Skip to main content
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:
1

You work naturally

Ask for things, correct what comes back, explain your preferences — exactly as you would with a new colleague.
2

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.
3

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.

​
What it learns: playbooks and skills

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

Guidance — the playbooks

How you want things done: rules, preferences, step-by-step procedures, and pitfalls to avoid. “Exclude internal transfers when computing monthly spend” lives here.

Functions — the skills

What your assistant can do again: concrete, reusable workflows it built while working for you. The corrected monthly-spend pipeline itself lives here.
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.
A third library, 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.

​
Seeing it happen

Learning isn’t a black box. The Console shows you all of it:
  • The Actions pane 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 let you browse everything it has learned, as readable documents and inspectable skills.

​
What’s in this section

Watching it work

The Actions pane — every request, every step, live.

Guidance & Functions

Browsing the playbooks and skills your assistant has picked up.

Knowledge

The durable facts and rules its answers rest on.

Teaching your assistant

Corrections, walkthroughs, documents — and how to make them stick.
Building on or extending the open-source runtime? The Developers sub-section documents how all of this is implemented in unifyai/unify — the dual library, the two-phase actor loop, StorageCheck, and the knowledge and memory subsystems.