Enabling editing on specific parts of human written text or AI generated responses.
Overview
Inline actions is a pattern for our textual experience. It helps us fine-tune specific parts of text, without starting over. Whether we’re working with an AI or writing on our own, we rarely edit everything at once. We’re always refining, line by line, thought by thought.
With inline actions, we can either update text or request feedback with targeted prompting. Like a smart co-editor who steps in where it’s needed, but under our control; no more, no less.
Using this pattern, iteration becomes faster, and focused prompts create momentum.
User intent
Getting result faster
Macro trend
Human in loop
Why do we need inline actions on text?
Tweaking is a natural human tendency, whether it be getting to a finalized output with an LLM or a human. Everything is always an iterative process; we like some sections of the idea, and for some, we "make it better".
The user need arises when we're writing a doc or generating textual ideas through an AI chat. Being able to highlight specific things digitally and request help on those parts is what makes the iteration experience easier and faster.
To understand it better, let's dive into some examples.
Examples
Lex's Page
is the perfect example of how you can empower users with inline actions in a note-taking or documentation experience.

Screenshot of Lex.page’s UX / Source: Aiverse
The tool leverages our mental model of selecting and highlighting text for commenting on documents, and calling an agent to update highlighted sections. This is an example of a great intuitive interaction, which requires a minimum learning curve because it's a natural human behaviour.

Entry points & loading states of Lex. page’s UX / Source: Aiverse
Requesting granular edits is not limited to just documentation tools. It's also useful in chat-based tools.
Chat GPT
is a chat-based tool that nails this interaction. However, instead of updating the content in the output, it lets you use it as a reference for your next instruction. It enables iterations & brainstorming on specific parts.

Screenshot of Chat.GPT’s UX / Source: Aiverse
It starts when you highlight a text piece and hit the 'Reply' button. Clicking it lets you choose that part as the focus for your next chat to prompt further.

Entrypoints & loading state of Chat.GPT’s UX / Source: Aiverse
Bigger vision? Humans can think, point, and talk all at once.
Drafting by simply pointing at text and speaking your intent. That’s where we’re headed: fluid, multimodal creation that keeps up with how we really think.

¿Se pregunta cómo las empresas están diseñando para la inteligencia artificial?¡Ahorre horas de investigación de UI y UX!
Fundadora de diseño en Studio Oblique

Curated by
