> ## Documentation Index
> Fetch the complete documentation index at: https://docs.cloudthinker.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Teach CloudThinker

> Choose between workspace memory, knowledge bases, skills, Learnings, and runbook sources when you want agents to work your team's way

Seven surfaces hold the context you give CloudThinker: workspace memory, Dreaming, Incident Memory, Learnings, knowledge bases, skills, and runbook sources. This page picks the right one for what you're teaching, and each row links to the page that sets it up.

## Which one to use

| Surface | What it teaches | Who writes it | Where it applies | Reach for it when |
| - | - | - | - | - |
| [Workspace Memory](https://docs.cloudthinker.io/guide/memory.md) | Durable facts about your environment, team preferences, decisions, and corrections | CloudThinker, as agents work. Anyone who can chat teaches or corrects it; workspace Admins edit and delete items directly | Workspace-wide. Loads into every conversation | You're tired of re-explaining your setup, or an agent keeps using a fact that's wrong |
| [Dreaming](https://docs.cloudthinker.io/guide/memory-dreaming.md) | Nothing new. It keeps workspace memory and [custom skills](https://docs.cloudthinker.io/guide/skills/custom-skills.md) short, current, and consistent | CloudThinker, nightly. A workspace Admin turns it on or off and tunes it | Workspace-wide: memory items and custom skills | Memory has filled up with duplicates and stale items — or your team curates by hand and you want it off. On by default |
| [Incident Memory](https://docs.cloudthinker.io/guide/incident/incident-memory.md) | What each investigation found: symptom, root cause, the fix, and a check that proves the fix | CloudThinker, at the end of an investigation. There's no form to fill in and nothing to switch on | [Resolve](https://docs.cloudthinker.io/guide/incident/overview.md) only | The same service keeps failing the same way and you want the next investigation to start from the last one |
| [Learnings](https://docs.cloudthinker.io/guide/code-review/convention-rules.md) | Your team's review standards — as rules distilled from resolved findings, and as the convention files you already keep in the repository | CloudThinker writes Learnings; your team writes the convention files it reads. A workspace Admin sets the schedule and retires a rule | [Review](https://docs.cloudthinker.io/guide/code-review/overview.md), one repository at a time | Review keeps raising something your team fixes by hand, or your standards are already written down in the repository |
| [Knowledge Base](https://docs.cloudthinker.io/guide/knowledge.md) | Your documents, as written: runbooks, policies, architecture notes, crawled web pages | You, by uploading files or crawling a site. A workspace Admin creates them and adds documents | Workspace-wide. Every agent can search every knowledge base, and Resolve can use them as evidence | Agents should answer from your document instead of generic advice |
| [Skills](https://docs.cloudthinker.io/guide/skills/overview.md) | A procedure or set of rules agents follow step by step | Usually you. CloudThinker can also write them, through a custom agent's **Skill Learning** setting, `/create-skill`, or Dreaming | Workspace-wide, but each skill runs only on the surfaces ticked under **Available in**: Chat, Review, Incident, Assessment | The same procedure should run the same way every time |
| [Runbooks](https://docs.cloudthinker.io/guide/incident/runbooks.md) — **Legacy** | Fix procedures you already keep in Confluence, GitHub, or GitLab, or upload as Markdown | You. The procedures stay in your own systems; a workspace Admin adds the source | Resolve only, during [root cause analysis](https://docs.cloudthinker.io/guide/incident/root-cause-analysis.md) | Your fix procedures already live in one of those systems and you don't want to rewrite them as skills |

> [!NOTE]
>
> **Runbooks** carries a **Legacy** label in the app. It works as described on its page, and no replacement or removal date has been announced. The other six surfaces are current.

## I want to…

| I want to | Use |
| - | - |
| Make agents follow our runbook, every time | Write the runbook as a [skill](https://docs.cloudthinker.io/guide/skills/overview.md) and tick the surfaces it applies to |
| Use the fix procedures we already keep in Confluence or a repository | Add them as a [runbook source](https://docs.cloudthinker.io/guide/incident/runbooks.md), or upload the same files to a [knowledge base](https://docs.cloudthinker.io/guide/knowledge.md) if you'd rather stay off a Legacy surface |
| Stop Review repeating a comment we keep dismissing | Find the rule in **Review → Learnings** and [retire it](https://docs.cloudthinker.io/guide/code-review/convention-rules.md#retire-or-restore-a-learning) |
| Teach Review a standard it keeps missing | Write it in a [convention file](https://docs.cloudthinker.io/guide/code-review/convention-rules.md#add-your-own-convention-files) in the repository |
| Give CloudThinker our architecture doc | Upload it to a [knowledge base](https://docs.cloudthinker.io/guide/knowledge.md) |
| Stop re-explaining which region production runs in | Say it once in chat and let [workspace memory](https://docs.cloudthinker.io/guide/memory.md) keep it |
| Correct a fact an agent got wrong | Say the correction in chat; [workspace memory](https://docs.cloudthinker.io/guide/memory.md#teach-or-correct-memory) updates the matching item |
| Reuse what we learned from the last outage | Nothing. [Incident Memory](https://docs.cloudthinker.io/guide/incident/incident-memory.md) already reads the last investigation before it forms a hypothesis |
| Keep memory from filling up with duplicates | Leave [Dreaming](https://docs.cloudthinker.io/guide/memory-dreaming.md) on, and add a focus instruction if a run keeps getting something wrong |

## How they fit together

Workspace memory is the foundation. Incident Memory and Learnings are specialized memory for one module each, written by CloudThinker rather than by you, and neither appears in the workspace memory list.

One test separates the two surfaces you write yourself: if agents should follow it step by step, make it a skill; if they should look things up in it, put it in a knowledge base. A skill can point agents at a knowledge base document, so the two work together.

## Examples

Teach or correct workspace memory by saying it in any chat. The reply shows a **Saved to memory** or **Updated memory** step.

```text theme={null}
Production runs in eu-west-1 and disaster recovery runs in eu-central-1.
Don't propose rightsizing for the staging cluster. Why: it's sized for load tests.
```

Name a knowledge base in your request to limit the search to that one.

```text theme={null}
Using the Payments runbooks knowledge base, how do I fail over the primary Postgres?
```

## Related

> **[Customize](https://docs.cloudthinker.io/guide/agents/customize.md)**
>
> Shape agents with instructions, skills, and connections

> **[Workspace Memory](https://docs.cloudthinker.io/guide/memory.md)**
>
> Browse and correct what CloudThinker remembers

> **[Skills](https://docs.cloudthinker.io/guide/skills/overview.md)**
>
> Turn a procedure into something agents apply on their own

> **[Core concepts](https://docs.cloudthinker.io/guide/concepts.md)**
>
> See how agents, approvals, and context fit together


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.