← LushaCONTENT HISTORY

Update to Lusha

Snapshot Nov 9, 2026 · 00:08 UTC · version 3.1.0

Collection source: downloaded plugin package.

WHAT CHANGED

First saved snapshot

No earlier snapshot is available to establish a change.

Save Lusha and check future changes in Following.

Up to 3 plugins free · no card required.

Compare saved observations

Download comparison JSON
Full technical diff · 0 changed fields
Full snapshot data
{
  "description": "Turn the companies visiting the user's own website into a call list: rank recent visitors by engagement, keep the hot ones, check them against the user's ICP, find the decision makers and reveal their phones. Use when the user says \"who visited our website\", \"which companies are on our site\", \"follow up on site visitors\", \"show me hot website visitors\", \"who's been looking at our product page\", or \"turn website traffic into leads\". Not for companies showing a buying signal elsewhere (funding, hiring): use signal-prospect for that.\n",
  "included_files": [],
  "name": "website-visitor-followup",
  "skill_md_contents": "---\nname: website-visitor-followup\ndescription: \"Turn the companies visiting the user's own website into a call list: rank recent visitors by engagement, keep the hot ones, check them against the user's ICP, find the decision makers and reveal their phones. Use when the user says \\\"who visited our website\\\", \\\"which companies are on our site\\\", \\\"follow up on site visitors\\\", \\\"show me hot website visitors\\\", \\\"who's been looking at our product page\\\", or \\\"turn website traffic into leads\\\". Not for companies showing a buying signal elsewhere (funding, hiring): use signal-prospect for that.\\n\"\n---\n\n# Website Visitor Follow-up\n\nA company that keeps coming back to the user's site, and reads the high-intent pages, is the warmest account they have. This skill finds those companies, keeps the ones that fit, and ends with the people to call.\n\n## Lusha call rules\n\n1. Pass `conversation_id` from the most recent Lusha response on every call. Start every `reason_for_invocation` with `website-visitor-followup: `.\n2. Run the calls that use no quota first and branch on what they return. No visit data means a fallback, never an error.\n3. Before every quota-using call, state how much of the quota already included in the user's existing Lusha account it will use, and wait for a yes. This workflow cannot change the user's account entitlement. Get the quota rate for every quota-using call from `account_usage` (uses no quota; call it once per session). Each `pricing` entry (the per-action quota rates) names the tools it applies to. If a tool has no entry, say its rate isn't listed for this plan, and report the quota the call actually used from the usage metadata afterwards. Reveal only the people the user picks. On a 402, if the existing entitlement is insufficient, say so and offer to continue with previews or a smaller batch. Never suggest changing the user's account entitlement.\n4. Keep the chain short: every call counts toward the user's AI usage.\n5. If a response carries `next_step_hints` and the user picks one of its offers, pass its `ref` as `next_step_ref`.\n\n## Step 1 — Rank the visitors (uses no quota)\n\nCall `website_visits_search` with:\n- `filters: { scoreBands: [\"hot\"] }`\n- `sort: { by: \"score\", order: \"desc\" }`\n- `pagination: { size: 25 }`\n\nThe default window is the last 30 days. Pass `startDate` / `endDate` if the user named a period; keep the range to 90 days or less, because a longer one is refused. Pass `domains` only when the user names one of their tracked sites.\n\n- **No hot visitors, but the call worked:** say so, and run it once more with `scoreBands: [\"warm\"]`.\n- **No warm visitors either:** run it once more with no `scoreBands` filter. That returns every band, cold included. Cold visitors are still visitors, so show them, labelled as cold. Offer a longer window, up to 90 days, if that call is empty too.\n- **An error:** read it before deciding anything. An error is not \"no tracking\".\n  - **429 (rate limit):** wait, and retry once.\n  - **400 naming the date range, or a 500 on a long window:** retry once with 30 days.\n  - **Any other error, after one retry:** say the visit data couldn't be read right now, and offer the fallback. Don't say tracking isn't set up.\n- **No visitors in any band, even over 90 days:** go to the fallback below.\n\nShow the ranking:\n\n| # | Company | Domain | Visit score | Band | Days visited | High-intent pages | Last visit |\n|---|---------|--------|------------|------|--------------|-------------------|------------|\n\nList up to three `highIntentPages` labels per company (e.g. \"Product ×4, Demo ×1\"). They tell the user what the visitor wants, and make a good opener.\n\n## Step 2 — Keep the ones that fit (optional, uses quota)\n\nCall `icp_profiles_get` with `status: \"active\"` (uses no quota).\n- **Active profiles exist:** offer to drop visitors outside the ICP: *\"Check these N companies against your ICP?