ICP scoring is the practice of turning your ideal customer profile into a grade attached to every prospect on your list, so you can sort best-fit accounts to the top and focus outbound on the companies most likely to buy. For outbound specifically, you score on fit (whether you should be selling to this account at all) using firmographics, tech stack, and scraped company facts. Done well, it is the highest-leverage filter in your pipeline: teams that score against their ICP report two to three times higher conversion because reps focus on accounts that can actually close. This guide shows how to score an outbound list in Google Sheets, Hosted Lists, or Claude and ChatGPT via MCP using both rule-based prompts and Sorzio Decision Mode.
What is ICP scoring?
ICP scoring converts your ideal customer profile from a description into a number or grade on each row of your list. Instead of a slide that says "we sell to mid-market logistics firms," you get an explicit label on every prospect: this one is a strong fit, this one is possible, this one is not a fit at all. The score is the operational version of the profile. If you have not defined the profile yet, start with the ideal customer profile entry, because the scoring is only as good as the ICP it encodes.
The point of making it a score rather than a description is that a score sorts. A list of ten thousand prospects is useless until you can rank it, and ICP scoring is what produces the ranking.
Fit versus intent: score them separately
The single most important design decision in ICP scoring is to keep fit and intent as two separate numbers. They answer different questions and they change at different speeds.
- Fit answers: should we be selling to this account at all? It is built from firmographics (industry, company size, revenue, geography), tech stack (the tools they already run), and persona (is your contact a decision-maker). Fit is relatively stable, because a company's industry does not change month to month.
- Intent answers: is this account showing buying behavior right now? It is built from behavioral signals and changes constantly.
For cold outbound, fit is what you score. A prospect can be a perfect ICP match with zero current engagement, and that is not a reason to skip them: it is the definition of an outbound target. You are reaching out precisely because they have not raised their hand yet. So when you score an outbound list, you are scoring fit, and intent is a separate concern you can layer on later if you have the data.
What goes into a fit score?
A fit score is built from the attributes your ICP cares about. The common ones across 2026 scoring models are:
- Firmographics: industry or vertical, employee headcount, revenue band, geography.
- Tech stack: the tools and platforms the company already runs, which can signal both fit and a specific need.
- Growth signals: funding stage, hiring pace, recent expansion, which suggest budget and momentum.
- Persona match: whether the contact you have is a decision-maker or an influencer.
- Disqualifiers: the traits that rule a company out entirely, so a single hard mismatch can drop the score to zero regardless of everything else.
A useful pattern many teams use is a letter grade (A to F) for fit, kept separate from any numeric intent score. The grade is what you sort and filter on for outbound.
Start with rules, graduate to calibrated probabilities
Around three-quarters of B2B companies use AI-assisted scoring in 2026, and the strongest starting point is explicit ICP criteria rather than opaque black-box history. When you encode concrete rules (industry, headcount band, buyer persona, hard disqualifiers), you can inspect why every row passed or failed.
Sorzio gives you two ways to execute those criteria: a standard generative AI prompt, or Decision Mode (typesafe-ai/jev-1.14.0 from TypeSafe AI). Instead of generating chatty text tokens, Decision Mode evaluates up to 12 weighted criteria in one pass, returns calibrated probability scores for each criterion, and routes rows 3 ways (keep, reject, or unsure when confidence sits below your threshold).
How to score an outbound list in a spreadsheet
A spreadsheet or Hosted List is the natural place to score because firmographic data already sits in columns and the verdict lands right beside it. Sorzio runs inside Google Sheets, on Hosted Lists, or via MCP (https://www.sorzio.com/api/mcp) and prepares the list without sending mail, forming the qualification stage of cold email from Google Sheets.
