> For the complete documentation index, see [llms.txt](https://docs.uptiq.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.uptiq.ai/ai-workbench-qore/core-concepts/knowledge-and-context.md).
# Knowledge & Context
What the agent can read.
A model knows what it was trained on. It does not know your credit policy, your product catalogue, or what your customer asked for last Tuesday. **Knowledge** is how you give an agent something to read that the model was never trained on.
The mechanism is retrieval: rather than putting everything in front of the model, the agent searches your material for the parts relevant to *this* request and pulls only those into context.
## Why retrieval instead of just uploading everything
Context is finite. A model can only hold so much at once, and filling it with material that isn't relevant to the current question makes answers worse, not better — the signal is still in there, but so is everything else.
Retrieval means your knowledge can be far larger than any context window, and what reaches the model is the part that matters. The cost is that retrieval has to find the right material. Two places show you what it works from:
* [Document processing](/ai-workbench-qore/console/knowledge/document-processing.md) — see how Qore split, tagged and extracted each document.
* [Try Knowledge](/ai-workbench-qore/console/knowledge/try-knowledge.md) — query a knowledge base and see the chunks behind each answer.
## Getting knowledge into an agent
Two steps, and they're separate on purpose.
1. [Knowledge](/ai-workbench-qore/console/knowledge.md) — build a knowledge base from your files. Qore processes them into a table of contents, tags, and embeddings. It exists whether or not any particular agent uses it. You can build one on the **Knowledge** page, by asking the [Console Operator](/ai-workbench-qore/console/console-operator.md), or from the Agent Builder chat.
2. [Attaching Knowledge to an Agent](/ai-workbench-qore/console/agent-builder/build/attaching-knowledge-to-an-agent.md) — point a specific agent at a knowledge base so its planner can query it.
Separating them means one body of knowledge can serve many agents, and an agent can draw on more than one.
## Keeping knowledge current
A knowledge base changes only when you **sync** it. Updating a file in a dataset does nothing to the knowledge base until that file is synced. Each sync creates a new **knowledge version**, and agents use the latest completed version. There is no draft or publish stage: a completed sync is live.
You can upload a new version of a file to an existing dataset, including from Google Drive, OneDrive, SharePoint, or a website. A dataset with auto sync turned on syncs eligible new files automatically. See [Sync & versions](/ai-workbench-qore/console/knowledge/sync-and-versions.md).
## Governed graphs
A [governed graph](/ai-workbench-qore/control-center/govern/governed-graph.md) is an institution's knowledge graph: its products, pricing, policies, document requirements, rules, and the sources behind each fact. You upload it in **Control Center → Govern → Governed Graph**. It is created for the whole account, so every project can read it.
Once uploaded, a graph is knowledge in the account, and you attach it to an agent like any other knowledge. The agent queries it with the **Knowledge Graph Search** skill, for structured questions such as which documents a product requires, rather than searching it as text.
## Knowledge is not memory
Easy to conflate, different in an important way.
* **Knowledge** is what you give the agent to read — deliberate, curated, the same for everyone.
* [Memory & Learning](/ai-workbench-qore/core-concepts/memory-and-learning.md) is what the agent carries forward from its own experience — accumulated, per-user or per-agent, and gated by approval where it changes behavior.
An agent answering "what is our maximum LTV?" is using knowledge. An agent remembering that *you* always ask about commercial rather than retail is using memory.
## How the agent reaches it
At runtime, the planner uses a skill to search attached knowledge: **Knowledge Search**, which finds passages by meaning, or **Knowledge Lexical Search**, which matches the words themselves. Both are built-in General skills. A governed graph is reached through **Knowledge Graph Search**. Retrieval is subject to the same rule as everything else the agent does: if the skill isn't enabled, the knowledge can't be reached, however well the knowledge base is built. See [Skills & Tools](/ai-workbench-qore/core-concepts/skills-and-tools.md).
## Where this is configured
* [Knowledge](/ai-workbench-qore/console/knowledge.md) — building knowledge bases from your files
* [Sync & versions](/ai-workbench-qore/console/knowledge/sync-and-versions.md) — sync, knowledge versions, and auto sync
* [Attaching Knowledge to an Agent](/ai-workbench-qore/console/agent-builder/build/attaching-knowledge-to-an-agent.md) — pointing an agent at a knowledge base or a governed graph
* [Governed Graph](/ai-workbench-qore/control-center/govern/governed-graph.md) — uploading a governed graph
* [General skills](/ai-workbench-qore/platform-resources/skill-library/general-skills.md) — Knowledge Search and Knowledge Lexical Search, the built-in skills that query attached knowledge
***
{% columns %}
{% column width="83.33333333333334%" %}
Maintained by Abhishek Paul
AI-assisted, human-approved
{% endcolumn %}
{% column width="16.666666666666664%" %}
{% endcolumn %}
{% endcolumns %}
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.
Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:
```
GET https://docs.uptiq.ai/ai-workbench-qore/core-concepts/knowledge-and-context.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