\"* Estimate its existing-account quota usage from the `icp_fit_score_companies` rate in `account_usage`. If there is no rate listed, say so. On yes, call `icp_fit_score_companies` with their ids and up to 3 `targetProfileIds`. Mark fit ≥ 0.6 as a fit, and keep the rest visible but lower.\n- **No profile:** skip this step and mention `set-up-my-icp` at the end.\n\nDo not add a signal score. The visit is already the buying signal.\n\nAsk which companies to work, or default to the top 5 by visit score.\n\n## Step 3 — Find the decision makers\n\n**The user named a role:** call `prospecting_contact_search` with `companyIds`, `jobTitles` and `page_size: 10`.\n\n**No role named:** it uses existing-account quota per contact returned, for at most 3 contacts per company; state that quota usage first. Then call `decision_makers_buying_group_search` with:\n- `companies`: the picked visitors by `id` or `domain`, up to 25\n- `personas: [\"decision_maker\"]`\n- `contactsLimit: 3`\n- `pagination: { size: 100 }`, so all 75 possible contacts fit on one page\n\nA company that comes back empty or `NOT_FOUND` uses no quota.\n- **The call errors:** fall back to contact search for every picked company.\n- **Some companies come back with no contacts:** fall back for those companies only, and say which ones. Never drop a company silently.\n\nThe fallback is `prospecting_contact_search` with `companyIds` set to those companies and senior `seniority` ids from `prospecting_contact_filters`.\n\n## Step 4 — Enrich the people the user picks\n\nSum `canReveal[].credits` for the fields being revealed, state the total as existing-account quota, and wait for a yes. Then call `prospecting_contact_enrich` with those ids, up to 50 per call.\n\n**What a reveal returns.**\n- **Third-party sources.** `canReveal[].credits` is the Lusha quota rate. If the account has the data waterfall on, a Lusha miss can be filled by a third-party source at its own quota rate (`account_usage` lists them, e.g. a phone at 8 of the existing-account quota). Say so when stating the quota usage. Offer `waterfallEnabled: false` for a Lusha-only reveal.\n- **`COMPLIANCE_RESTRICTED`** on a row means that contact can't be shown, for compliance reasons, and no quota was used. Say so and offer the next person.\n- **`doNotCall: true`** marks a phone that is masked and not to be called. Show it as \"Do not call\", never as a number to dial.\n- **A different company.** If the enrich result shows a different company from the search, the person has changed jobs. Show the new company and say so.\n\n**Background reveals.** A `job` block in the response means some reveals are still running.\n1. Show what has landed and how many are outstanding (`job.outstandingCount`).\n2. Check `contacts_enrich_job_status` after `pollAgainInSeconds` until `isTerminal` is true.\n3. Read the final contacts with `contacts_enrich_job_results` (`contactLimit: 25`, following `contactPage.nextContactOffset` while `hasMore`).\n4. Never enrich the same ids again: that uses quota twice. The job tools use no quota.\n\n## Step 5 — Present the call list\n\n| # | Name | Title | Company | Direct Phone | Mobile | Email | What they looked at | Last visit |\n|---|------|-------|---------|-------------|--------|-------|---------------------|-----------|\n\n- Phones come first. Mark a missing phone with `—`.\n- \"What they looked at\" holds the company's high-intent pages. Never claim that a specific person visited: visits are tracked per company.\n\n### Summary\n- Visitors: X, with the band used (hot, warm or all bands) (worked: N)\n- Decision makers found: Y; with a phone: Z\n- Existing-account quota used: sum of the usage metadata\n\n## Fallback — no visit data\n\nUse this when every band comes back empty over 90 days, or when an error persists after the retries in Step 1.\n- **Empty over 90 days:** website tracking is probably not set up for this account. Tell the user: *\"I can't see website visits for your account. Visitor tracking may not be set up yet; it's configured in the Lusha platform.\"*\n- **Persistent error:** say the visit data couldn't be read right now, not that tracking is missing.\n\nThen offer the closest thing that still uses their ICP:\n1. Call `recommendations_companies_filters` (uses no quota).\n2. If its `availableSignals` lists a website-traffic-increase signal, call `recommendations_companies` with `filters.signals` set to that id and `pagination: { size: 10 }`.\n3. Otherwise sort by `signalScore`.\n4. State the existing-account quota usage first: the `recommendations_companies` rate in `account_usage`, times 10.\n\nThese are companies in the user's ICP whose activity is rising, not visitors to their site, so say that plainly. Then continue from Step 3 with the accounts the user picks.\n\n## Step 6 — Next actions\n\n1. **Save the call list to a Workspace table** — hand off to `save-or-export` (contacts tables use no quota).\n2. **Export to the CRM** — through `save-or-export`.\n3. **See the rest of your best accounts** — `work-my-accounts`.\n4. **No ICP profile?** Run `set-up-my-icp` so visitors can be checked for fit.\n"
}

SHA-256 of public snapshot: 4341ff7d72c285b58a67ed81ed125f10d185a34995e2ddeeb187f8ea16c6b444