Translate your ICP into Apollo, Clay, and Sales Nav filters
Closes the gap between your ICP document and an actual list: exact Apollo and Sales Navigator filter builds with title variants and exclusions, plus a Clay enrichment layer for the criteria native filters can't capture. The spot-check protocol catches list contamination before it burns your reply rates and domain reputation.
You are a list-building specialist who has translated ICPs into targeting filters across Apollo, Clay, and LinkedIn Sales Navigator for hundreds of campaigns. You know the dirty secret of outbound data: the gap between an ICP document and an actual filterable list is where most targeting quality dies. 'Growing mid-market logistics companies' is a strategy phrase; a list needs industry codes, headcount bands, title strings, and enrichment logic. You also know each tool's quirks — Apollo's industry taxonomy is loose, Sales Nav headcounts lag reality, and the best signals often need a Clay enrichment rather than a native filter. Translate my ICP into executable targeting. Produce: 1. APOLLO BUILD: exact filter selections — industries, employee ranges, technologies, keywords, title strings for my personas (including the title variants people actually hold), plus exclusions from my negative criteria. 2. SALES NAV BUILD: the equivalent using Sales Nav's filter set, noting where its taxonomy differs from Apollo and what to watch for. 3. CLAY LAYER: which ICP criteria can't be captured by native filters (tech stack details, hiring signals, specific page content) and the enrichment or Claygent prompt to score them. 4. QUALITY CONTROL: a 10-account spot-check protocol before any list goes to sequencing, with the 3 most likely contamination sources for my specific filters. 5. SIZE EXPECTATIONS: rough count each build should return, and what it means if reality is wildly off. Before you write anything, interview me. Ask me these questions ONE AT A TIME, waiting for my answer each time: 1. Paste your ICP — or describe your target companies as precisely as you can. 2. Which roles are you targeting inside those companies? 3. What should exclude a company from your lists (bad-fit criteria, current customers, competitors)? 4. Which of these tools do you actually have: Apollo, Clay, Sales Navigator, others? 5. Are there signals that make an account hot right now (hiring, funding, tech changes)? Once you have my answers, produce the builds for the tools I have. Where my ICP contains an unfilterable criterion, say so explicitly and give me the Clay workaround.
How to use it
- 1
Copy the prompt into Claude, ChatGPT, or any LLM.
- 2
Paste your written ICP for question 1 — the tighter the input, the more precise the filter build.
- 3
Build the filters in your tool as the model specifies, then compare returned counts against its size expectations.
- 4
Run the 10-account spot check religiously; ten minutes of eyeballing saves a thousand wasted sends.
- 5
Paste any wildly-off counts back into the chat and ask the model to diagnose which filter is misfiring.
Best practices
Never trust a single industry filter — Apollo's taxonomy is self-reported and loose, so pair industry with keywords or a Clay check on the company's own description.
Include every title variant the model suggests; targeting only 'VP Sales' misses the Heads of Revenue and Sales Directors holding the same job.
Apply exclusions with the same care as inclusions — current customers and competitors in a cold list are embarrassing at best.
Rebuild lists monthly rather than topping them up forever; filter drift and data staleness compound quietly.
Example: what this looks like in practice
An SDR team lead at an e-commerce logistics company has a solid ICP on paper: DTC brands doing $5-50M with in-house fulfillment struggles. She answers the interview listing Apollo and Clay as her tools. The model returns an Apollo build combining retail industry codes with Shopify technology filters and headcount 20-200, twelve title variants across operations and fulfillment roles, and exclusions for 3PLs and agencies. The Clay layer scores accounts by whether their careers page lists warehouse roles — an unfilterable signal of in-house fulfillment. The spot check flags that a quarter of the first pull are actually agencies, traced to one loose keyword; she drops it, rebuilds, and the cleaned list of 1,900 accounts books meetings at twice her previous rate.
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
Decompose each ICP criterion into Apollo's actual filter fields: industries (use several related codes, not one), employee ranges, technology filters, keywords, and title strings covering every variant of your target roles. Add exclusions for customers, competitors, and negative-ICP traits. This prompt produces the full build and flags which of your criteria Apollo can't filter natively.
More icp, targeting & lead scoring prompts
Define your ICP from your 10 best customers
Reverse-engineers a tight, one-page ICP from your actual closed-won history instead of aspirational guesswork. It forces narrow ranges, separates signal from coincidence, and flags when your customer base actually contains two different ICPs — the insight most founders miss until their outbound numbers tell them the hard way.
Design a lead scoring model with firmographic and behavioral points
Produces a complete, implementable lead scoring model: firmographic fit points, behavioral intent points with decay and negative scoring, threshold bands tied to actions, and a monthly validation loop. It caps complexity at 12 criteria and adapts to what you can actually track, so the model ships instead of dying in a spreadsheet.
Build a negative ICP: who to actively avoid and why
Turns your worst-customer war stories into a formal negative ICP: hard disqualifiers, stacking yellow flags, and the false-positive profile that keeps fooling your team. Includes list-building exclusion filters and a polite decline template, so avoiding bad fits becomes operational instead of a lesson everyone relearns quarterly.