Skip to main content
Hyperagent

Knowledge

The facts, methods, and reference material agents can use across work, and the controls that decide where each belongs.

A Customer Success agent preparing a renewal brief should not need the same setup every time. It can remember how leadership wants risk framed, follow the team's account-review method, and open the customer history and usage table when the work calls for them. Knowledge is the material that lets an agent begin from what your team has already established.

Knowledge gives future work a better starting point

Preserve the facts, methods, and reference material worth using again. The next thread can retrieve the right context without carrying every prior conversation with it.

An illustration of a Customer Success agent preparing a renewal brief: arrows lead from the agent to four sources it draws in, a memory preference recalled, an account-review skill loaded, a customer history document opened, and a usage table read, which together produce a renewal brief that leads with risk, movement, and next actions. The loop highlights each source in turn.
One renewal brief, drawing on knowledge: the agent recalls a preference, loads a skill, opens a document and a table, and produces the brief without being re-briefed.

Three kinds of knowledge

Knowledge is what you give an agent to work from

Knowledge is the material an agent begins from instead of rediscovering: a memory it recalls, a skill it follows, a document or table it reads. Some of it you lift out of real runs, a fact you corrected or a method that worked. Just as much of it you bring in from outside: upload a brand guide, write a memory by hand, attach a dataset the agent should treat as ground truth. Either way, giving an agent knowledge is deliberate.

That is also the property that separates knowledge from a thread's own history. A thread keeps the conversation and tool results for one piece of work, and the next thread does not inherit them. Knowledge is what you deliberately keep or provide so the next run can use it, there for work that hasn't started yet.

Work creates knowledge, and you decide what lasts

A run often reveals something worth keeping: a fact you corrected, a method that worked, reference material worth keeping current. The agent proposes a memory, skill, or prompt improvement, and nothing becomes standing knowledge until you accept it, unless you've allowed a trusted agent to save that kind on its own. Documents and tables the agent builds are editable outputs that live in the Library. See Learning for how proposals are raised and reviewed.

An animation cycling three states: a thread proposes a memory and a skill as suggestion cards; the reviewer edits the memory and accepts both; the saved items then appear in Memories and Skills panels, the memory marked Global and the skill marked Discoverable to show their reach.
From a thread suggestion to saved knowledge: propose a memory and a skill, edit and accept them, and see them land in Memories and Skills with their reach visible.

The agent loads only what a run needs

Saved knowledge is not poured into every run. A small amount of pinned context arrives up front; the rest surfaces or is fetched when the conversation makes it relevant, so the context window stays free for the work itself. This is why what an agent can reach and what it loads on a given run are different things. See How context gets into a thread.

Choose the right home

Match what you are preserving to the question it answers. This keeps one fact from becoming a document, one process from becoming a memory, and one run's temporary state from leaking into every future job.

You need to preservePut it hereExample
A standing fact, preference, correction, or relationshipA memory“Renewal briefs should lead with risk and next action.”
A repeatable process or quality standardA skill“How to prepare and review a renewal brief.”
Written material the agent reads or maintainsA documentA living customer brief or brand guide.
Structured records with reusable columnsA tableAccount health, owners, renewal dates, and status.
Facts, corrections, decisions, and plan details for this conversationThread Context Document“For this run, use the corrected renewal date of October 12.”
Data that already belongs in another systemKeep it in the connected systemCurrent CRM fields, support tickets, or calendar events the agent can retrieve when needed.

Control who can use and change knowledge

Before the work

Set what the agent may use

Knowledge and learning controls which memories the agent can read, whether it can discover skills, which context files travel with it, and where new learning is saved.

After the work

Review what the agent wants to keep

Learning collects proposed memories, skills, prompt improvements, and configuration changes. Review the suggestion before it becomes lasting knowledge, or allow trusted personal agents to save selected types automatically.

FAQs