← Back to the Brokerage CDP walkthrough
The firm layer · Brokerage

Memory for the Connected Brokerage

The brokerage promises the client a relationship with the firm, but every book is isolated (rightly), so when the roster changes, the firm forgets. This layer is that memory, built without breaking the isolation. The rule: identity and aggregates pool into a governed projection; content, history, and the mailbox never do. Each agent's book stays isolated (the moat). Across books, resolution links, it never merges: two agents who know the same client each keep their own relationship; the firm only learns “same human.”

$90KFIRM GCI
3AGENTS · 2 ACTIVE
3CROSS-AGENT LINKS
1CO-OWNED · COMPETITION
When an agent leaves, reassign by relationship path

The orphaned book routes to the agent who already has a link, not round-robin. The no-signal case is flagged honestly, not dressed up as a match. Each card below is the engine's own recommendation, carrying its own stated reason.

Susan ParkTom Gallagher
medium · referral path
Sphere connection: referred by Helen Park, who is known to Tom Gallagher.
Robert KingMaria Santos
strong · direct link
Direct relationship: already worked / known by Maria Santos.
Frank Daleload-balanced
none · honest fallback
No relationship signal: load-balanced fallback (human review).
Helen ParkTom Gallagher
strong · direct link
Direct relationship: already worked / known by Tom Gallagher.
Why this doesn't break the moat
Records and the mailbox stay per-agent and isolated. This whole layer is a read-mostly projection with governed visibility: the broker sees aggregates and resolved links; agents see their own book plus a co-ownership flag; nobody gets a merged dump of everyone's contacts. That's a customer data pool, not “merge everyone's CRM.”
Who sees what

Governance is the spine, not the headline. Brokers buy the outcome; these rules are why the agents say yes, and why this is not the surveillance version anyone could build. They ship opinionated: one matrix, not a matrix builder.

What poolsThe agent seesThe broker sees Another agent sees
Records, notes, message content, the mailboxThe moat. This is the row that never moves.Everything, unchangedNothingNothing
Resolved identity links (“same human”)Link, never merge. A false link leaks a client, so name-only is review.Own book, plus an unnamed co-ownership flagAggregate collision countsNothing until both agents confirm
Transaction facts: deals, sides, GCIThe firm already owns these. Pooling them breaks nothing.Own production, plus influence they earned elsewhereFirm rollups by agent and by cohortNothing
Individual activity: calls, opens, cadenceAggregates to the broker are fine. Individual activity is surveillance.Their ownNever, at any granularityNever
At the orphan momentThe one moment naming is on: the client needs an agent today.Sees their book leave with them, in writingA ranked reassignment with the reason shownThe named client, on assignment
The bright line
The graph responds to a departure. It never predicts one at the individual level. Recruiting intelligence pointed outward is a product Cloze already integrates; prediction pointed at your own roster is what burns the trust this layer runs on.
Stays with the firm
Transaction facts and the resolved links
the data prenup
Walks with the agent
Relationship history and the mailbox

Agreed while relations are good, so offboarding stops being a fight. It cuts both directions: the same architecture is the arrival-side answer to a recruit asking what the firm will be able to see of what they bring.

The payoff deck: firm analytics, almost free once the layer exists

Who drives firm GCI

AgentProductionInfluence
Tom Gallagheractive$42K+$10K
Maria Santosactive$26K
Dale Fosterdeparted$22K

Tom Gallagher's $10K of influence is GCI driven inside Maria Santos's book, by handing over one buyer (Paul Briggs). A flat per-agent production ranking cannot see it: the hidden originator, at firm scale.

Firm GCI by source cohort

Sphere$44K
Past Client$36K
Agent Referral$10K

The same cohort lens as Layer 4, rolled up across every agent's book. The broker sees which sources drive firm production, not just which agents.

Honesty notes (carried up from Layers 2 to 4): co-owned GCI is counted once, in the owning book (co-ownership is flagged, not double-billed). Cross-agent links are assisted and banded: a human confirms, and a name-only match is review, never auto, because a false cross-agent link leaks one agent's client to another. Reassignment is a ranked recommendation. Synthetic fixture; production wires the same engine to the real per-agent Cloze books. Every number on this page renders from brokerage/firm_graph.json, which the engine emits.