Consumer Behaviour
Agentic browser
Also known as: AI browser
A browser (or browsing layer) that uses an LLM agent to interpret pages, summarise content, and take actions on behalf of the user. Arc Search, Perplexity Comet, Browser Company's Dia, Dia browser, and similar.
What it is
An agentic browser is a browser or browsing layer that uses an LLM agent to interpret pages, summarise content, and carry out actions for the user. Arc Search, Perplexity Comet, and Dia are early examples.
Why it matters
It changes who reads the page: the agent consumes and condenses content before the human sees it, so visibility depends on being machine readable and quotable rather than on attracting a click.
How it works
The agent fetches pages, parses their structure and main content, synthesises an answer or completes a task such as filling a form, and presents a condensed result to the user.
When it applies
It applies when users delegate browsing or research to an assistant rather than navigating sites directly.
Examples
- A user asks the browser to compare three products and receives one synthesised summary instead of three tabs.
- An agent reads a recipe page and returns only the ingredients and steps, skipping the surrounding article.
- The browser books or pre fills a form on the user's behalf after reading the page.
How it is measured
- Share of sessions where content is summarised rather than read in full
- Rate of agent visits versus human page views
- Inclusion or citation rate within agent generated summaries
- Actions completed by the agent per visit
Related terms in Consumer Behaviour
- Brand demandSearch volume for branded terms. In an AI-search world, brand demand is the single strongest moat, generic queries are absorbed by AI Overviews and ChatGPT, while branded queries route users directly to brand properties.
- Consumer behaviour signalObservable patterns in how users phrase queries, refine searches, and choose answers, used by both ranking systems and generative models to infer intent and quality.
- Job-to-be-done (search)The functional outcome a searcher is trying to achieve when they issue a query. Distinct from the literal query text. The unit of analysis for intent-aligned content strategy.
- Prompt-shaping behaviourHow users refine the language of their prompts mid-conversation to get a better answer. Reveals a shift from keyword behaviour (typing fewer terms) to conversation behaviour (typing more, more naturally).