# B2B Sales Intelligence Agent (`joseph99/my-actor`) Actor

AI-powered B2B lead research agent. Scrapes company websites, scores ICP fit (0–100), surfaces buying signals from news, and generates personalised cold email + LinkedIn outreach copy. Powered by LangGraph + OpenRouter.

- **URL**: https://apify.com/joseph99/my-actor.md
- **Developed by:** [JOSEPH](https://apify.com/joseph99) (community)
- **Categories:** AI, Automation, Lead generation
- **Stats:** 3 total users, 0 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $200.00 / 1,000 lead enricheds

This Actor is paid per event and usage. You are charged both the fixed price for specific events and for Apify platform usage.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

Actors are web data automations that power AI and operations. They run on the Apify platform to scrape websites, process data, connect APIs, and automate workflows.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.
Actors are written with capital "A".

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.
The best way to integrate Actors is as follows.

- **AI agents and MCP clients** — the [Apify MCP server](https://docs.apify.com/integrations/mcp.md) at `https://mcp.apify.com` (remote, streamable HTTP, OAuth on first use).
- **Agentic workflows and local Actor development** — [Agent Skills](https://apify.com/.well-known/agent-skills/index.json) with the [Apify CLI](https://docs.apify.com/cli/docs.md): `npm install -g apify-cli`, then `apify login`.
- **JavaScript/TypeScript projects** — the official [JS/TS client](https://docs.apify.com/api/client/js/docs.md): `npm install apify-client`.
- **Python projects** — the official [Python client](https://docs.apify.com/api/client/python/docs.md): `pip install apify-client`.
- **Any other language** — the [REST API](https://docs.apify.com/api/v2.md).

For usage examples, see the [API](#api) section below.

For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt).

# README

## B2B Sales Intelligence & Lead Qualification Agent

Turn a list of company domains into a full sales intelligence dossier — complete with ICP scores, buying signals, and personalised outreach copy — in seconds.

Powered by **LangGraph** + **OpenRouter** (supports GPT-4o, GPT-4o-mini, and more).

***

### What it does

For each company you provide, the agent runs a 5-step research pipeline:

1. **Website scrape** — Fetches the homepage and About page to understand what the company actually does
2. **Firmographic enrichment** — Pulls tech stack data (via BuiltWith) and company details
3. **News signals** — Fetches recent headlines from Google News to surface buying triggers (fundraising, hiring, product launches, leadership changes)
4. **ICP scoring** — Scores the company 0–100 on how well it fits your Ideal Customer Profile, with detailed reasoning
5. **Outreach generation** — Writes a personalised cold email (150–200 words) and LinkedIn message (60–80 words) referencing real news signals

All results are pushed to a structured dataset you can export as JSON, CSV, or Excel.

***

### Who is this for

- **SDRs and AEs** who want to walk into a call knowing the company inside-out
- **Sales ops teams** automating prospect research at scale
- **Lead generation agencies** delivering enriched lists to clients
- **Founders** doing outbound without a sales team

***

### Input

| Field | Type | Required | Description |
|---|---|---|---|
| `leads` | Array | Yes | List of `{ domain, companyName }` objects |
| `icpCriteria` | Object | No | Your ICP definition (industries, sizes, regions, pain points) |
| `modelName` | String | No | LLM model: `gpt-4o-mini` (default), `gpt-4o`, `o1`, `o3-mini` |
| `openaiApiKey` | String | Yes | Your **OpenRouter** API key (get one free at openrouter.ai) |

#### Example input

```json
{
  "leads": [
    { "domain": "stripe.com", "companyName": "Stripe" },
    { "domain": "notion.so", "companyName": "Notion" },
    { "domain": "linear.app", "companyName": "Linear" }
  ],
  "icpCriteria": {
    "target_industries": ["SaaS", "FinTech", "Developer Tools"],
    "target_company_sizes": ["51-200", "201-500"],
    "target_regions": ["North America", "Europe"],
    "pain_points": ["manual workflows", "team collaboration", "scaling engineering"]
  },
  "modelName": "gpt-4o-mini",
  "openaiApiKey": "YOUR_OPENROUTER_API_KEY"
}
```

***

### Output

Each lead produces one row in the dataset:

| Field | Type | Description |
|---|---|---|
| `domain` | string | Company domain |
| `companyName` | string | Company name |
| `icpScore` | number | ICP fit score 0–100 |
| `icpReasoning` | string | Why this score was given |
| `firmographics` | object | About page text + tech stack snippet |
| `newsSignals` | array | Recent news headlines |
| `outreachEmail` | string | Ready-to-send cold email |
| `outreachLinkedIn` | string | Ready-to-send LinkedIn message |
| `error` | string | Error message if a lead failed, null otherwise |

***

### Pricing

This actor uses **Pay-Per-Event** (PPE) pricing:

| Event | Cost |
|---|---|
| Actor start | $0.10 per run |
| Lead enriched | $1.00 per successfully processed lead |

A run with 10 leads costs roughly **$10.10** — far cheaper than Apollo, ZoomInfo, or Clay for equivalent personalised research.

