> 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/memory-and-learning.md).
# Memory & Learning
What the agent carries forward — and what it deliberately doesn't.
By default, an agent starts every conversation knowing nothing about who it is talking to. That is often correct: an agent processing loan documents doesn't need to remember anyone.
But some agents get better by remembering, and Qore separates that into distinct kinds — because they have different scopes, different risks, and different rules about what may enter them.
## Three kinds of memory
All three live under **Agent Config → Reinforcement Learning** (Preview), one tab each.
| Kind | Tab | What it carries | Default |
| ----------------------- | ------------------ | ---------------------------------------------------------------- | -------------------- |
| **User persona memory** | **User Persona** | What an individual user has asked about, preferred, or corrected | Off |
| **FAQ memory** | **FAQ** | Canonical answers to questions the agent already knows | Off |
| **Learning cases** | **Learning Cases** | Reviewed corrections from real production behavior | Manual approval only |
**User persona memory** remembers what an individual user has asked about, preferred, or corrected — across conversations. Turn it on with **Enable User Persona**. The tab lists the stored persona memories, and you can delete one.
**FAQ memory** lets the agent reuse a stored canonical answer when a question matches a known FAQ, rather than answering from scratch each time. Turn it on with **Enable FAQ**. The tab lists the stored FAQs and their answers.
**Learning cases** are corrections captured from real production behavior — a case where the agent got something wrong and a person recorded what the right answer would have been.
{% hint style="info" %}
**The Fast capability leaves memory out.** With **Agent Capability** set to `Fast`, the agent doesn't use persona memory, FAQ memory, or learning cases, and the User Persona tab can't be changed. See [Steering & Reasoning](/ai-workbench-qore/core-concepts/steering-and-reasoning.md).
{% endhint %}
## Why learning cases require a human
Learning cases do not enter memory automatically. Each one is reviewed and approved by a person first.
{% hint style="warning" %}
**Approval is manual. Auto-approval is intentionally disabled,** so a malicious or mistaken input cannot quietly change the agent's behavior.
{% endhint %}
See [Human-in-the-Loop](/ai-workbench-qore/core-concepts/human-in-the-loop.md).
## The improvement loop
Memory is where the operating loop closes.
1. [Monitor](/ai-workbench-qore/console/agent-builder/monitor.md) production behavior and score live conversations to find where the agent missed.
2. Record what the correct behavior should have been — a **learning case**.
3. **Review and approve** it. This is the gate.
4. Validate the improvement with [Evals](/ai-workbench-qore/console/agent-builder/test/evals.md) before rolling it out more broadly.
The agent improves from real outcomes, not just from isolated test runs — but only through a door a person opens.
## Context is not memory
A related idea, easy to confuse. **Memory** is what the agent carries across conversations. **Context** is what it holds within one — the conversation so far, retrieved documents, tool results.
Context is finite. Long conversations eventually exceed what the model can hold. **Auto-compaction**, on [Agent Behavior](/ai-workbench-qore/console/agent-builder/build/agent-behavior.md), summarizes the conversation when it nears the context window, at a threshold you set between 50% and 95% of the window. It appears when the agent's executor version supports it. Retrieval — pulling only the relevant material into context rather than everything — is covered in [Knowledge & Context](/ai-workbench-qore/core-concepts/knowledge-and-context.md).
## Where this is configured
* [Reinforcement Learnings](/ai-workbench-qore/console/agent-builder/monitor/reinforcement-learnings.md) — Learning Cases, FAQ, and User Persona, and the learning-case approval flow
* [Agent Behavior](/ai-workbench-qore/console/agent-builder/build/agent-behavior.md) — Agent Capability and Auto-compaction
* [Monitor](/ai-workbench-qore/console/agent-builder/monitor.md) and [Online-Eval](/ai-workbench-qore/console/agent-builder/monitor/online-eval.md) — where misses are found
* [Evals](/ai-workbench-qore/console/agent-builder/test/evals.md) — validating an improvement before it ships
***
{% 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/memory-and-learning.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.
