# B2B Account Brief — AI Pre-Call Research for Sales Reps (`fuze/b2b-account-brief`) Actor

Give target company domains + what you sell; get a polished one-page AI account brief per company — overview, priorities, talking points, discovery questions and a cold opener — for pre-call sales research.

- **URL**: https://apify.com/fuze/b2b-account-brief.md
- **Developed by:** [Fredrik Hansson](https://apify.com/fuze) (community)
- **Categories:** Lead generation, AI
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $110.00 / 1,000 company briefeds

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.
Since this Actor supports Apify Store discounts, the price gets lower the higher subscription plan you have.

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

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
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.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## 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.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## B2B Account Brief — AI Pre-Call Research for Sales Reps

**Paste in the accounts you're about to call and get back a one-page brief for each one.** This Actor is a sales-enablement *super-actor*: give it a list of target company domains plus a line about what you sell, and for every company it orchestrates three research "organs" — firmographics, technology stack and recent news — then an AI synthesizes a polished **pre-call account brief** your account executive can read in two minutes before the meeting. Overview, what they do, likely priorities, tailored talking points, smart discovery questions, the right stakeholders to target, red flags, and a grounded cold-open line — plus a clean markdown version ready to paste straight into your CRM or Slack.

You bring the account list. It hands back a call-ready briefing.

![B2B Account Brief — AI Pre-Call Research for Sales Reps — input and sample output](https://datatools-hub.vercel.app/actor-shots/b2b-account-brief.png)

### 🔗 Chain it after your scraper

Already pulling accounts with **[Google Maps Scraper (`compass/crawler-google-places`)](https://apify.com/compass/crawler-google-places)**, **[LinkedIn Company Details Scraper (`harvestapi/linkedin-company`)](https://apify.com/harvestapi/linkedin-company)** or **[LinkedIn Jobs Scraper (`curious_coder/linkedin-jobs-scraper`)](https://apify.com/curious_coder/linkedin-jobs-scraper)**? Pipe the dataset straight in — paste its dataset ID (via the Integrations tab) and get a call-ready, one-page pre-call brief per account. Works with any Maps, LinkedIn or company scraper's output.

### Quick start

1. **Fill in the input** — set the fields in the input tab (prefilled with a working example).
2. **Click Start** — the Actor runs and writes one record per item to the dataset.
3. **Get your data** — export to **JSON, CSV or Excel**, or pull it via the API.

***

### The flow

```
                       ┌──────────────────────────────────────────┐
  domains +            │  ORGANS (orchestrated via Actor.call)      │
  "what you sell"  ──► │  firmographics → ai-company-enrichment     │ ──►  AI synthesis   ──►  one-page
                       │  tech stack    → b2b-tech-stack-detector   │      (OpenAI,            account brief
                       │  recent news   → google-news-scraper       │      grounded only      per company
                       └──────────────────────────────────────────┘      in organ data)
```

1. **Paste your target accounts** into `domains` and describe your `offering`.
2. The Actor runs each **research organ once across the whole list** (gracefully skipping any that return nothing).
3. **Per company**, an AI writes a grounded brief and assembles a clean `briefMarkdown` one-pager.

***

### What you get per company

For every company the brief contains:

1. **`companyOverview`** — 2–3 factual sentences on who they are.
2. **`whatTheyDo`** — one tight sentence.
3. **`industry`** and **`sizeSignal`** — category and size read.
4. **`techStackSummary`** — 1–2 sentences on their detected stack (or `null`).
5. **`recentDevelopments`** — short bullets drawn only from recent news (`[]` if none).
6. **`likelyPriorities`** — inferred business priorities to anchor the conversation.
7. **`talkingPoints`** — tailored to *your* `offering` when provided.
8. **`discoveryQuestions`** — smart, specific questions the rep can ask on the call.
9. **`stakeholdersToTarget`** — role titles likely relevant (e.g. "VP Engineering", "Head of Security").
10. **`redFlags`** — concrete reasons it may *not* be a fit (`[]` if none).
11. **`oneLineOpener`** — a single grounded cold-open line referencing one verifiable detail.
12. **`briefMarkdown`** — the entire brief as a clean one-page markdown doc, ready to paste into a CRM or Slack.

