Using AI to Instantly Score and Segment New Real Estate Leads

By the Follow Up Ace team· Last updated
Real estate agent reviewing an AI-generated lead scorecard on a laptop, with color-coded contact tiers — Hot, Warm, Cool — displayed in a Follow Up Boss CRM dashboard
Quick answer

Follow Up Ace's ACE Intelligence runs a nightly batch analysis across every contact in your Follow Up Boss account and writes AI-generated classification fields — lead type, property profile, search area, buyer readiness, a lead summary, and a recommended next action — directly into FUB custom fields alongside a rule-based engagement score (0–100) and a five-tier Hot/Warm/Cool/Cold/Dormant label. New leads also trigger a real-time fast-lane analysis (typically within minutes of creation), so agents always know who to call first without manually reviewing a single contact.

What does AI lead scoring actually do in a real estate CRM?

AI lead scoring reads every data point a contact generates — form fills, email replies, listing views passed through your CRM, call logs, stage changes, and notes — and distills them into a number that predicts how likely that person is to transact in the near term. Instead of a single opaque score, Follow Up Ace writes a multi-dimensional profile to Follow Up Boss so you can sort and filter on the dimension that matters for a given workflow.

The practical result: open FUB in the morning and your highest-probability contacts are already at the top. You are not deciding who to call — you are just working down the list.

What fields does ACE Intelligence write to Follow Up Boss?

ACE Intelligence creates and populates two groups of custom fields in your Follow Up Boss account (source: chat-app/shared/aceIntelligenceFieldsConfig.js):

Rule-based score and tier fields (free, webhook-driven — all accounts)

These fields are computed by a deterministic scoring engine (source: chat-app/utils/aceScoreEngine.js) and updated in real time as contacts generate activity in FUB — no AI Engine subscription required:

Field name What it measures Use case
ace_score Composite lead engagement score (0–100), event-weighted and recency-adjusted Primary sort field for daily call lists
ace_tier Hot / Warm / Cool / Cold / Dormant — derived from ace_score thresholds Filter smart lists by temperature in one click
ace_status Lifecycle stage: New / Contacted / Engaged / Active Client / Closed / Nurturing / Dormant Track pipeline progression without manual updates
ace_velocity_score Engagement velocity (0–100) derived from event volume in 7-day and 30-day windows Catch leads heating up before competitors do
ace_response_time Minutes from lead creation to first agent response Speed-to-lead accountability
ace_days_since_inbound Days since the contact last sent an inbound message or inquiry Surface contacts who have gone quiet
ace_preferred_channel The channel (sms / email / call) the contact most recently engages on Match outreach to the contact's preferred medium

AI-generated intelligence fields (AI Engine add-on)

The ACE Intelligence nightly batch and speed-to-lead fast lane write these six AI-generated fields for every contact in an AI Engine-enabled account (source: chat-app/shared/aceIntelligenceFieldsConfig.js — ACE_INTELLIGENCE_FIELDS):

Together these fields give any agent who picks up the phone an instant briefing without reading through years of notes.

How does ACE Intelligence's lead tier system work?

Each contact receives a composite ace_score (0–100) that maps to a tier label written to the ace_tier field (source: chat-app/utils/aceScoreEngine.js, lines 115–121 — TIER_THRESHOLDS):

Score range Tier Suggested action
75 – 100 Hot Call same day; prioritize scheduling
50 – 74 Warm Nurture with value content; weekly touch
25 – 49 Cool Automated drip; quarterly personal touch
1 – 24 Cold Long-cycle nurture; flag for seasonal campaigns
0 Dormant No meaningful activity; archive or re-permission

These tiers are live in FUB as a filterable dropdown, so creating a smart list of every Hot lead takes seconds — no export to a spreadsheet required.

When does ACE Intelligence analyze contacts — nightly batch or real time?

Both. The system uses two complementary paths:

Nightly account-wide batch

Every night, ACE Intelligence runs a batch analysis across all contacts in an AI Engine-enabled account. The batch system (built on OpenAI's Batch API) processes contacts in parallel chunks and writes the updated ace_* fields back to Follow Up Boss once scoring is complete. A minimum interval of 24 hours between analyses per contact prevents over-analysis (source: chat-app/firestore/functions/aceIntelligenceBatchAnalysis.js, line 28: MIN_TIME_BETWEEN_ANALYSES = 24 * 60 * 60 * 1000).

This means every morning your database is already re-scored. Contacts that were Warm last week and have since gone quiet are already re-tiered to Cool before you open FUB.

