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

# Overview

> Correct your assistant once, and the fix sticks

The difference between a tool and a teammate is that a teammate learns.
When you correct your assistant, show it how you like something done, or
simply work through a problem together, that experience doesn't evaporate
when the chat ends — it becomes part of how your assistant works from then
on. You shouldn't have to repeat yourself on similar work.

## How learning works

There's no training mode and no settings page. Learning happens as a natural
by-product of working together:

<Steps>
  <Step title="You work naturally">
    Ask for things, correct what comes back, explain your preferences —
    exactly as you would with a new colleague.
  </Step>

  <Step title="Your assistant reviews its own work">
    After it finishes a piece of work, your assistant looks back over what
    happened and asks itself: *is anything here worth keeping for next
    time?* A rule you corrected, a workflow that succeeded, a pitfall it hit
    — those get saved. Routine work saves nothing, and that's by design: a
    small, sharp library beats a big noisy one.
  </Step>

  <Step title="Next time starts smarter">
    Before starting any new piece of work, your assistant first checks what
    it has learned — the relevant playbooks and skills — and applies them,
    rather than reinventing the approach from scratch.
  </Step>
</Steps>

## What it learns: playbooks and skills

Learned material lands in two libraries, both visible in the Console:

<CardGroup cols={2}>
  <Card title="Guidance — the playbooks" icon="compass" color="#2f9d97" href="/learning/guidance-and-functions">
    *How* you want things done: rules, preferences, step-by-step procedures,
    and pitfalls to avoid. "Exclude internal transfers when computing
    monthly spend" lives here.
  </Card>

  <Card title="Functions — the skills" icon="braces" color="#cf9a3e" href="/learning/guidance-and-functions">
    *What* your assistant can do again: concrete, reusable workflows it
    built while working for you. The corrected monthly-spend pipeline itself
    lives here.
  </Card>
</CardGroup>

The two work together — a playbook often references the skills it uses.
Think of a function as a tool in the toolbox, and guidance as the recipe
that says which tools to use, in what order, and what to watch out for.

<Note>
  A third library, [**Knowledge**](/learning/knowledge), holds *facts* —
  documents you've shared, things that are true about your business.
  Guidance is *how-to*; Knowledge is *what-is*. Your assistant also quietly
  keeps notes on the people you both deal with — their details and
  preferences — in **Contacts**.
</Note>

## Seeing it happen

Learning isn't a black box. The Console shows you all of it:

* The [**Actions** pane](/learning/watching-it-work) shows your assistant's
  work live, step by step — including the moment it checks its libraries
  ("Searching for relevant guidance") and the moment it saves something new
  ("Storing reusable skills").
* The [**Guidance** and **Functions** panes](/learning/guidance-and-functions)
  let you browse everything it has learned, as readable documents and
  inspectable skills.

## What's in this section

<CardGroup cols={2}>
  <Card title="Watching it work" icon="wave-pulse" color="#c95f5a" href="/learning/watching-it-work">
    The Actions pane — every request, every step, live.
  </Card>

  <Card title="Guidance & Functions" icon="book-open" color="#4f7fa8" href="/learning/guidance-and-functions">
    Browsing the playbooks and skills your assistant has picked up.
  </Card>

  <Card title="Knowledge" icon="book" color="#ffb24a" href="/learning/knowledge">
    The durable facts and rules its answers rest on.
  </Card>

  <Card title="Teaching your assistant" icon="graduation-cap" color="#6e4a86" href="/learning/teaching">
    Corrections, walkthroughs, documents — and how to make them stick.
  </Card>
</CardGroup>

<Note>
  Building on or extending the open-source runtime? The
  [Developers](/learning/developers/architecture) sub-section documents how
  all of this is implemented in
  [`unifyai/unify`](https://github.com/unifyai/unify) — the dual library,
  the two-phase actor loop, StorageCheck, and the knowledge and memory
  subsystems.
</Note>