Next-Gen Custom Fields: Let Ace AI Write, Update & Report on Data You Never Thought Possible

What are AI-written custom fields in Follow Up Boss?

Follow Up Boss has always let teams add custom fields to contact records — a great feature for capturing notes, loan status, or referral source. The limitation has always been the same: someone on your team has to fill those fields in. If nobody does, they sit empty.

AI-written custom fields work differently. Instead of relying on manual entry, an AI layer reads every activity event on a contact — page views, property searches, text exchanges, email opens, call logs — and writes structured, machine-readable values to specific fields automatically. The fields update as behavior changes. They are always current because they are derived from the live data already flowing through your CRM.

Follow Up Ace installs a unified set of these fields into your Follow Up Boss account. The system is split into two tiers based on how they are produced and what plan you are on.

Which custom fields does Ace write, and what do they contain?

Ace manages fifteen custom fields organized into two groups. The free-tier fields update via webhooks in real time. The paid intelligence fields are populated by a deeper AI analysis run for contacts you have tagged for review.

Free fields — always on, webhook-driven

These seven fields are available on every Ace account at no additional cost. They update immediately when contact activity triggers a webhook from Follow Up Boss:

Paid Ace Trove fields — deep analysis for tagged contacts

When you enable Ace Trove, Ace runs a deeper AI analysis pass on contacts you have tagged for review. That analysis populates eight additional fields that require synthesizing unstructured data — notes, conversation history, IDX search patterns — into structured CRM values:

• customAceLeadType — Buyer / Seller / Investor / Buyer-Seller / Unknown, classified from behavioral patterns
• customAcePropertyProfile — AI-synthesized summary of property preferences from IDX search data
• customAceSearchArea — Geographic search areas synthesized from IDX activity
• customAceBuyerReadiness — Ready Now / Actively Looking / Researching / Passive / Unknown, assessed from behavioral signals
• customAceLeadSummary — AI-generated plain-English summary of the contact from notes and activity
• customAceNextAction — AI-recommended next step for this specific contact
• customAceSellerScore — Propensity-to-sell score (0–100) from property and behavioral signals
• customAceSellerTier — Very High / High / Moderate / Low / None, banded from the Seller Score

The timestamp field customAceLastAnalyzed records when each contact was last analyzed; it stays hidden when empty so it does not clutter records that have not been processed yet.

How does Ace AI actually write data into Follow Up Boss custom fields?

The mechanism differs between the two field tiers, but both write directly to Follow Up Boss via the API — meaning the values appear on the contact card immediately, are searchable, and are filterable inside FUB's native UI.

Webhook-driven updates (free tier)

Every time Follow Up Boss fires a webhook for a contact event — a new lead, a property view, a text message, a status change — Ace receives that event, re-scores the contact, and writes the updated value back to FUB. The round trip is near-instant. Score fields stay current without any scheduled job or manual trigger.

Ace Trove analysis (paid tier)

The deeper intelligence fields require an LLM pass over the contact's full history. You trigger this by tagging contacts for analysis, and Ace Trove processes them, writing structured values to the paid fields. The customAceLastAnalyzed date field tells you when each contact was last processed, so you can identify records due for a refresh.

The Seller Score fields are additionally refreshed nightly for Ace Trove accounts via a Seller Radar scan that incorporates property tenure, estimated equity, local appreciation data from the FHFA, area market pressure, and CRM seller signals.

What can you actually build with AI-written custom fields in FUB?

The value of any custom field depends on what you do with it. Because Ace fields are native FUB custom fields, they plug directly into everything Follow Up Boss already supports: filtering, sorting, Smart Lists, and automations. Below are the built-in recipe templates Ace ships with the Ace Trove.

Recipe: Hot Leads call queue

Filter on customAceScore >= 80 AND customAceTier = Hot, sorted by score descending. Save as a Smart List called something like "Hot — Call Now." The list reorders itself as Ace re-scores contacts throughout the day, so agents always start their session with the highest-intent leads at the top — no manual curation required.

