The boundary
We don't want your pipeline.
CRMs are a solved problem and a crowded market. RepVector does the part nobody solved: finding the complete universe of who to call in a market, enriching each name with what that organisation actually publishes about itself, understanding where it is exposed against competitors, and scoring the list so the call order is already decided. That list exports clean to Salesforce, HubSpot, or whatever you already run. We'd rather be the best answer to one question than a mediocre version of software you already own.
What RepVector does
- Resolves the geography you name to every county, ZIP, tract, and metro it touches
- Assembles the complete population of facilities, clinicians, and referral sources there
- Reads each target's own website for services, locations, phones, and named decision-makers
- Compares capabilities against competing providers and flags what changed since last time
- Scores every name 0–100 on volume, payer mix, opportunity gap, contact quality and recency
- Ranks counties for a siting decision, with Medicare rate context and the formulas printed
- Finds more accounts like the ones already working, from published attributes
- Locates published district contracts and vendors for teams selling into school districts
- Re-checks saved markets weekly and digests what moved, with the evidence URL
- Attaches a one-line reason and a citation to every row
- Exports the whole thing as CSV, Excel or JSON with provenance intact
What it will never do
- Log calls, emails, meetings, or visits
- Hold pipeline stages, deals, or forecast
- Sequence outreach or send email on your behalf
- Track rep activity or generate scorecards
- Store your customer records or contact history
- Replace Salesforce, HubSpot, or whatever you already run
How the handoff works
Every export is a flat CSV or JSON file with a header block carrying the query, exact parameters, geography, vintage, capture time, selection reason, publisher notes, and citation URL. The provenance travels with the data — so six months later, anyone can still tell where a row came from.
| Field | What it carries |
|---|---|
| target_name | Facility, organization, or clinician name as published |
| npi / ccn / facility_id | Publisher identifier for deduplication against your CRM |
| address, city, state, zip, lat, lon | Practice location, geocoded where the source allows |
| taxonomy / specialty / service_line | What they do, in the publisher's own vocabulary |
| website, phone | Published contact route for the organisation |
| contact_name, contact_title, contact_source_url | Named decision-maker read from the target's own site, with the page it came from |
| capabilities, capability_gaps | Services the site publishes, and the ones competitors publish that it doesn't |
| rank, tier, fit_score | Position in the target universe, its tier, and the 0–100 composite |
| score_breakdown | Volume, payer mix, opportunity gap, web completeness, contact and change-recency contributions |
| reason | One line stating why this name ranked where it did |
| last_change, last_change_url | What moved since the previous run, and the evidence for it |
| source_id, vintage, captured_at | Which dataset, which published period, when we pulled it |
| citation_url | Link back to the origin dataset |
Map npi or ccn to your CRM's account key and the import dedupes against what your reps already touched. What's left is the part of the market nobody has called yet — which is the whole point.
Build one list, export it, and see whether it loads clean.
Start free