Clean up company names for email merge fields
Converts raw vendor and CRM company names into the natural short form that reads like a human typed it — no 'LLC', no ALL CAPS, no taglines — so 'quick question about {company}' merges cleanly. One of the highest ROI-per-token prompts in outbound: every recipient sees this field.
You are a data-cleaning function running inside an enrichment pipeline. Your job is to convert one raw company name into the short, natural form a human would use in a sentence — the version that belongs in a cold email merge field. 'Acme Widgets Holdings, LLC' becomes 'Acme Widgets'. 'ACME WIDGETS INC.' becomes 'Acme Widgets'. A rep writing by hand would never type the legal suffix, and neither do you.
You will be given a raw company name string from a CRM, data vendor, or scrape.
Cleaning rules:
- Strip legal suffixes and their punctuation: Inc, LLC, Ltd, GmbH, S.A., B.V., Pty, Corp, Co., PLC, LLP, and equivalents.
- Strip trailing descriptors that are not part of the used name: 'Group', 'Holdings', 'Technologies', 'Solutions' — ONLY when the remaining name stands alone and remains unambiguous ('Meridian Technologies' → 'Meridian', but 'Align Technologies' stays if 'Align' alone is unclear; when unsure, keep the descriptor).
- Fix casing: ALL-CAPS and all-lowercase names become natural casing, but preserve intentional brand casing you can recognize from the string itself (iContact, eBay-style patterns, interior capitals).
- Preserve '&' vs 'and' as written. Preserve hyphens and apostrophes.
- Remove taglines, locations, and pipes ('Acme Widgets | Chicago's #1 Widget Shop' → 'Acme Widgets').
- Never translate, never abbreviate to initials, never expand abbreviations, never rename.
OUTPUT CONTRACT — follow exactly:
- Return ONLY the cleaned name as plain text. No quotes, no explanation, no restating the input.
- If the input is empty, a URL, a person's name, or not identifiable as a company name, return exactly: NOT_FOUND
- When a cleaning rule is uncertain for this string, prefer the more conservative edit. The output must always be a name the company itself would recognize.How to use it
- 1
Copy the prompt into Claude, ChatGPT, or any LLM — or into a Clay AI column.
- 2
In Clay, map your raw company-name column as the input, and write results to a new column — keep the original for CRM matching and legal-name needs.
- 3
Scan 50 outputs sorted alphabetically; suffix and casing errors cluster and jump out instantly in a sorted list.
- 4
Point every sequencer merge field at the cleaned column, never the raw one.
Best practices
Run cleanup before deduplication — 'Acme Inc' and 'ACME, LLC' collapse into one row only after both normalize to 'Acme'.
Add your market's local suffixes to the strip list (S.r.l., Oy, AB, K.K.) if you sell internationally.
Keep the conservative-edit rule intact when tempted to strip harder; an over-shortened name a company doesn't use reads as a data error mid-email.
Example: what this looks like in practice
A team launching a 15,000-contact campaign pulls company names from two vendors: one delivers legal names ('BRIGHTPATH LOGISTICS HOLDINGS, LLC'), the other scrapes LinkedIn taglines ('Brightpath | Moving Freight Forward 🚚'). Both normalize to 'Brightpath Logistics'. Before adopting this prompt they'd shipped a campaign where 30% of emails read 'companies like YOUR COMPANY NAME, INC.' — reply rate 0.9%. The cleaned rerun of the same list and copy pulls 3.4%. Deduplication after cleanup also merges 900 duplicate accounts the raw strings had hidden, saving a double-send that would have burned two domains.
Best fit
This prompt is one gear in a bigger machine. We orchestrate 20+ tools into outbound systems our clients own — and guarantee the results.
Apply for a Pilot Spot → →Frequently asked questions
Because merge fields expose your data. 'Quick question about ACME WIDGETS HOLDINGS, LLC' announces automation in the first line and kills the researched feel everything else worked to build. Humans write 'Acme Widgets'. Cleaning the column once means every merge field in every sequence reads naturally — the cheapest reply-rate improvement available.
More personalization at scale (clay & claygents) prompts
Generate a cold email first line from scraped research data
The workhorse of AI-personalized outbound: converts whatever research your enrichment waterfall produced into one 12–22-word observation-led first line per row. The swap-test rule and fact-invention ban are what separate lines that read researched from the AI slop prospects now delete on sight.
Turn a Claygent website scrape into a personalized one-liner
Produces a sub-25-word, website-specific opening line for every row in a Clay table — no human in the loop. The output contract forces plain text only and a NOT_FOUND fallback, so unreachable sites and thin homepages return a filterable sentinel instead of a hallucinated compliment that ends up in a prospect's inbox.
Analyze a pricing page for sales-relevant intelligence
Extracts a structured pricing profile from any pricing page: model, tier count, exact displayed prices, free-offer type, and a one-line read on their sales motion. At scale it segments prospect lists by how companies charge — which predicts budget, buying process, and which of your angles will land.