Recipe: Stale high-value re-engagement

Filter on customAceScore >= 60 AND customAceDaysSinceInbound >= 14. These are leads with strong scores who have gone quiet — the type that often converts when re-engaged before they drift to a competitor. Route them into a re-engagement action plan automatically using the API-supported POST /actionPlansPeople endpoint.

Recipe: Ghost / at-risk owner alert

Filter on customAceTier = Dormant AND customAceDaysSinceInbound >= 30. This surfaces contacts whose engagement has cratered — the type that silently fall out of a pipeline. Team leads can use this view for coaching, reassignment decisions, or a final save attempt before archiving.

Recipe: Speed-to-lead accountability

Filter on customAceResponseTime above your team's SLA threshold. Use this for coaching rather than discipline — agents who see their own response times on a shared dashboard tend to self-correct quickly. It is also useful for recovering leads that were answered late; a slow first response does not have to mean a lost lead if you flag it and follow up strategically.

Recipe: Ready buyers fast-track (Ace Trove)

With the Ace Trove enabled, filter on customAceBuyerReadiness = Ready Now. These are contacts the AI assessed as ready to transact based on their behavioral signals. Routing them to your most active agents — or into a showing-request workflow — with the least friction possible is straightforward once the field exists and is populated.

How does Ace use custom fields to surface seller opportunities?

The customAceSellerScore and customAceSellerTier fields represent a different category of AI-written data: propensity modeling applied to your existing database rather than lead scoring based on inbound behavior.

The Seller Score (0–100) is computed from a weighted set of signals: property tenure, estimated equity modeled from a conservative mortgage calculation (not observed lien data), FHFA appreciation data for the area, local market pressure indicators, and CRM-level seller tags you or your team have applied. Nightly, the Seller Radar scan refreshes these scores across your account's contacts.

What this means practically: you can build a FUB Smart List filtered on customAceSellerTier = Very High or High and have a standing view of the homeowners in your database most likely to consider selling — without any manual outreach tracking or spreadsheet maintenance.

A few important caveats. Equity figures are modeled estimates, not appraisal data. The Seller Radar surfaces suggested outreach in the dashboard for agent review — suggestions are not auto-sent. And Seller Score values in Follow Up Boss custom fields are currently read from the Seller Radar dashboard; automatic write-back to a FUB custom field is on the roadmap but not yet wired.

Learn more about how Ace approaches property intelligence in the Agentic overview.

Can Claude or ChatGPT read and use these custom fields?

Yes. Follow Up Ace exposes your Follow Up Boss data — including all Ace custom fields — to Claude and ChatGPT via an MCP (Model Context Protocol) connector. Claude connects via the Streamable HTTP endpoint at https://followupace.com/mcp; ChatGPT connects via the SSE endpoint at https://followupace.com/api/mcp/sse/. Both surface the same 200+ tools covering contacts, activities, tasks, and pipeline data.

With that connector active, an agent can ask Claude directly: "Summarize the last three interactions with Sarah Chen and suggest a follow-up message given her Ace Buyer Readiness and preferred channel." The AI reads the custom field values you already have in FUB and incorporates them into the answer without you needing to copy-paste anything. See the Agentic page for a full walkthrough of the connector setup.