***

### How to get your OpenRouter API key

1. Go to [openrouter.ai](https://openrouter.ai)
2. Sign up for a free account
3. Navigate to **Keys** → **Create Key**
4. Paste the key into the `openaiApiKey` field

OpenRouter supports GPT-4o, Claude 3.5, Gemini, and many more models on a pay-as-you-go basis.

***

### Notes

- The agent uses Google News RSS and public web pages only — no paid data providers required
- Results quality improves with a more detailed `icpCriteria` object
- For best results use `gpt-4o`; for fastest/cheapest use `gpt-4o-mini`
- Each lead takes approximately 15–40 seconds depending on the model and website speed

# Actor input Schema

## `leads` (type: `array`):

List of companies to research. Each item must have a 'domain' field (e.g. 'stripe.com') and optionally a 'companyName' field.

## `icpCriteria` (type: `object`):

Your Ideal Customer Profile definition. Used to score each lead 0-100.

## `modelName` (type: `string`):

The OpenRouter model to use. gpt-4o gives best results; gpt-4o-mini is faster and cheaper.

## `openaiApiKey` (type: `string`):

Your OpenRouter API key. It is stored as a secret input and decrypted only for the Actor run.

## Actor input object example

```json
{
  "leads": [
    {
      "domain": "stripe.com",
      "companyName": "Stripe"
    },
    {
      "domain": "notion.so",
      "companyName": "Notion"
    }
  ],
  "icpCriteria": {
    "target_industries": [
      "SaaS",
      "FinTech",
      "E-commerce",
      "MarTech"
    ],
    "employee_range": "50-5000",
    "revenue_range": "$5M-$500M",
    "target_titles": [
      "VP Sales",
      "Head of Revenue",
      "CRO",
      "CEO"
    ],
    "pain_points": [
      "scaling sales team",
      "lead quality",
      "CRM hygiene",
      "pipeline visibility"
    ],
    "tech_stack_must_have": [],
    "tech_stack_nice_to_have": [
      "Salesforce",
      "HubSpot",
      "Outreach"
    ]
  },
  "modelName": "openai/gpt-4o-mini"
}
```

# Actor output Schema

## `companyName` (type: `string`):

Name of the researched company

## `icpScore` (type: `string`):

Ideal Customer Profile fit score 0-100

## `outreachEmail` (type: `string`):

Ready-to-send personalised cold email

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "leads": [
        {
            "domain": "stripe.com",
            "companyName": "Stripe"
        },
        {
            "domain": "notion.so",
            "companyName": "Notion"
        }
    ],
    "icpCriteria": {
        "target_industries": [
            "SaaS",
            "FinTech",
            "E-commerce",
            "MarTech"
        ],
        "employee_range": "50-5000",
        "revenue_range": "$5M-$500M",
        "target_titles": [
            "VP Sales",
            "Head of Revenue",
            "CRO",
            "CEO"
        ],
        "pain_points": [
            "scaling sales team",
            "lead quality",
            "CRM hygiene",
            "pipeline visibility"
        ],
        "tech_stack_must_have": [],
        "tech_stack_nice_to_have": [
            "Salesforce",
            "HubSpot",
            "Outreach"
        ]
    },
    "modelName": "openai/gpt-4o-mini"
};

// Run the Actor and wait for it to finish
const run = await client.actor("joseph99/my-actor").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {
    "leads": [
        {
            "domain": "stripe.com",
            "companyName": "Stripe",
        },
        {
            "domain": "notion.so",
            "companyName": "Notion",
        },
    ],
    "icpCriteria": {
        "target_industries": [
            "SaaS",
            "FinTech",
            "E-commerce",
            "MarTech",
        ],
        "employee_range": "50-5000",
        "revenue_range": "$5M-$500M",
        "target_titles": [
            "VP Sales",
            "Head of Revenue",
            "CRO",
            "CEO",
        ],
        "pain_points": [
            "scaling sales team",
            "lead quality",
            "CRM hygiene",
            "pipeline visibility",
        ],
        "tech_stack_must_have": [],
        "tech_stack_nice_to_have": [
            "Salesforce",
            "HubSpot",
            "Outreach",
        ],
    },
    "modelName": "openai/gpt-4o-mini",
}

# Run the Actor and wait for it to finish
run = client.actor("joseph99/my-actor").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "leads": [
    {
      "domain": "stripe.com",
      "companyName": "Stripe"
    },
    {
      "domain": "notion.so",
      "companyName": "Notion"
    }
  ],
  "icpCriteria": {
    "target_industries": [
      "SaaS",
      "FinTech",
      "E-commerce",
      "MarTech"
    ],
    "employee_range": "50-5000",
    "revenue_range": "$5M-$500M",
    "target_titles": [
      "VP Sales",
      "Head of Revenue",
      "CRO",
      "CEO"
    ],
    "pain_points": [
      "scaling sales team",
      "lead quality",
      "CRM hygiene",
      "pipeline visibility"
    ],
    "tech_stack_must_have": [],
    "tech_stack_nice_to_have": [
      "Salesforce",
      "HubSpot",
      "Outreach"
    ]
  },
  "modelName": "openai/gpt-4o-mini"
}' |
apify call joseph99/my-actor --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,joseph99/my-actor"
        }
    }
}

```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/aizb2Xpr7eHuZ2Y06/builds/XmG4q1fhPWpwqeJIR/openapi.json