Every statement is grounded strictly in the research data — the AI never invents facts, customers or news.

***

### Three ways people use it

- **Sales reps / AE pre-call research** — stop googling five tabs before every call. One run gives you **pre-call briefing** for your whole day's pipeline, with **discovery call prep** questions already written. This is **account research** and **sales intelligence** on autopilot.
- **Account-based selling / ABM** — brief an entire target account list at once for **account planning**, align the team on priorities and stakeholders, and personalize outreach at scale.
- **SDR territory prep** — hand a new rep a territory of domains and get back a stack of briefs with openers and talking points, so **account research** and prospecting ramp from day one.

***

### Input

| Field | Type | Notes |
|---|---|---|
| `domains` | array | **Required.** Company domains, website URLs or emails (domain is extracted). One per line — these are the accounts to brief. |
| `offering` | string | What you sell. Tailors talking points, red flags and the opener to each account. |
| `maxResults` | integer | Cap how many companies to brief. Default `25`, max `1000`. One charge per company. |
| `maxConcurrency` | integer | How many companies to synthesize in parallel. Default `3`, max `10`. |
| `model` | string | OpenAI model override. Default `gpt-4o-mini`. |
| `useEnrichment` | boolean | Call `fuze/ai-company-enrichment` for firmographics. Default `true`. |
| `useTechStack` | boolean | Call `fuze/b2b-tech-stack-detector` for the tech stack. Default `true`. |
| `useNews` | boolean | Call `fuze/google-news-scraper` for recent developments. Default `true`. |

#### Minimal input example

```json
{
  "domains": ["stripe.com", "notion.so"],
  "offering": "We sell a SOC2 compliance automation platform for SaaS companies."
}
```

***

### Output example

```json
{
  "domain": "notion.so",
  "companyName": "Notion",
  "industry": "Productivity Software / SaaS",
  "sizeSignal": "Large, fast-growing company",
  "techStackSummary": "A modern stack built on React and Next.js with Segment analytics and Intercom support — a product-led engineering org.",
  "recentDevelopments": [
    "Expanded its AI features across the workspace",
    "Continued enterprise push with new admin controls"
  ],
  "likelyPriorities": [
    "Scaling enterprise trust and security posture",
    "Shipping AI features quickly without slowing compliance"
  ],
  "talkingPoints": [
    "As Notion moves upmarket, enterprise buyers demand SOC2 evidence fast — automation removes the audit drag.",
    "A product-led org can keep shipping while compliance runs in the background."
  ],
  "discoveryQuestions": [
    "How are you handling SOC2 evidence collection across engineering teams today?",
    "What's slowing down your enterprise security reviews?"
  ],
  "stakeholdersToTarget": ["Head of Security", "VP Engineering", "Compliance Lead"],
  "redFlags": ["May already have mature in-house compliance tooling given their scale"],
  "oneLineOpener": "Noticed Notion's enterprise push — curious how your team is keeping SOC2 evidence current while shipping AI features this fast.",
  "sourcesUsed": ["ai-company-enrichment", "b2b-tech-stack-detector", "google-news-scraper"],
  "briefMarkdown": "# Account Brief — Notion\n**Domain:** notion.so  ·  **Industry:** Productivity Software / SaaS\n\n## Overview\nNotion is a connected workspace...\n\n## Talking points\n- As Notion moves upmarket...\n\n## Cold opener\n> Noticed Notion's enterprise push..."
}
```

***

### How the orchestration works

This Actor is a **super-actor**: it doesn't scrape anything itself. It calls proven public organs via `Actor.call` and fuses their output with an LLM:

| Organ | Actor | Provides |
|---|---|---|
| Firmographics | [`fuze/ai-company-enrichment`](https://apify.com/fuze/ai-company-enrichment) | What they do, industry, size, offerings, target customers |
| Technographics | [`fuze/b2b-tech-stack-detector`](https://apify.com/fuze/b2b-tech-stack-detector) | Detected tech stack, maturity, inferred team signals |
| Recent news | [`fuze/google-news-scraper`](https://apify.com/fuze/google-news-scraper) | Latest headlines + snippets per company |

Each organ runs **once** across your whole domain list. Any organ that errors or returns nothing is skipped gracefully — the brief is still written from whatever data came back, and `sourcesUsed` always reflects reality.

