Add to ChromeResearch these companies using their public websites only. Our criteria are: [customer type, location, service]. Return each claim with its supporting text, source URL, date checked, and any unknowns. Do not buy contact data or send messages.
All use cases
PIPELINE
Find the prospects worth contacting.
Give Retriever AI (rtrvr.ai) your company list and the traits that make a good customer. Get a shortlist with evidence for each match, source links, and drafts to review.
BEST FORGTM teams working from event lists, directories, and signed-in searches.
WHAT YOU GET
500 attendees narrowed to 10 prospects
- 01People and companies enriched
- 02A fit reason tied to your criteria
- 03Ten specific outreach drafts
COPY A START
Use a prompt. Make it yours.
Replace the examples with your pages, rules, and approval point. rtrvr will work from the request you give it.
For the strongest matches, draft a short opening note grounded in one verified fact about each company. Do not invent a need or a relationship. Leave every draft for me to review.
Turn an event list into a shortlist.
The Luma workflow behind the Bright Data case study: research attendees, check the fit, and prepare outreach. This example includes paid data lookups.
WORKED EXAMPLE · PUBLIC-SITE RESEARCH
Start with a reason to reach out.
Suppose you provide training materials for wholesale coffee teams. These public pages give you a starting point for research, not proof that either company needs your service. Checked September 22, 2026; no contact-data purchase was used for this editorial example.
| Company | Public evidence | Still unknown |
|---|---|---|
| Verve Coffee | Wholesale page describes education and training | Training needs, budget, decision maker |
| Ritual Coffee | Wholesale page describes support for partners | Current tools, buying intent, decision maker |
Check the result.
A draft for Verve could begin: ‘I saw that your wholesale program includes education and training. We create training materials for coffee teams. Is that something your team handles in-house?’ Edit the offer to match your business. Do not claim a problem you have not established or send a message without reviewing it.
Public-site research and contact enrichment have different costs. Free Mode covers supported AI and browser time within its allowance. Paid datasets and managed proxies can use credits separately. The 500-to-10 case study above used about $1.25 in dataset lookups.
HOW THE RUN WORKS
Start small. Check the result.
Tell Retriever AI which pages to use, what to return, and where to pause. Review a small sample before expanding the task.
- 01
Read the list
rtrvr collects the authorized attendee or account records in your browser.
- 02
Research the fit
It adds public facts and evaluates each record against your stated criteria.
- 03
Prepare the next move
You get the shortlist, sources, fit reasons, and drafts for review.
WHY THIS FITS
In the Bright Data case study, one prompt researched 500 attendees and selected 10 prospects for about $1.25 in dataset lookups.
WHERE TO RUN IT
Pick the fastest way to start.
Use Chrome for sites you’re already signed into. Use Cloud for a separate browser, or the API for tasks from your own tools. Schedules require a paid plan.
Add to Chrome
Start from the event list or account search you are already signed into.
Bright Data case study
See the full 500-to-10 run and the data used at each step.
RUN YOUR VERSION