AI Company & Lead Researcher (Apify Actor)

Give it a list of company domains and your ICP description. For each domain it reads the homepage plus a few relevant pages (About / Pricing / Product), then uses an LLM (Gemini by default, Claude optional) to produce:

• a 2-3 sentence company summary
• an industry label
• an ICP fit score (1-10) with a specific reason
• buying signals found on the site (hiring, funding, launches, expansion)
• a personalized, non-generic outreach icebreaker

Typically chained after a discovery Actor (Google Maps Scraper, LinkedIn Company Scraper, Apollo-style leads finder) that produces the domain list.

Input

Getting an API key for $0

Default provider is Google Gemini, because its free tier is a standing allowance, not a trial: no credit card, no expiration, roughly 1,500 requests/day on gemini-2.5-flash.

1. Go to https://aistudio.google.com/apikey
2. Sign in with any Google account
3. Click "Create API key" - copy it

That's it - no billing setup. Set it as GEMINI_API_KEY (see below). One trade-off: Google may use free-tier prompts to improve its models, which is a non-issue here since you're only feeding it public company website text.

If you later want higher-quality analysis or hit Gemini's daily cap with real paying volume, switch llmProvider to anthropic and add a paid ANTHROPIC_API_KEY - the code already supports both, no rewrite needed.

Output (one dataset row per domain)

domain, companyName, companySummary, industry, icpFitScore, icpFitReason, buyingSignals, icebreaker, pagesCrawled, error

Monetization (Pay Per Event)

Two custom events, defined in .actor/pay_per_event.json:

• company-researched - charged once per domain successfully analyzed (primary event)
• company-failed - charged at a reduced rate for domains that couldn't be crawled (covers compute spent trying)

Starting price suggestion: $0.02 per company researched (~$20 per 1,000). On Gemini's free tier your per-call LLM cost is $0 (within the daily quota); if you switch to Claude Haiku it's roughly $0.001-0.003 per company at this text volume. Either way margin is wide even after Apify's 20% cut - raise the price once you have reviews, this is a floor, not a target.

Local development

npm install -g apify-cli
cd ai-lead-researcher
export GEMINI_API_KEY=AIza...     # free - see "Getting an API key for $0" above
apify run

Check storage/datasets/default/ for output after a local run.

Deploy to Apify

apify login          # opens browser, paste your Apify API token
apify push            # builds and uploads this Actor to your Apify account

Then in the Apify Console, on this Actor's page:

1. Settings -> Environment variables: add GEMINI_API_KEY (or ANTHROPIC_API_KEY if you switched providers) as a secret env var.
2. Publication -> Monetization: enable Pay Per Event, keep the synthetic apify-actor-start event on (free first 5s of compute), and import/confirm the company-researched / company-failed events and prices.
3. Turn off the apify-default-dataset-item synthetic event in Console - this Actor already charges per item explicitly via

   Actor.push_data(item, "company-researched")
   , so leaving both on double-charges users.
4. Write the Store listing (title, description, example input/output, screenshots) and set visibility to Public.

Zapier integration (for buyers)

No extra code needed - Apify's Zapier app already exposes:

• Trigger: "Finished Actor Run" -> fires when a run of this Actor completes
• Action: "Run Actor" -> lets a Zap kick off a run (e.g. from a new row in a Google Sheet of leads)
• Search: "Fetch Dataset Items" -> pulls the enriched rows into the next Zap step (CRM, Slack, Sheet, Notion...)

Buyers connect Apify to Zapier from their own Zapier account - once this Actor is public, it's usable in the Zap builder like any other Apify Actor.