ICP, Targeting & Lead Scoring prompts
Define who you sell to, score who's worth chasing, and turn your ICP into lists, tiers, and messaging that compound.
53 prompts · paste-ready, no variables to fill · free
Most outbound underperforms for one boring reason: the list was wrong before the first email went out. These prompts fix targeting at the source. They turn your closed-won history into a real ideal customer profile, build lead scoring models with actual point values, tier your accounts into A/B/C with different plays per tier, and translate all of it into Apollo, Clay, and Sales Navigator filters you can run today.
They're built for founders defining their first ICP, RevOps leaders formalizing scoring, and sales leaders who suspect their reps are burning hours on accounts that will never close. Every prompt interviews you first, so the output is grounded in your customers and your data, not generic firmographic guesswork. Start with the 10-best-customers prompt, then layer on scoring, tiering, and list-building from there.
Build a discovery question bank tailored to one persona
Generates a 15-question discovery bank built around one persona's actual responsibilities and failure modes, organized by call stage, with listening notes on what strong and weak answers sound like. Beats generic question lists because the interview forces your product, competitor, and deal-death context into every question.
Build a quarterly outbound plan that survives contact with reality
Produces a complete quarterly outbound plan — pipeline math, prioritized segments, 3-5 concrete plays, a launch calendar, and named risks — grounded in your actual win rate and team capacity. The capacity check is the killer feature: it forces the plan to admit when the math doesn't close instead of papering over it with optimism.
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.
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.
Architect a Clay table before you burn the credits
Designs the Clay table before you build it: sources, column order, run conditions, waterfalls, outputs, and a credit estimate. Column ordering and gating are where most teams silently overspend, so the prompt enforces filter-first architecture and makes every paid column defend its run condition — typically cutting credit burn 40-70% versus enrich-everything builds.
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.
Build a Sales Navigator search strategy for your ICP
Designs a layered Sales Navigator system instead of a one-off search: account filters with the miscategorization traps flagged, persona searches with paste-ready boolean strings, a signal layer that surfaces who to message this month, saved-search alerts, and a QA protocol. Built from your real customers, not an aspirational ICP doc.
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.
Build an inbound lead scoring rubric your team will actually use
Replaces inbound chaos with a four-bucket rubric — hot, work, nurture, discard — a rep can apply in 30 seconds. It ranks your conversion sources by true buying intent, defines the minimum enrichment before routing, and hands you implementable if-then routing logic with speed-to-lead targets per bucket.
Choose between two ICPs with a weighted decision matrix
Resolves the two-ICP dilemma with a weighted matrix that's actually honest: criteria and weights locked before scoring, thin evidence marked low-confidence, and a sensitivity check showing which assumption would flip the verdict. The commitment memo forces the part everyone skips — naming what you stop doing for the losing ICP.
Classify an account into one of your defined segments
Assigns every row in your table to exactly one of your named segments, with confidence and a short evidence trail. The exact-string rule means outputs feed lookups, filters, and campaign routing without normalization, and UNCLASSIFIED gives ambiguous rows a safe home instead of contaminating a segment.
Classify cold email replies for AI inbox triage
A production-grade classifier for the 'Categorize Reply' node in an n8n, Make, or custom pipeline. Every inbound reply becomes structured JSON — category, objection type, extracted referral contacts, OOO return dates, and a requires_human flag with explicit escalation rules — so your automation routes interested replies to reps in minutes while objections and OOOs feed the right follow-up branches.
Create a poll-based lead generation post that isn't cringe
Designs a complete poll funnel: a question your ICP genuinely wants peer data on, clean answer options, framing text, the results follow-up post, and the voter-outreach DM. Voters segment themselves by pain, turning a piece of content into a warm, pre-qualified outreach list plus a second post — without the cringe that made polls a punchline.
Create an ICP one-pager for onboarding new reps
Compresses your ICP into the one page a new rep will actually use: a 30-second fit check, ranked green and red flags with reasons, target roles with title variants, buyer vocabulary, and a single litmus question for gauging fit live. Built for week-one moments, not strategy-deck shelf life.