Real-time speed-to-lead fast lane

When a brand-new contact enters Follow Up Boss (a peopleCreated event), a dedicated fast-lane burst triggers immediately. The default quiet window for new leads is just 5 seconds, with a maximum delay cap of 60 seconds (source: chat-app/workers/aceAnalysisBurstScheduler.js, lines 52–55). The goal is a first AI analysis within minutes of the lead arriving — before the agent even picks up the phone.

For existing contacts, activity events such as stage changes, new notes, or inbound calls also trigger burst analysis through the same BullMQ queue, with a longer quiet window to batch rapid activity before scoring.

How do I set up AI lead scoring in Follow Up Boss?

  1. Connect your Follow Up Boss account from the AI Engine dashboard. Follow Up Ace reads your FUB data through the official API — no data export required.
  2. Choose an AI Engine tier based on your contact count: Starter ($49/mo, up to 5,000 contacts), Growth ($99/mo, up to 20,000), Team ($199/mo, up to 50,000), Brokerage ($349/mo, up to 100,000), Scale ($549/mo, up to 250,000), or Enterprise ($899/mo, up to 500,000) — source: chat-app/config/accountAiBillingConfig.js, lines 64–69.
  3. ACE Intelligence automatically creates all ace_* custom fields in your FUB account during first-run setup. No manual field configuration needed.
  4. The initial analysis batch begins processing your existing contacts. New contacts are scored on arrival.
  5. Build FUB smart lists using the new fields — for example, filter on ace_tier = Hot and sort by ace_score descending to get your call list for the day.

What is the difference between AI lead scoring and manual lead segmentation?

Manual segmentation requires an agent to read through contact history, make a judgment call, and update a tag or status field — a process that takes one to three minutes per contact and rarely gets done for the full database. It also reflects the agent's state of knowledge at a single point in time; a contact who went quiet three months ago and just re-engaged will stay in "Cold" until someone manually checks.

AI scoring is continuous and covers every contact equally. Because ACE Intelligence re-runs the nightly batch across the entire account, a contact that replied to an email yesterday will surface in this morning's Hot or Warm list without any manual action. The system also applies consistent criteria — it does not have good days or bad days, and it does not forget to update a record.

The practical upside for teams: agents spend time on conversations, not on database hygiene.

Does AI lead scoring work with compliance rules?

Yes. Follow Up Ace includes a built-in compliance layer that runs on every AI-generated message and suggestion. The scanForComplianceViolations() function (source: chat-app/utils/complianceGuard.js, line 293) checks text against Fair Housing Act prohibited language before anything reaches an agent's screen. This applies to AI-drafted follow-up suggestions that ACE Intelligence generates alongside the scoring output.

Learn more about how the compliance layer works on the Compliance page.

Can I use AI lead scoring data with Claude or ChatGPT via MCP?

Yes. Follow Up Ace's MCP (Model Context Protocol) connector exposes 215 tools to AI assistants like Claude and ChatGPT over a single URL (source: mcp-server/src/index.ts, line 3818). Once connected, you can ask Claude natural-language questions like "which of my Hot leads haven't been contacted in two weeks?" and get an answer drawn directly from your FUB data — including the ace_* scoring fields written by ACE Intelligence.

This makes the scored data actionable beyond the CRM: you can use it to draft personalized follow-up messages, build outreach plans, or analyze patterns across your pipeline — all in a conversational interface.

Which plan do I need for AI lead scoring?

ACE Intelligence and the nightly batch scoring are part of the AI Engine subscription, which is an account-level add-on separate from the per-seat plan. Individual agent seats are available on Free, Regular ($25/seat/month), or Pro ($55/seat/month) plans, with Pro required for voice chat (source: chat-app/routes/embed.js, line 2647: voiceChatEnabled: toPlan === 'pro').

The AI Engine tier is priced by contact count so that smaller teams are not paying for capacity they do not use. A single agent with 3,000 contacts qualifies for the Starter tier at $49/month; a brokerage with 80,000 contacts falls into Brokerage at $349/month.

See the Guides section for a walkthrough of how to set up your first AI Engine smart list in Follow Up Boss, and the Competitor Comparison page to see how ACE Intelligence stacks up against other CRM AI tools in the market.

Key takeaways

Try Follow Up Ace in your Follow Up Boss

Free to start, no sales call. Connect Follow Up Boss in one click and Ace works inside your CRM.

Get Started Free