Explorium

@explorium show me credit balance, then search for Series B SaaS companies in Austin with 50-200 employees and return audience stats before I pull the full list.

Your Explorium account has 9,847 credits remaining (paid tier). Applying your filters — Series B funding stage, SaaS industry, Austin metro location, employee count 50-200 — matches 127 businesses. The audience breaks down as: 68% have raised $10M-$25M, 22% are in marketing tech verticals, and 91% were founded after 2015. No credits were consumed for this stats preview. You can now enrich or export the full 127-record set; enrichment will cost ~127 credits.

This example chains credit-balance awareness with a zero-cost audience preview — a best practice before committing to metered enrichment. The MCP's Get Audience Stats tool lets you validate filter logic and result size without spending credits, but you must explicitly call Get Credit Balance first to see your runway.

@explorium match these three company domains to Explorium business IDs: acme.io, widgets.com, example.co — then enrich all three with firmographics including employee count, revenue estimate, and funding stage.

Matched: acme.io → business ID exp_12345, widgets.com → exp_67890, example.co → exp_11223. Enrichment complete (3 credits consumed). Acme.io: 180 employees, $15M-$25M estimated revenue, Series A, founded 2018. Widgets.com: 42 employees, $2M-$5M revenue, bootstrapped, founded 2020. Example.co: 310 employees, $50M+ revenue, Series C, founded 2014. All records include industry tags, HQ location, and tech stack signals.

This write-path example shows the two-step dance: Match Businesses returns IDs (credit-metered in production), then Enrich Business Firmographics adds detail (also metered, one credit per business in testing). Always check credit balance beforehand — a 50-record enrichment job will consume 50+ credits, and the MCP does not auto-throttle.

@explorium find prospects at Series B fintech companies who have 'Head of Growth' or 'VP Marketing' titles, return the first 20 matches, then draft a one-sentence outreach angle for each based on their company's funding stage and employee growth trend.

Retrieved 20 prospects matching your criteria (job consumed 4 credits). Example: Jane Doe, VP Marketing at PayCo (Series B, 95 employees, 40% YoY growth) — suggested angle: 'Congratulations on PayCo's recent Series B; as you scale from 95 to 150+ this year, I'd love to share how we help growth teams instrument attribution during hypergrowth.' The MCP returned prospect names, titles, LinkedIn URLs, and company firmographics; I synthesized the growth-trend insight from employee-count deltas and funding-stage metadata to personalize each pitch.

This synthesis example pairs Explorium's prospect-search tool with the AI's reasoning layer to generate contextual outreach copy. The MCP provides structured data (title, company, funding, headcount); the AI infers narrative hooks. Be aware: prospect searches are credit-metered, and the MCP does not return email addresses by default unless your Explorium subscription includes contact enrichment.

When Explorium beats manual LinkedIn scraping for cold outreach

A three-person sales team at a Series A SaaS company needs 200 qualified leads per week for cold email. They filter by industry, headcount, and job title, then enrich matched prospects with phone and email. Explorium's Match Prospects and Enrich tools let the team build that list in one Switchy session instead of toggling between LinkedIn Sales Navigator, ZoomInfo, and a spreadsheet. The credit model is predictable: matching costs credits per record, enrichment costs more, so the team checks Get Credit Balance first and stays under budget. This works until your list crosses 500 records per week—at that scale, you want a dedicated data ops person running batch jobs overnight, not an SDR waiting on API calls in Switchy. If you send fewer than 300 cold emails a week, Explorium in Switchy closes the loop from filter to enriched CSV in one workspace.

Why Explorium firmographics beat Googling before every demo

An account executive has four discovery calls scheduled and needs recent headcount, funding, and tech stack for each prospect company before dialing in. She pastes the four domain names into Switchy, calls Match Businesses to get Explorium IDs, then Enrich Business Firmographics to pull the data sheet. The entire workflow takes ninety seconds and costs four credits. Compare that to opening four browser tabs, hunting through Crunchbase and LinkedIn, and copy-pasting into a Google Doc. Explorium wins here because the data is normalized and the call is synchronous—no waiting on a CSV export. The edge case: if your AE preps more than twenty accounts a day, the credit burn adds up fast, and you should pre-enrich a master account list in your CRM instead. For ad-hoc research on fewer than ten accounts per session, Explorium in Switchy is the faster play.

When Get Audience Stats narrows your expansion list without burning credits

A customer success manager wants to identify which existing customers have grown past 100 employees in the last quarter, signaling readiness for an enterprise tier upsell. She sets a business filter for current customers, adds a headcount threshold, and calls Get Audience Stats to see the count before pulling the full list. The stats call costs zero credits, so she can iterate on filters—adding revenue bands or funding events—until the segment looks right. Only then does she run the actual search and enrichment. This two-step pattern prevents the classic mistake of burning fifty credits on a search that returns three irrelevant records. The threshold: if you're filtering more than five dimensions or need real-time alerts when a customer crosses a growth milestone, you want this data piped into your CRM with a scheduled sync, not queried ad-hoc in Switchy. For quarterly or monthly expansion reviews with fewer than three filter tweaks, Explorium's stats-first workflow saves both time and credits.