500+ qualified leads on demand, and about 70 hours saved on every list
Vollardian builds targeted lead lists for other companies to sell into. The best lists turn on criteria no database tracks, like whether a gym is a franchise, has a sauna, or teaches pilates, so the team built every list by hand, about 70 hours a time. We built them a platform that takes a plain-language brief, finds the companies, and qualifies each one against those exact criteria. Now they spin up as many lists as they want, pulling 500+ qualified leads on demand, and get those 70 hours back every time.
“Michelle and Andy really helped me understand what AI could actually do for us. They walked me through the options and the problem-solving without any jargon or hype, and clearly knew the technology inside out. Knowledgeable and easy to talk to.”
Arani SatgunaseelanCo-founder · VollardianThe problem
You know the kind of business you want, and what makes one worth a call: a dental clinic that offers Invisalign, a company that just opened a second office, an environmental firm that walks the talk on sustainability. No lead database holds any of that. You get it by opening each company and reading.
So the team did it by hand. Someone searched, opened each result, read enough to judge it, and saved the good ones. About 70 hours for a single list, and none of it carried into the next one.
- The gap
Build the list
Find and qualify companies against your own criteria.
No software. By hand. Enrich the list
Add phone numbers, revenue, and the right contacts.
Apollo, HubSpotReach out and track
Send sequences, automate follow-ups, and track every reply.
Outreach tools, CRM
The process
Two steps, both in plain language. First, name the lead. Say CrossFit gyms in Sydney. The platform writes its own searches, reads the results, and pulls the gyms out of the pages. This run found sixteen, and it keeps going for as many as you want.

Then name the enrichments, the details that decide whether a lead makes the cut. An enrichment can be a yes or no, like open 24/7. It can be a number, like how many trainers. Or free text, like the offers they run or a startup's funding stage. For each one it reads what it can find and answers like a person would, with the reasoning and source attached.

Stack as many as you want on one lead. Each company comes back answered on all of them. Most enrichment stops at size and revenue. This gets you what you would otherwise dig up by hand.
Here is the whole thing running, start to finish.
The result
The team now builds a fresh list in a day, 500+ qualified leads matched to the criteria that matter, and can spin up as many lists as they want. Each one used to take about 70 hours by hand.
And because the criteria live in the project, aiming at a new market or a new enrichment just means writing a new brief.
Built with
- FastAPI
- Python
- React
- Vite
- TypeScript
- PostgreSQL
- OpenAI
- Jina
- Docker Compose
- Vercel
Questions we get asked about this
Our leads are oddly specific. Can it really find them?
That is what it is built for. It reads each company and judges it against your own criteria, however niche, so what you export is a list you can act on. The more specific your leads, the more time it saves you.
We already have lists and a CRM. Do we start over?
No. Upload your existing spreadsheet and it merges straight in, then gets enriched alongside the leads the system finds. Your current data becomes part of the same set.
How do we know the AI is not making it up?
Every answer shows the reasoning behind it and a link to the source it read, so you can check any lead in a click. It only answers from what it can actually find about a company.
We are not technical. Is this a big setup?
It takes two keys. Add your own OpenAI and Jina keys on the live site and it runs. There is nothing to install, and the keys stay in your browser.
Could you build something like this for us?
Yes. Point it at your market and your criteria and the same system runs again. We start with the smallest version that already produces leads worth calling, then widen from there.