How to set up AI-written custom fields in Follow Up Boss — step by step

1. Connect Follow Up Boss. Sign into your Follow Up Ace account and complete the Follow Up Boss OAuth connection. Ace needs read and write access to populate fields on contact records.
2. Let Ace install the free fields. On first connection, Ace creates the free predictive fields — Ace Win Score and Ace Churn Risk — in your FUB account automatically. No manual field setup is required.
3. Verify the fields appear in FUB. Go to Admin → Custom Fields in Follow Up Boss and confirm you see the customAce* fields. If you have existing contacts, Ace begins scoring them as events arrive.
4. Build your first Smart List. In FUB, go to People → Filter. Sort by Ace Win Score descending (or filter Ace Churn Risk = High for the save-list). Save the view. This is your live priority queue.
5. Enable the Ace Trove for deeper fields. From the Ace admin dashboard, activate the Ace Trove. Pricing scales from $49/month for up to 5,000 contacts to $899/month for up to 500,000 contacts. The paid fields become available immediately after activation.
6. Tag contacts for AI analysis. Mark the contacts you want the Ace Trove to analyze deeply. Ace processes them and writes values to the intelligence fields — Expected GCI (est.), Opportunity, Seller Tier, and Last Analyzed.
7. Build recipes on top of the intelligence fields. Use the pre-built recipe guides in the Ace dashboard to create Smart Lists and action plan triggers for Ready Buyers, Investor Segments, and seller intent views.

What is the difference between free and paid Ace custom fields?

Do AI-written custom fields work with Fair Housing compliance?

This is a legitimate concern. Any AI system that classifies contacts and influences which ones receive outreach needs to be evaluated against Fair Housing standards. Ace's approach addresses this in two ways.

First, the classification fields — Lead Type, Buyer Readiness, Investor Segment — are based entirely on behavioral signals from the contact's own activity: their property searches, engagement patterns, and conversation history. They do not incorporate protected-class characteristics.

Second, Ace includes a Fair Housing compliance layer that scans outbound messages for language that could violate Fair Housing rules. The scanForComplianceViolations() function in the platform checks generated text before it is sent, flagging steering language, prohibited terms, and other compliance risks. You can read more about how this works on the Compliance page.

That said, how you act on AI-populated fields is ultimately your responsibility. Using a "Buyer Readiness = Ready Now" filter to prioritize outreach is appropriate; using any field as a proxy for a protected characteristic is not. Treat AI-written fields the same way you would treat any CRM segment — with the same Fair Housing judgment you apply to manual segmentation.

How do AI custom fields compare to building your own FUB custom fields manually?

You can absolutely build custom fields in Follow Up Boss manually — and many teams do. The difference comes down to who fills them in and how consistently that happens in practice.

Manual custom fields depend on agents entering data. That works well for fields that agents genuinely know and care about — closing date, referral source, buyer pre-approval status. It works less well for fields that require synthesizing activity data, like "how engaged is this lead" or "what properties are they looking at," because agents rarely have time to update those consistently across hundreds of contacts.

AI-written fields fill the gap. They handle the fields that would require a significant time investment to populate manually — engagement scores, behavioral summaries, channel preferences — and keep them updated continuously. Manual fields and AI fields coexist on the same contact card in FUB; there is no conflict between them.

For a broader view of what Ace adds to a Follow Up Boss workflow, the Guides section covers specific use cases including Zillow lead handling and pipeline velocity analysis.

Key takeaways

• Follow Up Ace writes six model-grounded custom fields to Follow Up Boss — Ace Win Score and Ace Churn Risk free, plus Expected GCI (est.), Opportunity, Seller Tier, and Last Analyzed through the paid Ace Trove.
• Free fields include Ace Score, Ace Tier, Ace Status, Response Time, Velocity Score, Days Since Inbound, and Preferred Channel. All update live from the FUB event stream.
• Ace Trove fields add Lead Type, Property Profile, Search Area, Buyer Readiness, Lead Summary, Next Action, Seller Score, and Seller Tier — all populated by AI analysis of the contact's full history.
• Every field is a native FUB custom field, filterable and sortable in the People view and usable in Smart List recipes.
• The Ace Trove is priced at $49–$899/month based on the number of contacts in your Follow Up Boss account.
• Claude and ChatGPT can read these fields via the MCP connector (Streamable HTTP at https://followupace.com/mcp; SSE at https://followupace.com/api/mcp/sse/).