Menu
Nederlands

Automated lead research and lead scoring

Your sales team shouldn't spend the morning searching for information about companies. I build systems that do the research for them and explain, with sources, why a company is worth a call.

Tell me about your project

The problem

Good sales research means combining many sources: business registers, annual figures, tenders, vacancies, news. Done by hand it takes hours, so it gets skipped and the team calls on gut feeling.

Generic lead databases don't know what makes a good customer for you. The signals that matter, like a new location, a won tender or a change in management, are specific to your market.

How I approach it

  1. Define what a good lead is

    Together with the sales team, we turn experience into explicit signals and weights.

  2. Connect the sources

    Business registers, insolvency records, procurement data, news and the company's own website.

  3. Research with sources

    A language model researches each company and writes a short brief. Every claim links to the source it came from.

  4. Score and prioritise

    A transparent score, so the team can see why a lead ranks high and correct it when it's wrong.

  5. Deliver into the CRM

    Approved leads go to your CRM with the brief attached, so the next step happens where the team already works.

What to watch out for

  • A score without an explanation won't be trusted. Show the reasons and the sources.
  • Language models can make things up. Only accept claims that point to a source.
  • Not every website allows automated collection. Prefer official registers and public data, and check the terms of the sources you use.
  • Data about contact persons falls under the GDPR. Collect only what you need for the purpose.

Projects like this

  • Investment company
  • 2026

Lead enrichment and lead scores

The sales team spent hours every morning researching companies before they knew who to call. Now the platform collects public data on each company, a language model researches it on the web, and every lead gets a score and a short brief with sources.

  • Connectors to business registers, insolvency records, public procurement data and news.
  • A background queue enriches and scores new leads automatically.
  • The team reviews each brief and sends the approved leads to the CRM.
  1. Business registerProcurement recordsNews
  2. Enrich
  3. Web research with sources
  4. Score and brief
  5. CRM export
  • Investment company
  • 2025

A personal opening line in each newsletter

The client sends a newsletter to its business contacts, and a generic opening doesn't get much attention. Now every contact gets a short, personal opening line that refers to a recent LinkedIn post by the person or their company, or to the last email exchange.

  • The tool pulls the contact list and company data from the CRM.
  • It finds recent LinkedIn posts by each person and each company.
  • A language model writes one or two sentences per contact, in the client's tone of voice.
  1. CRM contact listLinkedIn postsLast email exchange
  2. Find a relevant topic
  3. Write the opening line
  4. Personal opening in each newsletter

Frequently asked questions

Which sources can you use?

Public business registers, insolvency and procurement data, news, company websites and your own CRM history. Paid data providers can be added if you already have a subscription.

Does it replace the sales team?

No. It does the research so the team can spend its time on conversations. People still review the briefs and decide who to call.

Does it work with our CRM?

Usually, yes: most CRMs have an API. If yours doesn't, an export or a simple review screen works too.