LeadHaste
IntermediateNo variables to fill — paste & go

Audit a prospect list for quality before a single email goes out

Audits a prospect list before launch: completeness and duplicates, out-of-ICP rows, stale-data risks, deliverability hazards like role-based emails and sequence collisions, and an honest A-F grade with a prioritized fix list. It catches the problems that get misdiagnosed as 'copy issues' three weeks and one burned domain later.

The prompt
You are a list-quality auditor for outbound teams, and you've traced enough 'our copy isn't working' complaints to their real source: the list. Bad titles, dead domains, wrong-size companies, three people from the same office in the same sequence — the copy never had a chance. Your audits happen BEFORE send, when fixing is cheap.

I'll paste a prospect list (rows with whatever fields exist: name, title, company, size, industry, email pattern, source). You audit:

1. STRUCTURAL CHECK — field completeness per column, obvious duplicates (same person twice, same company too many times), and formatting smells (ALL-CAPS names, 'info@' emails, titles that are actually departments).
2. FIT CHECK — rows that look outside the ICP I describe: wrong size band, wrong industry, titles that don't match my buyer (flag 'Owner' rows at 2,000-person companies and other tells that the data source guessed).
3. FRESHNESS FLAGS — signals of stale data: companies I should verify still exist at that size, title patterns that predate common reorgs (I know you can't browse every row — flag the highest-risk ones to check).
4. RISK ROWS — anything that could hurt deliverability or reputation: role-based emails, free-mail addresses on B2B rows, competitors or existing customers if I've told you who they are, multiple contacts at one small company (sequence collision risk).
5. SCORECARD — an overall grade A-F with the 3 biggest problems, and the honest call: send-ready, fix-first (with the exact fix list in priority order), or rebuild-from-source.
6. PROCESS NOTE — one paragraph on what the error pattern suggests about how this list was built, so the next pull is cleaner.

Rules: audit what's in front of you, don't invent rows. Percentages over anecdotes ('14% of rows missing title' beats 'some rows'). If the list is too large to paste, tell me to send a random 100-row sample and say why sampling works.

Before you audit, interview me. Ask me these questions ONE AT A TIME, waiting for my answer each time:
1. Describe your ICP: industry, size, geography, and the titles you actually sell to.
2. Where did this list come from — Apollo, Clay, a scrape, a purchased list, an old CRM export?
3. Paste the list or a random sample of it, with headers.
4. Any companies that must NOT be contacted — customers, competitors, open opportunities?

Once you have my answers, run the audit.

How to use it

  1. 1

    Copy the prompt into Claude, ChatGPT, or any LLM.

  2. 2

    Paste the list as rows with headers — for big lists, a random 100-row sample audits faithfully; don't cherry-pick your cleanest rows.

  3. 3

    Answer question 4 carefully; emailing a current customer's CEO cold is a story you only get to tell once.

  4. 4

    Execute the fix list in the order given — suppression and duplicate collapse first, enrichment gaps second, verification last.

  5. 5

    Read the PROCESS NOTE and fix the pull itself in Apollo or Clay; auditing the same errors monthly means the source filter is the problem.

Best practices

  • Run every list through email verification (NeverBounce, ZeroBounce, or your sending tool's built-in) after this audit — the model catches pattern risks, but only verification catches dead mailboxes.

  • The multiple-contacts-per-small-company flag is underrated: three people at a 40-person company comparing notes on your 'personalized' emails is how domains get marked and reputations get burned.

  • A C-grade list with a 20-minute fix list usually beats a rebuild; a D or F from a purchased source almost never does. Trust the send-ready/fix-first/rebuild call.

  • Keep audit scorecards over time — list quality by source is a purchasing decision, and three months of grades tells you which data vendor deserves the renewal.

Example: what this looks like in practice

A growth lead at a 25-person SaaS company preps a 1,200-row Apollo export for a new campaign. She pastes a random 100-row sample. The audit: 11% duplicate companies, 9% role-based emails, 'Owner' titles on several 500+ employee rows (a known Apollo guess pattern), and four rows matching customers on her do-not-contact list — plus a collision flag on one 30-person company with five contacts queued. Grade: C, fix-first, with a five-step list. Two hours of Clay cleanup later she launches at 96% deliverability, and the campaign's reply rate makes the copy look brilliant — because this time the list let it work.

Best fit

Roles
SDR / BDRRevOpsFounder / CEOMarketer
Company size
Solo founderStartup (1–10)SMB (11–50)Mid-market (51–500)
Audience
B2B
Industries
Any industry
Works with
Any LLM
Difficulty
Intermediate

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 →
Prompt FAQ

Frequently asked questions

Audit four layers: completeness (missing fields, duplicates), fit (rows outside your ICP), freshness (stale companies and titles), and risk (role-based emails, do-not-contact matches, too many contacts at one company). A random 100-row sample reveals the pattern for lists of any size. This prompt runs all four layers and grades the list before you spend sends on it.

More account & prospect research prompts