***

### Pay-per-event pricing

This Actor uses **pay-per-event** billing with a single event:

| Event | Price | Charged when |
|---|---|---|
| `company-briefed` | **$0.25** | Once per company researched and briefed. **This one charge bundles up to three orchestrated sub-actor runs** (firmographics, tech stack, news) plus the OpenAI synthesis into a finished one-page brief. |

The Actor logs its OpenAI token usage and the estimated AI cost at the end of every run, so the event price always stays safely above the model cost.

***

### Setup

The AI synthesis layer calls the OpenAI API. Set the environment variable / secret **`OPENAI_API_KEY`** on the Actor. Without it the run stops early — the brief synthesis needs the model.

***

### Use it from an AI agent (Apify MCP server)

This Actor is available through the [Apify MCP server](https://mcp.apify.com), so AI agents (Claude, ChatGPT, or anything that speaks MCP) can call it as a tool — hand it `domains` and an `offering`, and read back finished account briefs — with no custom integration code.

***

### Run it locally

```bash
npm install
## put your input in storage/key_value_stores/default/INPUT.json
export OPENAI_API_KEY=sk-...
apify run -p
```

***

### Related actors

- [B2B Intent Radar](https://apify.com/fuze/b2b-intent-radar) — Surface buying-intent signals for your target accounts.
- [AI Company Enrichment](https://apify.com/fuze/ai-company-enrichment) — Turn domains into structured firmographic profiles with contacts and ICP fit.
- [B2B Tech Stack Detector](https://apify.com/fuze/b2b-tech-stack-detector) — Detect the technology stack behind any company's website.
- [AI Cold Email Personalizer](https://apify.com/fuze/ai-cold-email-personalizer) — Turn a list of domains into personalized cold-email openers.

# Actor input Schema

## `domains` (type: `array`):

Company domains, website URLs or emails (the domain is extracted). One per line — these are the accounts you want briefed.

## `offering` (type: `string`):

Describe what your company sells. If set, talking points, red flags and the cold opener are tailored to how your offering fits each account.

## `datasetId` (type: `string`):

Optional. Read the domains from a previous Actor run's dataset — for no-code chaining via the Integrations tab.

## `datasetField` (type: `string`):

Which dataset field holds the domain/URL. Leave blank to auto-detect (domain, website, companyDomain, url, companyUrl).

## `maxResults` (type: `integer`):

Max companies to brief. One pay-per-event charge per company briefed.

## `maxConcurrency` (type: `integer`):

How many companies to synthesize in parallel in the AI brief stage.

## `model` (type: `string`):

Override the model (default gpt-4o-mini).

## `useEnrichment` (type: `boolean`):

Call fuze/ai-company-enrichment for firmographics (what they do, industry, size, offerings).

## `useTechStack` (type: `boolean`):

Call fuze/b2b-tech-stack-detector for the detected technology stack and team signals.

## `useNews` (type: `boolean`):

Call fuze/google-news-scraper for recent developments (headlines + snippets) per company.

## Actor input object example

```json
{
  "domains": [
    "stripe.com",
    "notion.so"
  ],
  "maxResults": 25,
  "maxConcurrency": 3,
  "model": "gpt-4o-mini",
  "useEnrichment": true,
  "useTechStack": true,
  "useNews": true
}
```

# Actor output Schema

## `briefs` (type: `string`):

All account briefs in the default dataset.

# 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 = {
    "domains": [
        "stripe.com",
        "notion.so"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("fuze/b2b-account-brief").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 = { "domains": [
        "stripe.com",
        "notion.so",
    ] }

# Run the Actor and wait for it to finish
run = client.actor("fuze/b2b-account-brief").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 '{
  "domains": [
    "stripe.com",
    "notion.so"
  ]
}' |
apify call fuze/b2b-account-brief --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,fuze/b2b-account-brief"
        }
    }
}
```

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/fV0aHfEgD15cf0AAA/builds/tjhbfQ8qhJ6nwitIG/openapi.json