Create persona cards for every buying role you sell to
Produces working persona cards for every role in your deals — built on metrics, pains, language, and objections rather than demographic fluff. Each card ends in a concrete outreach angle and channel, so the personas plug straight into email copy, call prep, and sequence design instead of gathering dust in a strategy doc.
Customize BANT, MEDDIC, or SPICED to your sales motion
Picks the right qualification framework for your specific motion — then rebuilds every element for your context, with the discovery question that surfaces it, strong-versus-weak answer examples, and stage gates. The honesty tests catch wishful-thinking qualification, which is how frameworks actually fail in practice.
Decide which enrichment result wins in a waterfall
Resolves provider disagreements in your enrichment waterfall with explicit arbitration logic: verification over popularity, recency over rank, and a hard ban on blended values. Each field gets one winner (or an honest NONE), a source, and confidence — turning 'which vendor do we trust' from a vibe into a rule.
Decode what a company's open roles reveal about its problems
Reads a company's open roles as evidence: what the hiring pattern says about scaling and rebuilding, which specific problems the postings confess to, what tools they name, what leadership vacancies mean for your deal, and the two best outreach hooks tied to it all. Job postings are the one public document marketing doesn't edit — this extracts everything they leak.
Design an ICP hypothesis testing plan for a new product
Turns 'who should we sell this to?' from a debate into an experiment: explicit ICP hypotheses with reasoned mechanisms, head-to-head outbound test designs sized to your capacity, and pre-committed confirm/kill thresholds that prevent goalpost-moving. The learning log ensures even failed tests compound into targeting knowledge.
Design lead routing logic that never drops a lead
Produces a complete routing spec: an explicit decision tree, tiebreakers, SLA clocks with breach behavior, implementation notes for your CRM, and guards against the three classic silent failures. It turns 'we sort of round-robin' into logic precise enough to build in an afternoon and audit in a quarter.
Design sales territories that reps believe are fair
Produces a complete territory model — carving logic, precise ownership definitions, a fairness analysis, rules of engagement, and rebalancing triggers. The fairness check and dispute rules are what most homegrown territory splits skip, and they're exactly what causes rep churn and CRM chaos six months later.
Design the data schema for your outbound operation
Produces a complete data architecture for outbound: entity model, typed field dictionary with source-of-truth per field, stable cross-tool keys, legal lifecycle transitions, system write permissions, and a check that the schema answers your actual reporting questions. It's the difference between owning your data and renting fragments of it from five tools.
Detect a company's tech stack from its website
Builds an evidence-backed technographic profile per account: up to eight tools with category, the exact place on the site each was spotted, and a uses-versus-integrates flag. Cheaper than technographic data vendors for targeted lists, and the evidence field makes every entry auditable and quotable in copy.
Diagnose why your sequence isn't getting replies
Isolates why your sequence underperforms by walking your funnel numbers through the four possible causes — deliverability, targeting, message, offer — and names the most likely one with reasoning and confidence, ranked fixes, and a cheap test to falsify the diagnosis. It stops you rewriting copy when the real problem is the inbox never showing it.
Estimate your segment size and rough TAM bottom-up
Turns your ICP into a defensible bottom-up market size: specific filter queries to count matching companies, funnel math with stated assumptions and ranges, revenue potential at your pricing, and cross-checks. You learn whether the segment supports your goals — and when outbound alone will saturate it — before spending a quarter finding out.
Expand your ICP into a new vertical with adjacency analysis
Scores candidate verticals on the five dimensions that actually predict expansion success — problem, buying motion, proof, product gap, and competition — instead of headline market size. You get a ranked verdict, the translation work for messaging and case studies, and a 90-day beachhead plan with explicit kill criteria.
Extract hiring signals from a careers page with Claygent
Converts any careers page into a structured hiring-signal record: open role count, departments, up to three notable titles, a GTM-hiring boolean, and a one-sentence signal summary. Clean JSON per row means you can filter, score, and merge hiring triggers into copy without parsing free text.
