point of view, in two groups:

- **From Knowledge Hub** — sources added on another agent that this one draws on.
  Each says which agent it came from, and **stop using** takes it off this
  agent only. The source stays in Knowledge Hub and every other agent that uses it
  is untouched.
- **Added here** — sources whose home is this agent. These are the ones you can
  rename, hold back, open, and remove.

On an account with one agent there's nothing to come *from*, so the list stays
flat until you have a second one.

The page has four tabs — **Sources**, **Add**, **What it knows** and
**Guardrails** — and one thing above all of them: **Words used**, so how much
of your plan this agent takes is stated once for the screen rather than beside
every tab.

### Finding one page among four hundred

Once you've imported a site, **Added here** stops being a list you can read
top to bottom. So it isn't one. Sources are grouped by **where they came
from** — the site, then the section of it — and each group says how many
sources and how many words it holds.

Groups are ordered biggest first, and a bar under each one shows its share of
the level above, so the thing you have too much of is the first row you read.
Open a group to see the sections inside it, or the pages themselves. A long
group shows the first twenty pages and offers the rest in one press.

Above the tree there are two ways to narrow it:

- **Search** matches the title, the type and the **address** — so `billing`
  finds the section as well as the pages that mention it — and opens every
  group that still has something in it, so nothing matching stays hidden
  behind a closed heading.
- **Kind chips** — Web pages, Video, Files, Notes, Written by hiy — filter to
  one kind. Kind is deliberately a filter and not the grouping: "your 399 web
  pages" is not a heading you can navigate by.

Both narrow the same tree at once, and a line under it says how many of your
sources are showing. A short list — eight sources or fewer — keeps the plain
list and neither control appears, because there's nothing there to find.

**Note:** Grouping is by origin today. Topic categories you assign yourself are the next
layer, not this one — origin needs no setup and fixes the unreadable list now.

### Guardrails

The fourth tab is what this agent will and won't take on: every **off-limits
topic** in full, the **subjects it covers** and what it does when asked
something outside them, whether it's been **interviewed**, and — for a Support
or Team Agent — where **handing over** to a person is set.

It states them; it doesn't edit them. Each group opens onto the current answer
and a way through to **Voice & rules**, which is the one place these are
changed, so two screens can never disagree about what you last said. See
[What it answers](/docs/what-it-answers) for what each setting does.

### Taking something from the library

**Use something from Knowledge Hub** opens a checklist of everything the account
holds that this agent isn't already using. Tick what you want and press the
button; nothing is copied, and it costs nothing against your source limit —
the same source now feeds both agents.

**Note:** It joins this agent at the next train, tonight or sooner with **Train now** —
the same as adding a source. Until then this agent answers from what it had,
unless it has never been trained at all, in which case there is nothing to wait
for and the build runs at once.

### What a shared source does when you change it

Each agent builds its own index, so each one picks a change up at its own next
train — the nightly one, or **Train now** on that agent if you'd rather not
wait.

- **Removing it** removes it everywhere. It's one source, not a copy per agent,
  so taking it out of the agent it was added on takes it out of all of them.
- **Holding it back** works the same way: a held source is out of *every*
  agent's index, not just the one you were looking at when you held it.
- **Stop using**, on an agent's own page, is the one that isn't global — it
  takes the source off that agent and leaves everyone else alone.

## Confidential sources

Marking a source **confidential** keeps it to your Team Agent — the one kind
only colleagues you invite can reach.

It's blocked from your public twin, and from a Support Agent too. A Support
Agent isn't on a public page, but the people it answers are your customers'
users, not your colleagues, so confidential material has no business there.

**Warning:** This is enforced in the database, not by a checkbox. There are three ways a
confidential source could reach an agent visitors can talk to — attaching it,
switching an agent to a visitor-facing kind while it holds one, or marking one
confidential after the fact — and all three are refused. The screens refuse
them too, so you read a sentence instead of an error, but the database is what
makes it true.

What that means in practice:

- The picker on a public twin or a Support Agent doesn't offer confidential
  sources at all, and says how many it's holding back.
- You can't mark a source confidential while one of those agents uses it. Take
  it off that agent first — the row tells you which one.
- Nothing confidential reaches such an agent's answers, its summary, the way it
  learns to sound, or the suggested questions on its page. That check is on the
  read as well as the write, so it holds even if something writes around it.

Confidential is for material a Team Agent should answer from and the public
never sees: internal notes, salary bands, unreleased plans. Your public twin
keeps working; it just can't see those rows.

## Limits

A source added on an agent is counted once, against that agent. Something added straight to the Hub has no agent to count against, so it counts against the Hub's own allowance instead — five times a single agent's words. Subscribing
another agent to it doesn't spend anything — that would defeat the point of a
library. The words meter on each agent's Knowledge page counts what was added
*there*, which is exactly what the plan limit counts.