# Write cold email first lines that show you looked. Each one from a fact you can check 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. - For: SDRs, founders and agencies sending outbound - Providers: 3 (Icypeas, ScrapeCreators and Serper), 3 tools - Example (25 prospects, 25 profiles, 25 company pages’ posts, 25 news searches): at most $1.01, 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. - **Icypeas** (1 tool, at most $0.72): Each prospect’s LinkedIn profile: role, tenure and background. - **ScrapeCreators** (1 tool, at most $0.05): Each company’s recent LinkedIn posts. - **Serper** (1 tool, at most $0.25): Google News results for each company. ## Give this to your agent ```text 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. ``` ## You provide - Your prospect list with LinkedIn and company page URLs - What you sell ## What you get: a first line per prospect with its source - 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 ## How to write personalised first lines for cold emails in Claude or ChatGPT Prices are the most each call can reserve for this example: 25 prospects, 25 profiles, 25 company pages’ posts, 25 news searches. ### 1. Read the prospects Icypeas reads each prospect’s LinkedIn profile, with role, tenure and background. - [Icypeas LinkedIn profiles in batch](/tools/icypeas/scrape-profiles-batch.md) `icypeas/scrape-profiles-batch` (Icypeas, 25 profiles): at most $0.72 ### 2. Read their companies’ posts ScrapeCreators reads each company’s recent LinkedIn posts. - [LinkedIn company posts](/tools/scrapecreators/get-v1-linkedin-company-posts.md) `scrapecreators/get-v1-linkedin-company-posts` (ScrapeCreators, 25 companies): at most $0.05 ### 3. Read their news Serper searches Google News for each company. - [Google News search](/tools/serper/news.md) `serper/news` (Serper, 25 companies): at most $0.25 ### 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. Example total: at most $1.01. Each call is billed for measured usage; unused reservations are released. ## Ask it your way - Write a first line for each of these 25 prospects from something recent. - What did each of these companies post on LinkedIn this month? - Find a recent news hook for each company on my list. - Flag the prospects where you found nothing worth mentioning. ## Why through Agentik - Profiles, company posts and news come from Icypeas, ScrapeCreators and Serper through one connection. - Profiles are the largest share of the price, billed only when found. ## 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. ## Cold email first lines: 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. ## 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. - [Leads from a LinkedIn post](/linkedin-post-commenters.md): The people who commented on a LinkedIn post about your problem, their roles and companies, and verified emails for those who match your buyer. - [Account research](/account-research.md): Their site, latest news, official filings and the profiles of the people you’ll meet, in a one-page brief with sources. - [B2B data and enrichment tools for your agent](/tools/enrichment.md) - [News tools for your agent](/tools/news.md) - [Social tools for your agent](/tools/social.md) [All playbooks](/playbooks.md) · [Connection guides](/docs/clients.md) · [Billing](/docs/billing.md) --- [HTML page](/cold-email-first-lines) · [Agent index](/llms.txt)