Quick Start Guide

Get Started in 5 Minutes

Conturs scores your leads by comparing them to successful conversions of similar businesses — automatically. No manual rules, no black-box algorithms. Here's how to get started.

Step 1: Create Your Account

Go to conturs.com and click Start Free. Enter your work email — you'll receive a magic link to sign in. No password needed.

After signing in, you'll land on your Dashboard. Here you can manage your API key, view scoring stats, and configure integrations.

Step 2: Get Your API Key

Go to Dashboard → API and copy your API key. You'll need this to authenticate scoring requests.

Step 3: Set Up the Scoring Service

Conturs uses a lightweight self-hosted scoring service that runs on your infrastructure. Your lead data never leaves your servers.

# Clone and build
git clone https://github.com/conturs-team/scoring.git
cd scoring
go build -o scoring main.go

# Start the service
./scoring
# Running on http://localhost:8082

The service connects to api.conturs.com once to fetch your personalized scoring weights, then caches them locally. All scoring happens on your machine.

Step 4: Score Your First Leads

Send a batch of leads to the scoring service:

curl -X POST http://localhost:8082/leads \
  -H "Content-Type: application/json" \
  -d '{
    "api_key": "YOUR_API_KEY",
    "email": "you@company.com",
    "leads": [
      {
        "email": "john@acme.com",
        "company": "Acme Corp",
        "job_title": "VP Sales",
        "industry": "B2B SaaS",
        "lead_status": "qualified"
      }
    ]
  }'

You'll get back scored leads with transparent factor breakdowns:

{
  "scores": [
    {
      "email": "john@acme.com",
      "score": 87,
      "label": "Hot Lead",
      "factors": [
        {"name": "Company Match", "weight": 0.15, "value": 1.0, "contribution": 0.15},
        {"name": "Industry Match", "weight": 0.12, "value": 1.0, "contribution": 0.12},
        {"name": "Lead Status", "weight": 0.10, "value": 0.9, "contribution": 0.09}
      ]
    }
  ],
  "method": "similar_clients"
}

Step 5: Understand Your Scores

Every lead gets a score from 0 to 100 based on personalized weights learned from similar businesses.

Score Labels

• 80–100: Hot Lead — Excellent fit. Route to sales immediately.

• 60–79: Warm Lead — Good fit. Add to SDR outreach sequence.

• 40–59: Cool Lead — Average fit. Nurture if other signals are positive.

• 0–39: Cold Lead — Low fit. Marketing drip only.

What Makes Scores Transparent

Every score comes with a factors breakdown showing exactly what contributed:

• Factor name — Which attribute was evaluated (Company Match, Industry, Engagement, etc.)

• Weight — How important this factor is (personalized for your business)

• Value — How well this lead performed on this factor

• Contribution — How much this factor added to the total score

Weight Methods

Your scores improve over time through three weight sources:

• similar_clients — Best quality. Based on conversion patterns of businesses like yours.

• industry_prior — Good quality. Industry-specific benchmarks when limited similar client data.

• default — Baseline weights. Used on initial registration, still produces useful scores.

Step 6: Connect to Your Workflow

Integrate the scoring service with your existing tools:

• HubSpot — Native app available (scores sync automatically to contact properties)

• Uspacy — Install from the Uspacy marketplace

• n8n / Zapier — HTTP Request to POST /leads endpoint

• Custom code — Any HTTP client works (Python, JavaScript, curl)

Step 7: Improve Over Time (Optional)

Send feedback on lead outcomes to improve scoring for your business and similar companies:

• converted — Lead became a customer

• replied — Lead engaged with outreach

• clicked — Lead clicked a link

• ignored — No response

• bounced — Email bounced

The more feedback you provide, the more accurate your personalized weights become.

Next Steps

• API Reference — Full endpoint documentation, all lead fields, response format

• HubSpot Guide — Native integration setup

• FAQ — Common questions about scoring and privacy