Pattern 26 · Onboarding

Capability discovery

Users only use the 10% of an AI product they found by accident; the rest might as well not exist.

By Aleksey StepikinUpdated October 20263 min readLive demo
Live demo · try it

An interactive mock built in plain HTML, CSS and JavaScript. Data is fictional; no model is called.

FitWhen to use it — and when not

Use it when

  • Assistants with many skills, tools or modes
  • Products where power features drive retention
  • After onboarding, as users grow

Skip it when

  • Single-purpose tools with one job

AnatomyThe parts of the pattern

  1. Slash menu"/" opens commands with descriptions; filters as you type.
  2. Rotating hintPlaceholder that suggests a real capability.
  3. Contextual tipsSuggest a capability when the context fits.
  4. Capability listAn honest "what I can and cannot do".

GuidelinesDo & don’t

Do

  • Describe each command by outcome, not by name.
  • Support keyboard: arrows, Enter, Esc.
  • Surface capabilities at the moment they are useful.

Don’t

  • Hide features behind a docs page only.
  • Tour every feature on day one.
  • Claim capabilities the model does unreliably.

In the wildReal-world examples

Notion AICursorClaude CodeRaycastSlack

Products named for reference only — no affiliation, and the demo above is an original illustration, not a copy of their UI.

For engineersImplementation notes

  • Register commands as data (name, description, args schema) shared by the UI menu and the model's tool list.
  • Fuzzy-match on name and description; rank by the user's recent usage.
  • Track discovery: first use per capability per user.

OnboardingRelated patterns

All 26 LLM UX patterns

Building an AI product?

I design and ship AI products end to end — LLM interfaces, agents, RAG, billing — from concept to a live product in weeks, not quarters. Tell me what you are building and get a fixed estimate.

Get an estimateBook a call

Create bold.
Deliver better.

See our workGet in touch