Facilitate a market segmentation workshop with your team
Turns the model into a structured workshop facilitator that walks your team through market segmentation in five enforced phases: inventory, cutting dimensions, segment drafting, forced ranking, and a decision memo. It pushes past default industry-based slicing and refuses to end with everything ranked 'priority', which is how these sessions usually fail.
Find patterns across 5–10 call transcripts: objections, drop-offs, momentum
Analyzes a batch of transcripts as a dataset instead of one-off reviews: objections recurring across calls, the exact points where prospect energy dies, the moments that reliably create engagement, and gaps between what you pitch and what prospects care about. Ends with three evidence-backed changes your team can start Monday.
Form a pre-call pain hypothesis before your discovery call
Turns raw account research into a ranked, falsifiable pain hypothesis with an opener that positions you as informed rather than interrogating, plus validation questions and an explicit qualify-out signal. It replaces 45 minutes of unfocused pre-call reading with a brief you can act on in the first five minutes of the call.
Generate industry-specific cold email angles
Produces a complete vertical angle brief: five industry-specific ways into a cold email written in the buyer's own vocabulary, language do's and don'ts, what proof that industry finds credible, and a ranked recommendation. It's positioning translation for verticals — not your horizontal pitch with an industry label stapled on.
Infer a prospect's tech stack and what it says about their pain
Turns raw tech-stack evidence — BuiltWith exports, tool mentions in job posts, integration pages — into a confidence-labeled read of what a prospect runs, what they almost certainly also run, and what it reveals about budget, maturity, and gaps your product fills. It converts a list of logos into a fit assessment and a credible talk track.
Localize a winning sequence for a new vertical
Ports a proven sequence into a new vertical without the find-and-replace trap: it extracts the structural mechanics that made your winner work, maps how pain, vocabulary, and proof shift in the new industry, rewrites every touch on the same skeleton, and flags the proof gaps and assumptions to validate before you scale sends.
Map your buying committee and their conflicting priorities
Maps the full buying committee for your deals — including the stakeholders you never meet — and, critically, where their priorities collide. You get veto powers with early-warning signs, reconciliation arguments for each conflict, and a coverage plan that tells you which stakeholders need direct outreach versus champion enablement.
Mine Glassdoor reviews for internal pain signals at a target account
Extracts operational intelligence from employee reviews of a target account — broken tooling, manual process complaints, understaffing, leadership churn — with an explicit bias check on the sample, a department-level read, and the selling implications. It also draws the hard line: this intel shapes strategy and discovery questions, and never appears in outreach.
Normalize messy job titles into seniority and function
Turns the chaos of raw titles — emojis, slashes, vanity titles, abbreviations — into two controlled-vocabulary fields plus a decision-maker flag. It's the unglamorous prompt that makes everything downstream work: routing, scoring, and personalization all break when 'Chief Revenue Wizard 🧙' sits unparsed in your title column.
Plan your market entry into a new vertical
Turns 'we should go after healthcare' into a beachhead plan: a specific sub-segment, the message translated into the vertical's own vocabulary, a proof strategy for having zero logos, 90-day milestones, and pre-agreed kill criteria. It forces the translation and proof work most vertical expansions skip on the way to failing.
Refine your ICP with win/loss data
Puts your ICP on trial against actual deal outcomes: every criterion gets a confirmed/challenged/untested verdict, hidden win and loss pockets get surfaced, and loss reasons get sorted into targeting versus execution problems. You leave with an evidence-backed revised ICP and one clean hypothesis to test next quarter.
Research a territory and select the accounts actually worth working
Turns a raw territory assignment into a worked plan: the shape of the actual market in your patch, where timing pressure clusters right now, a committed shortlist with explicit selection logic, a deliberate ignore list, coverage math matched to your real capacity, and a first-two-weeks sequence. It's the difference between inheriting a list and owning a territory.
Run a jobs-to-be-done analysis for each persona
Goes a layer deeper than persona cards: for each buying role, it uncovers the functional, emotional, and social jobs they're hiring your product for, plus the struggling moments that make buying urgent. Each analysis converts directly into a discovery question and a cold email opener, so the theory ships as sales material.
