# Brief yourself on a company before the call. Its news, its record and the people you’ll meet

Account research gives you, before a call, what the company does, what changed lately and who you’re meeting. With Agentik, your AI reads the company’s site with Firecrawl, its latest news with Serper, its official filings from SEC EDGAR, and the public LinkedIn profiles of the company and your attendees with Icypeas.

- For: Account executives, founders and investors
- Providers: 4 (Firecrawl, Serper, SEC EDGAR and Icypeas), 5 tools
- Example (One US-listed company, 3 pages of its site, 20 news results, its filings, its LinkedIn page and 3 attendees): at most $0.12, computed from the live catalog
- Updated: 2026-10-10

## Each provider does one part

No single provider covers this job. Through Agentik your AI calls each one for its part, from one connection and one prepaid balance.

- **Firecrawl** (1 tool, at most $0.0075): The company’s homepage, pricing and customers pages, as text.
- **Serper** (1 tool, at most $0.01): The latest Google News about the company.
- **SEC EDGAR** (1 tool, free): For a US-listed company, its latest 10-K, 10-Q and 8-K filings.
- **Icypeas** (2 tools, at most $0.10): The public LinkedIn profiles of the company and the people you’ll meet.

## Give this to your agent

```text
Use my connected Agentik MCP server for this job: account research.

Brief me on a company before my call. First ask me for its website, the names of the people I’ll meet and what I sell.

Read its homepage, pricing and customers pages with firecrawl/scrape. Get recent news with serper/news. If it is a US-listed company, read its latest filings with sec-edgar/company-filings. Read its LinkedIn page with icypeas/scrape-company and the attendees’ profiles with icypeas/scrape-profile.

Finish with a one-page brief (what they do, what changed, official record, who I’ll meet, five questions to ask) with a source for each fact.

Before running anything, inspect each tool with inspect_tool, ask me for any input you don’t have instead of inventing it, and tell me the total price. Wait for my go. At the end, tell me what Agentik charged.
```

## You provide

- The company’s website
- The names of the people you’ll meet
- What you sell

## What you get: a one-page account brief

- What they do, for whom, and at what price
- What changed in the last months, with sources
- Their SEC filings, when the company is US-listed
- Who you’ll meet, their background, and five questions to ask

## How to research an account before a sales call in Claude or ChatGPT

Prices are the most each call can reserve for this example: One US-listed company, 3 pages of its site, 20 news results, its filings, its LinkedIn page and 3 attendees.

### 1. Read their site

Firecrawl reads the homepage, pricing and customers pages.

- [Scrape a web page to markdown](/tools/firecrawl/scrape.md) `firecrawl/scrape` (Firecrawl, 3 pages): at most $0.0075

### 2. Catch up on the news

Serper searches Google News for what the company announced, or was covered for, lately.

- [Google News search](/tools/serper/news.md) `serper/news` (Serper, 20 results): at most $0.01

### 3. Check the official record

SEC EDGAR returns the profile and recent filings of a US-listed company.

- [SEC EDGAR company filings](/tools/sec-edgar/company-filings.md) `sec-edgar/company-filings` (SEC EDGAR, 1 company): free

### 4. Know who you’ll meet

Icypeas reads the company’s LinkedIn page and each attendee’s public profile.

- [Icypeas LinkedIn company page](/tools/icypeas/scrape-company.md) `icypeas/scrape-company` (Icypeas, 1 company): at most $0.0095
- [Icypeas LinkedIn profile](/tools/icypeas/scrape-profile.md) `icypeas/scrape-profile` (Icypeas, 3 people): at most $0.09

### 5. Write the brief

Your AI writes one page with a source for each fact, and the questions worth asking.

Example total: at most $0.12. Each call is billed for measured usage; unused reservations are released.

## Ask it your way

- Brief me on this prospect before tomorrow’s call with their VP of Engineering.
- What changed at this account in the last three months?
- Who am I meeting, and what did they do before?
- Give me five questions that show I did my homework.

## Why through Agentik

- Website, news, filings and profiles come from four providers through one connection.
- SEC filings are free. The rest is priced before your agent runs.

## Good to know

- SEC EDGAR covers companies that file with the SEC. For the others, your agent relies on the news and the website.
- Use profile data for your meeting only, and keep it out of shared tools you don’t control.

## When to use something else

To keep account data in your CRM automatically, an enrichment integration fits better. Agentik suits briefs before the meetings that matter.

## Account research: questions

### Does it work for private companies?

Yes. The site, the news and the profiles work for any company. Filings exist only for companies that file with the SEC.

### Couldn’t I just use one data provider?

No single provider covers websites, news, filings and profiles. Through Agentik your AI reads all four from one connection. The example costs at most $0.12.

### What does the example cost?

At most $0.12. The filings are free.

## Keep going

- [B2B lead list](/b2b-lead-list.md): People who match your buyer, emails found by two providers and verified, and a recent news hook for each company.
- [Company due diligence](/company-due-diligence.md): Its legal identity and status, its SEC filings when it is US-listed, when its domain was registered, and any lawsuits or liquidation in the news.
- [Market research](/market-research.md): The companies in the space, their pricing pages, Google search demand for the category, and what buyers say on Lemmy and X.
- [B2B data and enrichment tools for your agent](/tools/enrichment.md)
- [Company data tools for your agent](/tools/company.md)
- [News tools for your agent](/tools/news.md)

## Agent tool guides

- [Runtime tool discovery](/ai-agent-tool-discovery.md)

[All playbooks](/playbooks.md) · [Connection guides](/docs/clients.md) · [Billing](/docs/billing.md)

---

[HTML page](/account-research) · [Agent index](/llms.txt)
