Write cold email first lines that show you looked

For each prospect on your list, their LinkedIn profile, their company’s latest posts and news, turned into a first line that shows you looked.

Steps

At most, per call

A good first line proves you read something about the person or their company. With Agentik, your AI reads each prospect’s LinkedIn profile with Icypeas, their company’s recent LinkedIn posts through ScrapeCreators, and their news with Serper.

Step 1: Read the prospects
Icypeas reads each prospect’s LinkedIn profile, with role, tenure and background.
- Icypeas LinkedIn profiles in batchIcypeas · 25 profiles$0.72
Step 2: Read their companies’ posts
ScrapeCreators reads each company’s recent LinkedIn posts.
- LinkedIn company postsScrapeCreators · 25 companies$0.05
Step 3: Read their news
Serper searches Google News for each company.
- Google News searchSerper · 25 companies$0.25
Step 4: Write the first lines
Your AI writes a first line per prospect with the fact and its source, and flags prospects with nothing recent.
Your agent does this part, with no tool call.

Cost of the example

At most $1.01one run

25 prospects, 25 profiles, 25 company pages’ posts, 25 news searches.

Give this to your agent

Use my connected Agentik MCP server for this job: cold email first lines.

Write personalised first lines for my prospect list. First ask me for the list (name, company, LinkedIn URL, company page) and what I sell.

Read each prospect’s profile with icypeas/scrape-profiles-batch. Read each company’s recent LinkedIn posts with scrapecreators/get-v1-linkedin-company-posts. Search each company’s news with serper/news.

Finish with a table (prospect, the fact used, its source, first line) and flag prospects where nothing recent was found instead of inventing a hook.

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.

3 providers, one connection

What you get

A first line per prospect with its source.

You provide

Your prospect list with LinkedIn and company page URLs
What you sell

Your agent returns

A first line per prospect
The fact and source behind each line
Prospects with no recent hook, flagged
A short follow-up idea for each

First linesExample layout

Prospect	Fact used	Source	First line
Prospect A	New office opening	Company post	Congrats on the new office
Prospect B	Promoted this year	Profile	Six months into the new role
Prospect C	Nothing recent	None	Flagged, no hook

Placeholders. Your rows come from your run.

Each provider does one part

No single provider covers this job. Your agent calls each one for its part, from one connection.

Good to know

Each line cites a real post or article; your AI flags a prospect rather than invent a hook.
Keep lines short and about them; the pitch comes after.

When to use something else

To send sequences and track replies, use your outreach tool. This playbook writes the opening lines from facts you can check.

Questions

Will it invent a hook when it finds nothing?

No. It flags the prospect instead, so you decide.

Does it send the emails?

No. It writes the first lines; your outreach tool sends them.

What does the example cost?

At most $1.01, reserved before each call and settled at the measured usage.

Connect your agent to 2,400+ tools for free

Get $5 free credit Get $5 free credit