Status : ActiveRef BS_RECORD
Remote · Canada / US / UK / EU
← The LedgerLEDGER-023
RestrictedClaude / CoworkClienta B2B SaaS company

Automatic research on every inbound lead

No inbound lead reaches sales un-researched

Paste an email or a website. About two minutes later there's a sales-ready brief in the team's workspace — who they are, how well they fit, and how to approach them — so every inbound lead arrives pre-briefed instead of cold.

The problem

Researching every inbound lead by hand takes 30 to 60 minutes each — so when leads come in faster than that, the research gets skipped and sales works them blind.

The solution

An engine that reads a lead's website and socials, scores how well they fit, and writes a sales-ready brief into the team's workspace in about two minutes — so every inbound lead is pre-researched before sales makes contact.

Claude CodeNotionFirecrawlPython
BeforeAfter
Research per lead30–60 minutes across a few tabsabout 2 minutes — paste and go
Which leads get researchedthe ones someone had time forevery one, automatically
How consistent it isno two worked up the same waythe same workup, every lead
Knowing if they fita quick gut read, if anya fit score with the reasons behind it
What sales opens witha name and an email addressa sales-ready brief, ready to act on
The delta

Research stops being a 30-to-60-minute chore that gets cut the moment things get busy, and becomes something that just happens to every lead automatically. The compression — half an hour down to two minutes — matters, but the real change is coverage: every lead gets the same workup, so the team isn't choosing which leads are worth researching and quietly flying blind on the rest.

What I built

An engine that researches every inbound lead before sales makes contact. It isn't an app to log into — it runs as an AI routine inside the tools the team already uses (Claude and Notion), so a brief lands where the team already works.

  • One simple input. Paste an email address or a website. That's all it needs to start — no form to fill in, no setup per lead.
  • Reads the lead from the outside. It reads the lead's website and social profiles, gathering what's publicly known about who they are and what they do — the same digging a person would do across a handful of tabs, done in one pass.
  • Scores how well they fit. It rates the lead against the kind of customer the company is actually trying to win, and gives the reasons behind the rating — so a rep gets a judgment to act on, not just a summary to read.
  • Writes a sales-ready brief. In about two minutes it produces a brief — who they are, whether they fit, and how to approach them — written straight into the team's workspace, ready to use.
  • Runs on every lead. Because it's fast and consistent, it isn't reserved for the leads that look promising. Every inbound lead gets the same workup, so the team stops quietly flying blind on the rest.

It's in regular use — the team's growth lead runs it weekly as inbound comes in.

Why it matters

The payoff is coverage. The point isn't only that two minutes beats half an hour — it's that the half-hour version was the first thing to get cut whenever leads came in faster than the team could keep up, which left reps reaching out to people they knew nothing about. When research is this fast and this consistent, it stops being a choice. Every inbound lead arrives pre-briefed, the fortieth gets the same careful read as the first, and sales never makes first contact cold.

Normally, "every lead researched and scored before sales touches it" is the kind of thing a company staffs a sales-development function to do. Here it runs automatically, inside the tools the team already works in, on every lead that comes in.

The hard part

The hard part isn't gathering facts about a company — it's turning them into a judgment a salesperson will actually act on, the same way every time. A summary of someone's website is easy and nearly useless; what a rep needs is "are these the kind of customer we want, and why." So the work is in the scoring: deciding which signals off a website and social profiles actually predict fit, and encoding that judgment so the fortieth lead of the day gets the same careful read as the first. And because the brief lands in front of a customer conversation, it stays honest about what it found versus what it's inferring — a thin brief that says so beats a confident one that's guessing.

The bottom line

The shift is from researching the leads you have time for to having every lead arrive already researched. Sales never opens cold, the workup is the same for the fortieth lead as the first, and the half-hour of digging that used to get skipped under pressure now just happens — quietly, on every lead.

Held back

How the engine scores fit against the ideal customer — which signals it reads off a website and social profiles, and how it turns them into a judgment a salesperson can actually trust — is what separates a useful brief from a generic summary. That scoring method is the part clients pay for.

Talk it through under NDA