Run a yes/no ICP match classifier on any account
Puts a strict tri-state gate (YES / NO / UNKNOWN) at the front of your pipeline: accounts fully matching your written ICP proceed, confirmed misfits exit with the failed criterion named, and thin-data rows queue for enrichment instead of being silently misjudged. The named-criteria output makes every rejection auditable.
Score a scraped snippet's relevance before it reaches copy
Adds a QA gate between scraping and writing: every snippet gets a 1–5 usability score, the single best fact extracted, and a reason. Gating your first-line prompt on score 4+ is the difference between personalization built on real research and confident emails built on cookie banners.
Score a single account against your ICP before it enters a sequence
Scores one account against your actual ICP criteria with evidence per line, an honest verdict, and — critically — explicit unknowns and anti-signals. It stops the quiet list-decay where 'close enough' accounts leak into sequences, and it converts vague ICP language into a repeatable 0-2 scorecard you can apply to every borderline account.
Spot the early-warning signals that a customer will churn
Autopsies your churned accounts to find the pre-sale traits that predicted failure — your anti-ICP signals — and builds a ranked early-warning board of post-sale signals with intervention thresholds. The save-ability verdict splits churn into rescuable accounts versus accounts that should never have been sold, which demand opposite fixes.
Tier a raw account list so research effort follows revenue potential
Turns a flat account list into a three-tier system with explicit entry criteria derived from your closed-won patterns, a justification per account, flagged edge cases, the data gaps distorting the tiering, and a concrete effort map — touches and research minutes per tier. It's the allocation decision most teams skip straight past on their way to burning a quarter evenly across 200 accounts.
Tier your accounts into A/B/C with plays for each tier
Builds a complete account tiering system: definitions, effort allocation, channel mix, and touch counts per tier, plus promotion/demotion triggers and the capacity math to prove your team can actually run it. The output is a one-page operating system for outbound effort, not a labeling exercise.
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.
Turn a trigger event into a cold call script within 48 hours
Converts any trigger event into a call built on the trigger's implication rather than the news itself: a ranked implication map, a sub-50-word script with honest branches, the callable window before the angle stales, and a disqualifier check. It separates your call from the fifteen congratulations calls the prospect got this week.
Turn your ICP into messaging pillars for every campaign
Converts your ICP into 3-4 messaging pillars — core arguments mapped to specific ICP pains, each with proof, an emotional undertone, and ready translations for email, phone, and LinkedIn. The pillar test kills generic claims any vendor could make, and the usage map tells campaigns which argument leads where.
Turn your LinkedIn profile viewers into conversations
Converts the 'who viewed your profile' list from vanity metric to warm pipeline: a triage filter for which viewers deserve action, DM and connection-note templates that never mention the view, traceback logic for guessing what brought them, and a 10-minute twice-weekly routine. The view tells you who; it must never be your stated why.
Write a cold email when you have no personalization signal
Solves the no-signal prospect problem with segment-level precision instead of fake personalization. You get an under-80-word email whose opening problem statement is so specific to the role and industry that it reads as researched — the honest, scalable alternative to 'I was browsing your website'.
Write a disqualification checklist that saves your reps hours
Arms your team with an objective disqualification system: instant-kill conditions, a three-strike warning framework, qualify-out questions that surface bad fits early, and graceful exit templates. The math section quantifies the rep-hours recovered, which is what turns disqualification from a guilt trip into an obvious win.
Frequently asked questions
Yes, if you feed it real customer data. AI is excellent at pattern-finding: give it your 10 best customers with deal size, sales cycle, and use case, and it will surface commonalities you'd miss staring at a spreadsheet. What it can't do is invent your ICP from nothing, which is why every prompt here interviews you for real inputs before producing anything.
More prompt categories
Want this running on autopilot instead?
We wire prompts like these into a full outbound system — data, personalization, sending, and replies orchestrated end to end. You own the infrastructure. We guarantee the results.
Apply for a Pilot Spot →