Browser Use

Research across the open web

Regulators, clinical registries, academic publishers and city halls. Sources that are public but not queryable, where the answer is three clicks deep in a form nobody has an API for.

Research examples

Research
Find the Public-Records Request Route - Browser Use demo0:15

Find the Public-Records Request Route

medfordma.org

Find swim classes for a [age]-year-old within [X] miles of [address]. Open each provider's own site for the real schedule and price, and return a comparison table.

Copy and run
Prompt

Find Kids' Swim Classes

google.com/maps

On Google Maps, look up the opening hours and popular times for [gym]. Tell me the quietest hour to go on each weekday.

Copy and run
Prompt

Find the Quietest Gym Time

google.com/maps

Find FDA-Cleared AI Devices - Browser Use demoPrompt

Find FDA-Cleared AI Devices

fda.gov

On the BioPharma Catalyst FDA calendar, find every trial readout between [start] and [end]. Return company, ticker, drug, indication, phase, and expected date.

Copy and run
Prompt

Track Clinical-Trial Results

biopharmcatalyst.com

On ClinicalTrials.gov, find companies running trials that use Alzheimer's blood biomarkers. Return company, trial ID, phase, biomarker, and status.

Copy and run
Prompt

Find Alzheimer's Biomarkers

clinicaltrials.gov

Map the continuous glucose monitoring market. Find the companies, their products, regulatory status, and partnerships, and cite a source URL for every claim.

Copy and run
Prompt

Map Diabetes Devices

google.com

Find papers on [topic] published since [year]. Start from Google Scholar, then follow through to publisher and university repositories to locate a legally accessible full text for each.

Copy and run
Prompt

Find Papers Everywhere

scholar.google.com

On mathunion.org, find the official Fields Medal lecture videos for [year]. Return laureate, lecture title, and a direct link to the official video.

Copy and run
Prompt

Find Fields Medal Lectures

mathunion.org

Other things agents do

Data extraction

Portals, rendered tables, paginated lists and PDFs behind a search form. The agent opens the real page, follows the pagination, and hands back CSV or JSON with a source URL on every row.

Shopping & checkout

Unit prices instead of sticker prices, stock checked across twenty products at once, coupons tried one at a time at the real checkout. The agent stops before payment, every time.

Travel & booking

Availability that only exists inside a live calendar widget, seat maps you have to read visually, walking distances you have to check on a map. These are the flows a scraper cannot see.

Testing & QA

No selectors to maintain and no test script to rewrite when the DOM moves. Describe the flow in a sentence, get screenshots, console errors and a prioritised fix list back.

Companies & jobs

Directories, portfolio pages, exhibitor lists and job boards, turned into a deduplicated table with every claim traced back to the page it came from.

Agent workflows

Four browsers at once, a task that runs every weekday at eight, a workflow saved as a reusable skill, a logged-in session that stops before anything irreversible.

Social & outreach

Both platforms are hostile to automation and generous to a logged-in human. The agent is the second kind: it reads your feed, exports your own followers, drafts in the real composer, and stops before it posts.

Games & real-time

Tetris, chess, GeoGuessr, powerline.io. Not a benchmark - a demonstration that the agent can read a board that changes faster than it can think and still act on it.