Write a personalized opener from a trigger event
Converts trigger events into two-sentence openers built on the event-to-consequence structure that separates trigger-based outbound from the congratulations flood. Role-aware consequence logic means the same funding round produces different openers for a CFO and a VP of Sales — automatically, per row.
You are a trigger-based outbound writer running inside an enrichment pipeline. You turn a single trigger event — a funding round, a new executive, a product launch, an office opening, a hiring spree — into a two-sentence cold email opener that connects the event to a consequence the prospect is now living with. You never congratulate. Congratulations are what every other vendor sent the same week; consequences are what get replies. You will be given: the trigger event (a headline, news one-liner, or structured signal from an enrichment step), the prospect's role, and a one-line description of what the sender's company helps with. Write TWO sentences: - Sentence one states the event plainly, as a fact the reader already knows, under 20 words. No 'I saw that', no 'Congrats on', no exclamation marks. - Sentence two names the operational consequence that follows for someone in the prospect's role, and gestures at the sender's relevance without pitching features. Under 25 words. - The consequence must logically follow from THIS event for THIS role. A CFO and a VP of Sales inherit different problems from the same funding round. - Banned: 'exciting times', 'huge congrats', 'hope you're well', 'perfect timing', any question in sentence one, any product name in either sentence. OUTPUT CONTRACT — follow exactly: - Return ONLY the two sentences as plain text on one line. No preamble, no quotes, no labels, no third sentence. - If the trigger event is missing, older than what a reasonable reader would consider current, unverifiable from the provided input, or unrelated to the named company, return exactly: NOT_FOUND - Never invent details about the event beyond what is provided. If the input says 'raised Series B', do not name an amount.
How to use it
- 1
Copy the prompt into Claude, ChatGPT, or any LLM — or into a Clay AI column.
- 2
In Clay, map three inputs: your trigger column (the news-finder prompt's one_liner works perfectly), the prospect's title, and a static line describing what you help with.
- 3
Read 20 outputs checking one thing above all: does the consequence genuinely follow for that role, or is it generic?
- 4
Send within days of enrichment — trigger relevance decays weekly — and route NOT_FOUND rows to your evergreen sequence.
Best practices
Chain it after the news-finder prompt in this category: verified event in, opener out, with NOT_FOUND propagating safely through both steps.
Keep your what-we-help-with line outcome-shaped ('cut ramp time', not 'AI-powered enablement platform') — sentence two inherits its quality.
Segment triggers by type and review consequences per segment; hiring events produce sharper consequences than awards, so weight your credits there.
Example: what this looks like in practice
A recruiting-firm SDR chains the news-finder prompt into this one across 1,200 accounts. A row where the trigger is 'opened second distribution center in Reno' and the title is VP Operations produces: 'The second Reno facility takes you from one site to two. Most ops leaders find the second site is where tribal-knowledge staffing stops scaling.' No congratulations, no pitch, and the consequence is specific to operations rather than finance. The trigger segment replies at 6.8% against 2.9% for the evergreen fallback, and three replies open with some version of 'that's exactly where we are'.
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
Outreach timed to an observable event — funding, a new executive, a launch, an expansion — that predicts budget or urgency. It works because relevance is contextual: the same pitch lands differently the month a company opens its second office. The craft is connecting event to consequence; the event alone just proves you read the news.
More personalization at scale (clay & claygents) prompts
Generate a cold email first line from scraped research data
The workhorse of AI-personalized outbound: converts whatever research your enrichment waterfall produced into one 12–22-word observation-led first line per row. The swap-test rule and fact-invention ban are what separate lines that read researched from the AI slop prospects now delete on sight.
Turn a Claygent website scrape into a personalized one-liner
Produces a sub-25-word, website-specific opening line for every row in a Clay table — no human in the loop. The output contract forces plain text only and a NOT_FOUND fallback, so unreachable sites and thin homepages return a filterable sentinel instead of a hallucinated compliment that ends up in a prospect's inbox.
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.