Prompt

Check accounts for new job posts and draft outreach

Tools: ClaudeLusha

Outputs on this page come from a live run on September 12, 2026. Company names are masked to initials. No contacts were previewed or revealed.

New job post is one of 26 company signals in the Lusha plugin for Claude. It is the earlier, narrower version of surge in hiring: one opening in a specific department, weeks before it becomes a pattern anyone else can see. Run alone, it catches an account before the surge signal has enough postings to fire.

The prompt

Check my target account list for new job posts and tell me which openings are worth an early message versus which have already turned into a hiring surge.

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 (domain, one per line):
[PASTE UP TO 25 DOMAINS]

Target department (or write "any"):
[PASTE]

Steps:
1. Run signals_companies_search on the list with signalTypes ["newJobPost"], startDate 30 days ago. Batch in groups of 25 if the list is longer.
2. For every hit, record department, job title (where returned), location and posted date. Group multiple hits at the same account together rather than listing them as separate rows.
3. Classify each account: SINGLE if exactly one posting fired in the target department; WATCH if two or three postings fired in the same department within the window; SURGE if more than three fired in the same department. Route SURGE accounts to the surge-in-hiring play instead of this one.
4. For SINGLE and WATCH accounts, rank by posting recency: under 7 days first, 7 to 30 days next.
5. Flag any account where the same job title and department repeats across two or more countries on the same posted date; that is very likely one role cross-posted regionally, not several openings, and should count as one signal, not several.
6. For the top 5 SINGLE or WATCH accounts, write one opening line that references the department and role without naming the job board or sounding like a job listing was scraped.

Output: one table with columns Account | Department | Location | Posted | Class | Opening line. Then two lines: how many accounts had zero hits, and credits used.

What you get

The situation. Three accounts from the standard Lusha demo roster, checked for new job posts. Names masked to initials with an industry descriptor: S.K. (data cloud platform), D.D. (cloud monitoring platform), M.G. (database platform). No target department supplied, so all departments were included.

The run. account_usage first, at zero credits. Then one batch call on 3 domains for newJobPost, 30 day window. 2 of 3 fired, 10 signal events, 11 credits.

What came back.

AccountDepartmentLocationPostedClassOpening line
S.K. (data cloud platform)Information Technology, Finance (Revenue Manager), General ManagementUS-CASep 5WATCHNoticed a few openings building on your team; happy to share what similar-stage teams are seeing while those seats are still open.
D.D. (cloud monitoring platform)Information Technology (Senior System Software Engineer, x5)France, SpainSep 7FLAG: likely one role cross-posted, not fiveHeld; same title and department across two countries on the same day usually means one opening posted regionally, not five distinct roles.
M.G. (database platform)no signal

 

Classification based on posting count and department repetition within the account. Credits used: 11. Confirmed live via Lusha connector, September 12, 2026. Company names masked.

What happens next. S.K.’s mixed-department postings stay in this play’s queue as WATCH, worth an early message before the pattern is obvious to anyone else. D.D.’s result is the one worth teaching: five hits, same title, same day, two countries, is very likely a single regional hiring decision mirrored across job boards, not five open seats. Confirm before pitching it as five separate signals. If a genuine department-level surge shows up on a rerun, move that account to the surge in hiring play.

Why use Lusha in Claude

Sales teams notice a hiring surge because it eventually becomes visible: three postings, a LinkedIn note, a competitor’s rep mentioning it. What they miss is the first posting, the single opening that shows a specific need forming weeks before anyone would call it a pattern. This signal reads that moment directly from job posting data, and the prompt does the filtering a rep would not do by hand: grouping postings by account, telling a genuine single opening apart from one role cross-posted across five countries on the same day, and handing off to the surge signal the moment a pattern actually forms. Every signal is sourced under Lusha’s data methodology and compliance framework.

FAQ

What counts as a new job post?

A job listing Lusha detects as newly published at a company, returned with department, location and posted date. Job title and seniority are returned when the listing includes them; many postings come back with no title field, which is normal, not a data gap.

Why not just wait for the surge signal?

Timing. Surge in hiring confirms a pattern that already exists, and by the time it fires, other vendors have often noticed the same account. A single new job post is the first data point in that same pattern, before it is visible to anyone watching for the surge.

What does it mean when the same posting shows up in several countries at once?

Usually one role, cross-posted regionally on the same day, not several distinct openings. The prompt flags this so it is not counted as five separate signals when it is one hiring decision.

When should an account move to the surge-in-hiring play instead?

Once more than three postings fire in the same department within the window. At that point the pattern is established and the surge play, built for that stage, is the better fit.

Does this spend credits?

One credit per event returned. In the live run, three roster accounts returned 10 events for 11 credits. No contact preview or reveal runs in this play.

Ready to run this?

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