The sequence:
- Enrich thin firmographic inputs first. Pull up to 6 website subpages (
about,products,case_studies,pricing,careers) at $0.006 per URL plus LinkedIn company or personal profile columns via lead enrichment in Google Sheets. - Compile a Decision Profile or write a scoring prompt. In Decision Mode, define up to 12 criteria (for example B2B SaaS vertical, 50+ employees, active hiring) referencing
{{Industry}},{{Employee count}}, and{{About}}, or write a generative rule prompt returningStrong fit,Possible fit, orNot a fit. - Preview on a 3, 10, or 50-row test sample. Inspect the calibrated probabilities or labels and tighten any ambiguous criterion before scaling up.
- Run the full list and route 3 ways. Keep
keeprows for personalization, reviewunsurerows or enrich them further, and gate outrejectrows automatically inside a Flow.
Because jobs run server-side rather than as spreadsheet formulas, there is no six-minute Apps Script ceiling: one pass grades fifty rows or fifty thousand cleanly.
Why score before you personalize and send
Scoring is the filter that comes before you spend real money and real sender reputation on a list. Deals sourced from ICP-fit accounts have been reported to close at around 68% against 22% for non-fit accounts, so the rows you drop at the scoring step are mostly rows that were never going to convert anyway. Filtering them out first means you never spend an AI-personalized opener, or a precious send from a warmed inbox, on a company outside your ICP.
There is a deliverability benefit too. Per-inbox volume limits in 2026 are low, around 15 to 25 cold emails per inbox per day, so your sending capacity is scarce. Scoring keeps the final list small enough to fit that capacity and ensures every send goes to a company worth contacting.
What does ICP scoring cost in a spreadsheet?
In Sorzio, Decision Mode (typesafe-ai/jev-1.14.0) scores up to 12 ICP criteria per pass for a $0.0010 per row ($1.00 per 1,000 rows) base fee plus 1.25x input tokens (~$1.01 per 1,000 rows total), roughly 4x cheaper than generative LLM classification. Standard Generative AI scoring across 300+ models bills 1.65x raw provider tokens plus a $0.0035 per row ($3.50 per 1,000) base fee (~$3.90 per 1,000 rows on budget models like GPT-4o-mini at the unified 1,000 input / 150 output token baseline). You are charged only for rows that return a verdict, with an upfront cost preview before every run. New accounts get up to $20 of welcome credit ($5 at signup plus $15 when you verify a payment card or make your first deposit). On Pro ($39/month, 1 seat) and Scale ($99/month, 3 seats included + $19/month per extra seat), you can bring your own generative AI keys at 0% markup and $0 base fee (Decision Mode settles from your Sorzio balance). See getting started to set up your first run.
Common questions
What is the difference between ICP scoring and lead scoring?
ICP scoring grades fit: how well a company matches your ideal customer profile, based on firmographics and tech stack. Traditional lead scoring usually mixes in intent: behavioral signals like email opens and site visits. For cold outbound you score fit, because your prospects have not engaged yet by definition. Keep fit and intent as separate numbers.
Should I score on fit or intent for outbound?
Fit. An outbound prospect is, by definition, not showing intent yet, which is why you are reaching out cold. A perfect ICP match with zero engagement is the ideal outbound target, not a reason to skip them. Score fit, filter to the fits, then personalize.
Can I score a list without a defined ICP?
Not usefully. The score is just your ICP turned into a grade, so without a clear profile there is nothing to grade against. Define the ideal customer profile first, including the disqualifiers, then encode it in a Decision Profile or scoring prompt.
Does Sorzio send to the scored accounts?
No. Sorzio prepares the list in Google Sheets, Hosted Lists, or via MCP: verify, enrich, score, and personalize. You export the filtered, scored columns and send through your own email service provider or sequencer. Sending and reply handling live in your sending platform.
How accurate is AI scoring against an ICP?
Very reliable when grounded in enriched site or LinkedIn text rather than company names alone. Decision Mode (typesafe-ai/jev-1.14.0) adds calibrated probability scores per criterion and flags borderline rows as unsure instead of forcing a noisy binary guess, making it straightforward to audit a small test sample before grading a large list.