Personalize your call script from raw account data in seconds
Converts each pasted account record into four things: an opener insert, a problem-statement insert, the right proof story to cite, and a skip flag for bad-fit accounts, each under 25 words. It gives you Clay-grade personalization at call speed without rewriting your script per prospect, which is what keeps daily dial volume intact.
You are a call-prep specialist who turns raw account data into personalized script inserts for outbound reps. You work like the best enrichment-to-copy pipelines: take structured data (a Clay row, a CRM export, an Apollo record) and produce not a whole new script, but the three or four personalized lines that slot into an existing script's sockets. Rewriting the whole script per prospect kills volume; personalizing the right three lines keeps volume and beats generic calls.
I will give you my base script and then paste account data one prospect at a time. For each prospect, produce:
- OPENER INSERT: one sentence for my opener socket, built on the single most relevant data point. It must pass the 'so what' test: the data point ties to a business implication, not 'congrats on the funding'.
- PROBLEM INSERT: one sentence adapting my problem statement to their likely situation, with the inference labeled ('9 open sales roles suggests ramp pain').
- PROOF INSERT: which of my customer stories or metrics to use for this prospect and why, chosen for similarity of industry, size, or situation.
- SKIP FLAG: if the data shows this prospect is a bad fit or the timing is wrong (just signed a competitor, layoffs in the relevant team), say 'consider skipping' and why. Do not manufacture relevance for a bad-fit account.
Rules: never fabricate data not present in what I paste, never use a data point without tying it to an implication, and keep each insert under 25 words.
Before the first prospect, interview me. Ask me these questions ONE AT A TIME, waiting for my answer each time:
1. Paste your base call script and mark where the opener, problem, and proof sockets are, roughly.
2. What do you sell, and what outcomes do your 2 or 3 best customer stories prove?
3. What data fields do your account records usually contain?
4. Paste the first prospect's data.
After the first, I paste new data and you return the four-part insert block, no repeats.How to use it
- 1
Copy the prompt into Claude, ChatGPT, or any LLM.
- 2
Paste your base script with sockets marked, plus your customer stories, then feed prospects one at a time.
- 3
Batch-generate inserts for tomorrow's call list at the end of each day.
- 4
Respect the skip flags; deleting a bad dial is personalization too.
- 5
Advanced: run this prompt inside a Clay AI column so inserts land in the same row as the enrichment data.
Best practices
The inserts are only as good as the fields you feed; headcount growth, hiring data, tech stack, and recent news out-produce firmographics alone.
Watch for the labeled inferences and downgrade any that feel like a stretch before dialing.
Keep your proof stories updated in the chat; stale case studies produce stale proof inserts.
Example: what this looks like in practice
A rep at a sales compensation platform preps 25 dials from a Clay table with headcount, funding stage, open roles, and comp-tool stack. For one prospect the model returns: opener insert 'You've posted 11 sales roles since January; someone is about to do a lot of comp plans in spreadsheets' (under 25 words), problem insert labeling the inference, proof insert pointing to their 200-rep fintech story rather than the SMB one, and no skip flag. Two rows later it flags 'consider skipping: they announced a CaptivateIQ rollout last month.' She dials 23 instead of 25, has personalized lines for each, and finishes prep in 20 minutes instead of 90.
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
Do not rewrite the script per prospect; personalize three sockets in a fixed script: the opener line, the problem statement, and which proof story you cite. That is what this prompt generates from each account record, in under 25 words per insert. Reps keep their dial volume, and every call still opens with something specific to the prospect.
More cold calling scripts & openers prompts
Build a full cold call script: opener, problem, value, CTA
Builds a complete, branching cold call script with labeled sections, stage notes for delivery, and pre-written pivots for the most likely prospect responses. Total talk time stays under 60 seconds. You get a call structure a new SDR can run on day one, instead of a monologue that collapses at the first interruption.
Cold call role-play: the AI plays a skeptical VP and scores your performance
Turns the model into a realistic, interruption-prone VP buyer who objects, tests, and warms or cools based on how you actually perform, then scores you across five dimensions with the exact moment you lost them and a drill to fix it. It is unlimited call practice with instant, specific feedback and no burned leads.
Adapt your cold call script to a new industry without losing what works
Rewrites your proven script for a new vertical while preserving its structure, marking every change with the reason, and delivering an industry brief, shifted objections, and the outsider red flags in your original. You enter a new market sounding like someone who has sold there before, without rebuilding your script from zero.