Prompt

Reopen closed lost accounts after a strategic shift

Tools: ClaudeLusha

Outputs on this page come from a live run on September 10, 2026. Company names are masked to initials. No contacts were previewed or revealed.

Corporate Strategy is one of seven news signal types in the Lusha plugin for Claude. It is the closed lost signal because it is the one that describes budgets and ownership being reshuffled, which is the only thing that turns a no into a new conversation.

The prompt

Check my closed lost and stalled accounts for a strategic shift that resets the conversation, and tell me which ones to reopen.

Before anything else, run account_usage and tell me my remaining credits. Do not run any signal call if fewer than 50 credits remain; stop and tell me.

Here is my list of closed lost or stalled accounts (domain, one per line):
[PASTE UP TO 25 DOMAINS]

For each, if you know it, the month we lost or stalled and the title of the person who said no:
[PASTE OR WRITE "unknown"]

Steps:
1. Run signals_companies_search on the list with signalTypes ["corporateStrategyNews"], filters.include.newsEventTypes ["M&A", "New Location", "Facilities Expansion", "Facility Closure"], startDate 180 days ago, maxResultsPerSignal 2. Strategic events take months to change who owns what, so the window is longer than for other signals. Batch in groups of 25 if the list is longer.
2. For every event, pull the event type, the summary, the effective date, the article date and the source. Drop any event whose effective date is more than 180 days before today, even if the article is recent; news rehashes old deals constantly. If there is no effective date and the summary says "planning to", "agreed to" or "to acquire", mark it PENDING and keep it.
3. Classify the company's role: ACQUIRER (it bought something), ACQUIRED (it was bought), RESTRUCTURING (closed or consolidated offices), EXPANSION (opened a new location). If an M&A event lists the company as the buyer, it is ACQUIRER; being acquired shows up on the target's own record, so it only appears if the target is on my list.
4. Rank for reopening: RESTRUCTURING first (the people who said no may no longer own the decision), then ACQUIRED (the stack is about to be reviewed), then ACQUIRER (two teams and two toolsets to reconcile), then EXPANSION (route to the regional play rather than reopening here).
5. For every ranked account, tell me to verify whether the original contact is still in seat before reopening. Do not draft to the old contact by default.
6. For the top 5, write one opening line for whoever now owns the decision that references the direction of the change without naming the acquired company, the closed office, or any figure, and without the words layoffs, restructuring or cuts.

Output: one table with columns Account | Event | Role | Effective date | Status | Lost or stalled when | Opening line. Then two lines: what the ranking is based on, and credits used. Do not preview or reveal any contacts in this run.

What you'll get back

The situation. A list of 25 enterprise software companies treated as closed lost, 2,000 to 70,000 employees. Loss dates and original contacts not supplied.

The run. account_usage first, at zero credits. Then one batch call on 25 domains for corporateStrategyNews filtered to M&A, New Location, Facilities Expansion and Facility Closure, 90 day window, two events per account. 8 of 25 fired, 14 events, 14 credits. After dropping events with effective dates outside 180 days: 9 events at 6 companies.

What came back.

AccountEventRoleEffective dateStatusSource typeOpening line
I.N. (financial software, ~18,000 emp)Closed two offices as part of consolidating teams into fewer hubsRESTRUCTURINGMay 20 (113 days)Confirmed, two sourcesLaw firm press releases citing a wire reportConsolidating teams into fewer hubs usually changes who owns which tools. If the people we spoke with last year have moved, happy to pick the conversation up with whoever holds it now.
A.D. (creative software, ~30,000 emp)Acquired a market intelligence startupACQUIRERSep 2 (8 days)ConfirmedFinancial news wireBringing a new team in mid quarter means two sets of tools and two sets of customer data to reconcile. That is the moment a shared data layer is cheapest to put in.
A.D. (creative software)Agreed to acquire an AI imaging company, closing second half of 2026ACQUIRERnonePENDING, regulatory approvalTrade pressSame account; the pending deal strengthens the first line, no separate outreach.
O.K. (identity, ~6,000 emp)Agreed to acquire an AI security startupACQUIRERJul 30 (42 days)Confirmed, one source says priceTrade pressAn acquisition mid year usually reshapes the buying group we spoke to. Worth ten minutes to see who owns the data stack now.
D.D. (observability, ~6,000 emp)Acquired an AI research companyACQUIRERJun 30 (72 days)ConfirmedCompany press releaseWhen an acquired team lands, someone has to decide which systems it runs on. If that decision is still open, we should be in it.
S.F. (data cloud, ~7,000 emp)Opened a new French headquartersEXPANSIONJul 2 (70 days)ConfirmedFinancial blogRoute to the regional play; a new office is a territory question, not a reopening.
D.D. (observability)Paris office expansionEXPANSIONnoneDropped: a company history article describing an office opened years agoBlog
Z.I., B.X., O.K., C.S.Acquisitions and a closure from 2012, 2014, 2021 and 20232012 to 2023Dropped: mentioned in a pricing guide, a Forbes profile, an office directory and an acquisitions roundupVarious
17 accountsno eventNo strategic shift in the window. Do not reopen on this signal.

 

Ranking based on role (restructuring, then acquired, then acquirer, then expansion) and confirmation inside 180 days. Credits used: 14. Confirmed live via Lusha connector, September 10, 2026. Company names masked to initials.

What happens next. Before any reopening, run the original contact through the verify a contact’s title play. If they are gone or moved, the buying group play finds who holds the decision now. Reopen as a new opportunity, not by reviving the old record; the old one carries the old no. The EXPANSION rows belong to the regional hiring play, not here.

Why use Lusha in Claude

Why it works

Closed lost lists get worked on a calendar: six months later, someone sends a check in. That email lands on the same person with the same plan and gets the same answer. This play replaces the calendar with the event that actually changes the answer. An acquisition means two teams choosing one set of tools. A consolidation means the people who owned the decision may have moved. Inside Claude, the plugin returns those events for the whole lost list in one call, the prompt strips out the history the news keeps recycling, and what remains is a short list of accounts where the no is no longer attached to anyone. The run costs signal credits only, and the prompt insists on a title check before anyone reaches out. Every signal is sourced under Lusha’s data methodology and compliance framework.

FAQ

What counts as a corporate strategy event?

A published article describing an acquisition, a new location, a facilities expansion or a facility closure involving the company, with the event type, a summary, an effective date where the article states one, and the source. Partnerships and product events sit under Commercial Activity, a separate signal.

Why 180 days when other plays use 90?

Because the effect of a strategic event on who owns a decision lasts longer than the news cycle. Integrations run for quarters. An office consolidation announced in spring is still moving people in autumn. Shorten it if your sales cycle is short; lengthen it for enterprise.

Should I reopen the old opportunity or create a new one?

New. The old record carries the reasons for the no, and the reason for reopening is that those reasons may no longer apply. A new opportunity linked to the event keeps attribution clean and stops the rep inheriting a dead thread.

Why not contact the person who said no?

Because after a restructuring or an acquisition they may not own the decision, and if they still do, the no stands. The prompt requires a title check first and drafts for whoever holds the decision now. If it turns out to be the same person, you have at least confirmed it before writing.

Does this spend credits?

One credit per event returned, including the old deals the prompt later drops. In the live run, 25 domains cost 14 credits. account_usage runs first and the prompt stops under 50. No contact preview or reveal runs in this play.

How often should I run it?

Monthly on the closed lost list. Strategic events are infrequent and the 180 day window carries them, weekly is wasted credits.

Ready to run this?

One data connection. Works in Claude, ChatGPT, your CRM, or any agent you build.