What it does
Real Estate Lead Scoring Pipeline merges Google Analytics 4 visitor behavior with HubSpot CRM contact history to compute a weighted buyer-intent score (listing views 35%, contact form 30%, email engagement 20%, time on site 15%). It ranks all visitors into hot (>=70), warm (>=40), or cold (<40) tiers, tags hot leads in HubSpot, and sends a daily digest to the assigned agent via Slack DM. Fully explainable scores with no black-box ML, GDPR/CCPA consent-mode compliant. Built for real estate brokerages and agents who want automated, explainable lead prioritization instead of manually cross-referencing web analytics and CRM data.
Example prompts
- Run the full lead scoring pipeline and send today's hot-lead digest
- Score these lead profiles by buyer intent
- Preview the hot and warm leads for this listing
- Explain how the buyer-intent score is calculated
Tools (8)
Tools the agent exposes — your AI client calls them automatically when it needs them.
- run_full — Run the full lead scoring pipeline: collect GA4 + HubSpot data, score all visitors by buyer intent, synthesize an LLM digest, return the complete AgentResult JSON.
- score_leads — Score an explicit array of lead profiles using the weighted intent formula and return ranked ScoredLead[]. Pure, deterministic.
- get_lead_detail — Score a single lead profile and return the full breakdown: weighted score, tier, top signals, component scores.
- preview_hot_leads — Preview the hot and warm lead list for a property without any CRM or Slack side-effects.
- explain_score — Return the scoring formula, tier thresholds, and component weight table.
- plan_inputs — Plan the inputs for a tool: returns questions, schema and a ready-to-edit example.
- discover_intent — Proactive intent discovery: given a freeform goal, restate it, ask clarifying questions, propose a concrete input.
- list_capabilities — List all available tools, the scoring formula, and tier thresholds.
What you'll need to connect
This agent will ask you for the following. You enter them when you connect — they're encrypted and never shared with the creator.
- Service account JSON · optionalIn Google Analytics, find your property ID under Admin → Property Settings. Then create a service-account JSON key in Google Cloud (IAM & Admin → Service Accounts → Keys → Add key → JSON) and give that service account Viewer access to the GA4 property.Paste the full JSON of your service-account key file (not a file path). FindAgent stores it securely and gives the agent a file path to it.Only sent to: analyticsdata.googleapis.com, oauth2.googleapis.com
- HubSpot API Key · optionalHubSpot private-app access token. Scope: contacts:read, contacts:write. Required for live CRM tagging.Get this from hubapi.com's account or API settings.Paste the value as a single line.Only sent to: api.hubapi.com
- Slack Bot Token · optionalSlack bot OAuth token (chat:write scope). Required to send the daily hot-lead digest DM.Create a Slack app (api.slack.com/apps), add the scopes the agent needs, install it to your workspace, and copy the bot/user token.Paste the value as a single line.Only sent to: slack.com
- Anthropic API Key · optionalOptional. Leave blank on a sampling-capable client to use the host model with no key.Create a key on the Anthropic Console API keys page (console.anthropic.com → API keys).Paste the value as a single line.Only sent to: api.anthropic.com
How you're protected
FindAgent runs these safety checks on every agent automatically. They're always on and can't be turned off.
- Prompt-injection scanning
Every request is checked for known prompt-injection and jailbreak attempts before the agent runs. This is always on.
- Secret-leak scanning
Every response is scanned for leaked API keys, tokens, and other secrets before it reaches you. This is always on.
